Token | the |
Token ID | 262 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
manif | +0.231 |
incent | +0.219 |
ngth | +0.211 |
regulators | +0.199 |
undermin | +0.196 |
Neg logit contributions | |
Interstitial | -0.240 |
ovember | -0.219 |
DK | -0.219 |
ドラゴン | -0.202 |
ingen | -0.199 |
Token | experience |
Token ID | 1998 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
manif | +0.165 |
incent | +0.155 |
ngth | +0.149 |
regulators | +0.141 |
equations | +0.138 |
Neg logit contributions | |
Interstitial | -0.199 |
ovember | -0.183 |
DK | -0.183 |
ドラゴン | -0.170 |
ingen | -0.168 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
manif | +0.156 |
incent | +0.148 |
ngth | +0.144 |
regulators | +0.136 |
undermin | +0.134 |
Neg logit contributions | |
Interstitial | -0.134 |
ovember | -0.122 |
DK | -0.121 |
ドラゴン | -0.111 |
ingen | -0.110 |
Token | He |
Token ID | 679 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
manif | +0.134 |
incent | +0.128 |
ngth | +0.125 |
regulators | +0.118 |
equations | +0.117 |
Neg logit contributions | |
Interstitial | -0.105 |
ovember | -0.095 |
DK | -0.093 |
ドラゴン | -0.085 |
ingen | -0.085 |
Token | reass |
Token ID | 12719 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
manif | +0.018 |
incent | +0.017 |
ngth | +0.017 |
regulators | +0.016 |
undermin | +0.015 |
Neg logit contributions | |
Interstitial | -0.018 |
ovember | -0.016 |
DK | -0.016 |
ドラゴン | -0.015 |
ingen | -0.015 |
Token | ures |
Token ID | 942 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Interstitial | +0.029 |
ovember | +0.026 |
DK | +0.026 |
ドラゴン | +0.024 |
ingen | +0.024 |
Neg logit contributions | |
manif | -0.031 |
incent | -0.030 |
ngth | -0.029 |
regulators | -0.027 |
equations | -0.026 |
Token | Ryan |
Token ID | 6047 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
manif | +1.341 |
incent | +1.262 |
ngth | +1.213 |
regulators | +1.162 |
equations | +1.134 |
Neg logit contributions | |
Interstitial | -1.465 |
ovember | -1.338 |
DK | -1.323 |
ドラゴン | -1.232 |
ingen | -1.220 |
Token | that |
Token ID | 326 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Interstitial | +0.375 |
ovember | +0.342 |
DK | +0.341 |
ドラゴン | +0.314 |
ingen | +0.311 |
Neg logit contributions | |
manif | -0.376 |
incent | -0.356 |
ngth | -0.345 |
regulators | -0.325 |
undermin | -0.320 |
Token | he |
Token ID | 339 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
manif | +0.115 |
incent | +0.109 |
ngth | +0.105 |
regulators | +0.100 |
equations | +0.098 |
Neg logit contributions | |
Interstitial | -0.112 |
ovember | -0.102 |
DK | -0.101 |
ドラゴン | -0.093 |
ingen | -0.092 |
Token | will |
Token ID | 481 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.099 |
ngth | +0.096 |
regulators | +0.090 |
equations | +0.089 |
Neg logit contributions | |
Interstitial | -0.099 |
ovember | -0.090 |
DK | -0.090 |
ドラゴン | -0.083 |
ingen | -0.082 |
Token | recover |
Token ID | 8551 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
manif | +0.127 |
incent | +0.121 |
ngth | +0.115 |
regulators | +0.108 |
equations | +0.107 |
Neg logit contributions | |
Interstitial | -0.143 |
DK | -0.131 |
ovember | -0.131 |
ドラゴン | -0.122 |
ingen | -0.120 |
Token | ard |
Token ID | 446 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Interstitial | +0.087 |
ovember | +0.076 |
DK | +0.075 |
ドラゴン | +0.068 |
ingen | +0.065 |
Neg logit contributions | |
manif | -0.155 |
incent | -0.147 |
ngth | -0.145 |
regulators | -0.138 |
equations | -0.136 |
Token | has |
Token ID | 468 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Interstitial | +0.212 |
ovember | +0.192 |
DK | +0.191 |
ドラゴン | +0.176 |
ingen | +0.174 |
Neg logit contributions | |
manif | -0.228 |
incent | -0.217 |
ngth | -0.209 |
regulators | -0.198 |
equations | -0.195 |
Token | supported |
Token ID | 4855 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
manif | +0.100 |
incent | +0.094 |
ngth | +0.089 |
regulators | +0.086 |
equations | +0.085 |
Neg logit contributions | |
Interstitial | -0.105 |
DK | -0.095 |
ovember | -0.095 |
ドラゴン | -0.088 |
ingen | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
manif | +0.117 |
incent | +0.110 |
ngth | +0.105 |
regulators | +0.099 |
undermin | +0.097 |
Neg logit contributions | |
Interstitial | -0.150 |
DK | -0.137 |
ovember | -0.137 |
ドラゴン | -0.128 |
ingen | -0.126 |
Token | Industrial |
Token ID | 19034 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
manif | +0.107 |
incent | +0.100 |
ngth | +0.095 |
regulators | +0.091 |
equations | +0.088 |
Neg logit contributions | |
Interstitial | -0.135 |
DK | -0.123 |
ovember | -0.123 |
ドラゴン | -0.115 |
ingen | -0.114 |
Token | Hemp |
Token ID | 50060 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
manif | +0.157 |
incent | +0.148 |
ngth | +0.142 |
regulators | +0.133 |
equations | +0.130 |
Neg logit contributions | |
Interstitial | -0.191 |
ovember | -0.175 |
DK | -0.174 |
ドラゴン | -0.162 |
ingen | -0.161 |
Token | Farming |
Token ID | 39831 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
manif | +1.223 |
incent | +1.161 |
ngth | +1.117 |
regulators | +1.069 |
equations | +1.043 |
Neg logit contributions | |
Interstitial | -1.206 |
ovember | -1.086 |
DK | -1.085 |
ドラゴン | -1.006 |
ingen | -0.991 |
Token | Act |
Token ID | 2191 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
manif | +0.880 |
incent | +0.834 |
ngth | +0.786 |
regulators | +0.751 |
equations | +0.733 |
Neg logit contributions | |
Interstitial | -1.126 |
ovember | -1.036 |
DK | -1.032 |
ドラゴン | -0.964 |
ingen | -0.951 |
Token | that |
Token ID | 326 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
manif | +0.267 |
incent | +0.254 |
ngth | +0.247 |
regulators | +0.232 |
undermin | +0.230 |
Neg logit contributions | |
Interstitial | -0.239 |
ovember | -0.217 |
DK | -0.216 |
ドラゴン | -0.198 |
ingen | -0.196 |
Token | would |
Token ID | 561 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
manif | +0.022 |
incent | +0.021 |
ngth | +0.020 |
regulators | +0.019 |
undermin | +0.019 |
Neg logit contributions | |
Interstitial | -0.024 |
ovember | -0.022 |
DK | -0.022 |
ドラゴン | -0.020 |
ingen | -0.020 |
Token | allow |
Token ID | 1249 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
manif | +0.133 |
incent | +0.123 |
ngth | +0.119 |
regulators | +0.108 |
undermin | +0.107 |
Neg logit contributions | |
Interstitial | -0.208 |
ovember | -0.193 |
DK | -0.193 |
ドラゴン | -0.181 |
ingen | -0.179 |
Token | marks |
Token ID | 8849 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
Interstitial | +0.044 |
DK | +0.040 |
ovember | +0.040 |
ドラゴン | +0.037 |
ingen | +0.037 |
Neg logit contributions | |
manif | -0.041 |
incent | -0.039 |
ngth | -0.037 |
regulators | -0.035 |
equations | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
Interstitial | +0.080 |
ovember | +0.073 |
DK | +0.072 |
ドラゴン | +0.066 |
ingen | +0.066 |
Neg logit contributions | |
manif | -0.085 |
incent | -0.081 |
ngth | -0.078 |
regulators | -0.074 |
undermin | -0.073 |
Token | 8 |
Token ID | 807 |
Feature activation | +6.57e-02 |
Pos logit contributions | |
Interstitial | +0.022 |
ovember | +0.020 |
DK | +0.020 |
ドラゴン | +0.019 |
ingen | +0.019 |
Neg logit contributions | |
manif | -0.014 |
incent | -0.013 |
ngth | -0.012 |
regulators | -0.011 |
undermin | -0.011 |
Token | th |
Token ID | 400 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
manif | +0.055 |
incent | +0.052 |
ngth | +0.050 |
regulators | +0.047 |
equations | +0.046 |
Neg logit contributions | |
Interstitial | -0.057 |
DK | -0.052 |
ovember | -0.052 |
ドラゴン | -0.048 |
ingen | -0.047 |
Token | annual |
Token ID | 5079 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
manif | +0.221 |
incent | +0.207 |
ngth | +0.197 |
regulators | +0.187 |
undermin | +0.180 |
Neg logit contributions | |
Interstitial | -0.282 |
ovember | -0.259 |
DK | -0.258 |
ドラゴン | -0.242 |
ingen | -0.240 |
Token | Hemp |
Token ID | 50060 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
manif | +0.290 |
incent | +0.275 |
ngth | +0.262 |
regulators | +0.252 |
equations | +0.245 |
Neg logit contributions | |
Interstitial | -0.277 |
ovember | -0.251 |
DK | -0.250 |
ドラゴン | -0.230 |
ingen | -0.227 |
Token | History |
Token ID | 7443 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
manif | +1.325 |
incent | +1.260 |
ngth | +1.219 |
regulators | +1.165 |
undermin | +1.137 |
Neg logit contributions | |
Interstitial | -1.081 |
DK | -0.964 |
ovember | -0.962 |
ドラゴン | -0.888 |
ingen | -0.867 |
Token | Week |
Token ID | 6119 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Interstitial | +0.054 |
DK | +0.048 |
ovember | +0.048 |
ドラゴン | +0.043 |
ingen | +0.043 |
Neg logit contributions | |
manif | -0.082 |
incent | -0.079 |
ngth | -0.076 |
regulators | -0.073 |
equations | -0.071 |
Token | which |
Token ID | 543 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
manif | +0.103 |
incent | +0.098 |
ngth | +0.095 |
regulators | +0.090 |
undermin | +0.088 |
Neg logit contributions | |
Interstitial | -0.086 |
ovember | -0.078 |
DK | -0.077 |
ドラゴン | -0.071 |
ingen | -0.070 |
Token | runs |
Token ID | 4539 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
Interstitial | +0.055 |
ovember | +0.050 |
DK | +0.050 |
ドラゴン | +0.046 |
ingen | +0.046 |
Neg logit contributions | |
manif | -0.053 |
incent | -0.050 |
ngth | -0.048 |
regulators | -0.045 |
undermin | -0.044 |
Token | June |
Token ID | 2795 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Interstitial | +0.483 |
DK | +0.433 |
ovember | +0.432 |
ドラゴン | +0.394 |
ingen | +0.389 |
Neg logit contributions | |
manif | -0.631 |
incent | -0.600 |
ngth | -0.583 |
regulators | -0.554 |
undermin | -0.545 |
Token | Be |
Token ID | 1355 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
manif | +0.212 |
incent | +0.201 |
ngth | +0.197 |
regulators | +0.186 |
undermin | +0.183 |
Neg logit contributions | |
Interstitial | -0.167 |
ovember | -0.150 |
DK | -0.149 |
ドラゴン | -0.137 |
ingen | -0.134 |
Token | eg |
Token ID | 1533 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
manif | +0.292 |
incent | +0.276 |
ngth | +0.271 |
regulators | +0.255 |
equations | +0.251 |
Neg logit contributions | |
Interstitial | -0.235 |
DK | -0.209 |
ovember | -0.208 |
ドラゴン | -0.194 |
ingen | -0.187 |
Token | le |
Token ID | 293 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
manif | +0.030 |
incent | +0.029 |
ngth | +0.028 |
regulators | +0.027 |
equations | +0.026 |
Neg logit contributions | |
Interstitial | -0.022 |
ovember | -0.020 |
DK | -0.020 |
ドラゴン | -0.018 |
ゼウス | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
Interstitial | +0.218 |
ovember | +0.196 |
DK | +0.196 |
ドラゴン | +0.180 |
ingen | +0.175 |
Neg logit contributions | |
manif | -0.275 |
incent | -0.262 |
ngth | -0.256 |
regulators | -0.241 |
undermin | -0.236 |
Token | Colorado |
Token ID | 7492 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Interstitial | +0.072 |
ovember | +0.066 |
DK | +0.065 |
ドラゴン | +0.061 |
ingen | +0.060 |
Neg logit contributions | |
manif | -0.072 |
incent | -0.068 |
ngth | -0.065 |
regulators | -0.062 |
undermin | -0.061 |
Token | Hemp |
Token ID | 50060 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
manif | +0.292 |
incent | +0.277 |
ngth | +0.268 |
regulators | +0.255 |
undermin | +0.249 |
Neg logit contributions | |
Interstitial | -0.263 |
ovember | -0.238 |
DK | -0.237 |
ドラゴン | -0.218 |
ingen | -0.215 |
Token | Company |
Token ID | 5834 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
manif | +1.348 |
incent | +1.281 |
ngth | +1.238 |
regulators | +1.199 |
undermin | +1.165 |
Neg logit contributions | |
Interstitial | -1.011 |
ovember | -0.895 |
DK | -0.890 |
ドラゴン | -0.820 |
ingen | -0.798 |
Token | . |
Token ID | 13 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
Interstitial | +0.165 |
ovember | +0.148 |
DK | +0.146 |
ドラゴン | +0.134 |
ingen | +0.132 |
Neg logit contributions | |
manif | -0.214 |
incent | -0.204 |
ngth | -0.196 |
regulators | -0.189 |
undermin | -0.185 |
Token | � |
Token ID | 564 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Interstitial | +0.030 |
ovember | +0.027 |
DK | +0.026 |
ドラゴン | +0.024 |
ingen | +0.024 |
Neg logit contributions | |
manif | -0.036 |
incent | -0.035 |
ngth | -0.034 |
regulators | -0.032 |
equations | -0.031 |
Token | � |
Token ID | 250 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Interstitial | +0.024 |
DK | +0.022 |
ovember | +0.022 |
ドラゴン | +0.020 |
ingen | +0.020 |
Neg logit contributions | |
manif | -0.020 |
incent | -0.019 |
ngth | -0.019 |
regulators | -0.017 |
ratios | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | +7.92e-02 |
Pos logit contributions | |
manif | +0.022 |
incent | +0.021 |
ngth | +0.021 |
regulators | +0.020 |
equations | +0.019 |
Neg logit contributions | |
Interstitial | -0.017 |
ovember | -0.016 |
DK | -0.016 |
ドラゴン | -0.014 |
ingen | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
Interstitial | +0.030 |
ovember | +0.027 |
DK | +0.027 |
ドラゴン | +0.024 |
ingen | +0.024 |
Neg logit contributions | |
manif | -0.037 |
incent | -0.036 |
ngth | -0.035 |
regulators | -0.033 |
equations | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
manif | +0.019 |
incent | +0.017 |
ngth | +0.017 |
regulators | +0.017 |
equations | +0.016 |
Neg logit contributions | |
Interstitial | -0.016 |
ovember | -0.014 |
DK | -0.014 |
ドラゴン | -0.013 |
ingen | -0.013 |
Token | Israel |
Token ID | 14040 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Interstitial | +0.039 |
ovember | +0.036 |
DK | +0.035 |
ドラゴン | +0.032 |
ingen | +0.032 |
Neg logit contributions | |
manif | -0.050 |
incent | -0.047 |
ngth | -0.046 |
regulators | -0.044 |
equations | -0.043 |
Token | also |
Token ID | 635 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
manif | +0.205 |
incent | +0.194 |
ngth | +0.188 |
regulators | +0.177 |
undermin | +0.174 |
Neg logit contributions | |
Interstitial | -0.202 |
ovember | -0.184 |
DK | -0.183 |
ドラゴン | -0.168 |
ingen | -0.167 |
Token | nurt |
Token ID | 23868 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
manif | +0.031 |
incent | +0.029 |
ngth | +0.028 |
regulators | +0.026 |
equations | +0.026 |
Neg logit contributions | |
Interstitial | -0.034 |
ovember | -0.031 |
DK | -0.031 |
ドラゴン | -0.029 |
ingen | -0.028 |
Token | ures |
Token ID | 942 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
manif | +0.079 |
incent | +0.074 |
ngth | +0.072 |
regulators | +0.068 |
equations | +0.067 |
Neg logit contributions | |
Interstitial | -0.077 |
ovember | -0.070 |
DK | -0.070 |
ドラゴン | -0.064 |
ingen | -0.063 |
Token | separation |
Token ID | 14139 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
manif | +1.101 |
incent | +1.036 |
ngth | +0.997 |
regulators | +0.939 |
equations | +0.926 |
Neg logit contributions | |
Interstitial | -1.239 |
ovember | -1.141 |
DK | -1.135 |
ドラゴン | -1.049 |
ingen | -1.040 |
Token | within |
Token ID | 1626 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
manif | +0.260 |
incent | +0.245 |
ngth | +0.237 |
regulators | +0.225 |
equations | +0.221 |
Neg logit contributions | |
Interstitial | -0.253 |
ovember | -0.231 |
DK | -0.230 |
ドラゴン | -0.211 |
ingen | -0.210 |
Token | the |
Token ID | 262 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
Interstitial | +0.035 |
ovember | +0.032 |
DK | +0.032 |
ドラゴン | +0.030 |
ingen | +0.029 |
Neg logit contributions | |
manif | -0.033 |
incent | -0.031 |
ngth | -0.030 |
regulators | -0.028 |
undermin | -0.028 |
Token | West |
Token ID | 2688 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
Interstitial | +0.028 |
DK | +0.026 |
ovember | +0.026 |
ドラゴン | +0.024 |
lan | +0.024 |
Neg logit contributions | |
manif | -0.028 |
incent | -0.027 |
ngth | -0.026 |
regulators | -0.024 |
undermin | -0.024 |
Token | Bank |
Token ID | 5018 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
manif | +0.706 |
incent | +0.675 |
ngth | +0.658 |
regulators | +0.631 |
equations | +0.623 |
Neg logit contributions | |
Interstitial | -0.420 |
ovember | -0.371 |
DK | -0.370 |
ドラゴン | -0.329 |
ingen | -0.325 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
Interstitial | +0.001 |
DK | +0.001 |
ovember | +0.001 |
ドラゴン | +0.001 |
ingen | +0.001 |
Neg logit contributions | |
manif | -0.001 |
incent | -0.001 |
ngth | -0.001 |
regulators | -0.001 |
undermin | -0.001 |
Token | first |
Token ID | 717 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Interstitial | +0.036 |
ovember | +0.033 |
DK | +0.033 |
ドラゴン | +0.030 |
ingen | +0.030 |
Neg logit contributions | |
manif | -0.034 |
incent | -0.032 |
ngth | -0.031 |
regulators | -0.029 |
equations | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
manif | +0.265 |
incent | +0.250 |
ngth | +0.241 |
regulators | +0.227 |
undermin | +0.223 |
Neg logit contributions | |
Interstitial | -0.294 |
ovember | -0.270 |
DK | -0.270 |
ドラゴン | -0.249 |
ingen | -0.248 |
Token | ever |
Token ID | 964 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
Interstitial | +0.070 |
DK | +0.064 |
ovember | +0.064 |
ドラゴン | +0.059 |
lan | +0.059 |
Neg logit contributions | |
manif | -0.069 |
incent | -0.065 |
ngth | -0.063 |
undermin | -0.059 |
regulators | -0.059 |
Token | Hawaii |
Token ID | 13708 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
manif | +0.657 |
incent | +0.620 |
ngth | +0.593 |
regulators | +0.570 |
equations | +0.557 |
Neg logit contributions | |
Interstitial | -0.653 |
ovember | -0.596 |
DK | -0.596 |
ドラゴン | -0.548 |
ingen | -0.545 |
Token | Hemp |
Token ID | 50060 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Interstitial | +0.145 |
DK | +0.131 |
ovember | +0.130 |
ドラゴン | +0.120 |
ingen | +0.119 |
Neg logit contributions | |
manif | -0.160 |
incent | -0.152 |
ngth | -0.146 |
regulators | -0.139 |
undermin | -0.137 |
Token | Conference |
Token ID | 8785 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
manif | +1.308 |
incent | +1.249 |
ngth | +1.206 |
regulators | +1.157 |
equations | +1.129 |
Neg logit contributions | |
Interstitial | -1.010 |
DK | -0.903 |
ovember | -0.895 |
ドラゴン | -0.827 |
ingen | -0.810 |
Token | in |
Token ID | 287 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
Interstitial | +0.244 |
DK | +0.219 |
ovember | +0.219 |
ドラゴン | +0.201 |
ingen | +0.198 |
Neg logit contributions | |
manif | -0.287 |
incent | -0.273 |
ngth | -0.264 |
regulators | -0.251 |
equations | -0.246 |
Token | H |
Token ID | 367 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Interstitial | +0.063 |
ovember | +0.056 |
DK | +0.056 |
ドラゴン | +0.050 |
ingen | +0.050 |
Neg logit contributions | |
manif | -0.088 |
incent | -0.084 |
ngth | -0.081 |
regulators | -0.078 |
equations | -0.077 |
Token | ilo |
Token ID | 18526 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Interstitial | +0.128 |
ovember | +0.105 |
DK | +0.104 |
ドラゴン | +0.092 |
ingen | +0.090 |
Neg logit contributions | |
manif | -0.308 |
incent | -0.299 |
ngth | -0.292 |
regulators | -0.280 |
equations | -0.277 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
Interstitial | +0.124 |
ovember | +0.112 |
DK | +0.112 |
ドラゴン | +0.102 |
ingen | +0.101 |
Neg logit contributions | |
manif | -0.149 |
incent | -0.142 |
ngth | -0.138 |
regulators | -0.130 |
undermin | -0.129 |
Token | Un |
Token ID | 791 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Interstitial | +0.240 |
ovember | +0.220 |
DK | +0.219 |
ドラゴン | +0.201 |
ingen | +0.199 |
Neg logit contributions | |
manif | -0.260 |
incent | -0.247 |
ngth | -0.239 |
regulators | -0.225 |
undermin | -0.222 |
Token | ilateral |
Token ID | 14796 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
manif | +0.318 |
incent | +0.302 |
ngth | +0.292 |
regulators | +0.277 |
equations | +0.273 |
Neg logit contributions | |
Interstitial | -0.254 |
ovember | -0.230 |
DK | -0.230 |
ドラゴン | -0.211 |
ingen | -0.206 |
Token | de |
Token ID | 390 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
manif | +0.270 |
incent | +0.257 |
ngth | +0.249 |
regulators | +0.235 |
equations | +0.232 |
Neg logit contributions | |
Interstitial | -0.228 |
ovember | -0.210 |
DK | -0.208 |
ドラゴン | -0.191 |
ingen | -0.188 |
Token | Ind |
Token ID | 1423 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
manif | +0.117 |
incent | +0.111 |
ngth | +0.108 |
regulators | +0.102 |
undermin | +0.100 |
Neg logit contributions | |
Interstitial | -0.102 |
ovember | -0.093 |
DK | -0.092 |
ドラゴン | -0.084 |
ingen | -0.083 |
Token | epend |
Token ID | 2690 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
manif | +0.400 |
incent | +0.380 |
ngth | +0.367 |
regulators | +0.347 |
equations | +0.342 |
Neg logit contributions | |
Interstitial | -0.358 |
DK | -0.326 |
ovember | -0.323 |
ドラゴン | -0.305 |
ingen | -0.291 |
Token | encia |
Token ID | 29634 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
manif | +0.252 |
incent | +0.238 |
ngth | +0.229 |
regulators | +0.210 |
equations | +0.206 |
Neg logit contributions | |
Interstitial | -0.342 |
ovember | -0.316 |
DK | -0.316 |
ドラゴン | -0.298 |
ingen | -0.289 |
Token | ) |
Token ID | 8 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
manif | +1.279 |
incent | +1.217 |
ngth | +1.174 |
regulators | +1.111 |
equations | +1.099 |
Neg logit contributions | |
Interstitial | -1.022 |
ovember | -0.939 |
DK | -0.929 |
ドラゴン | -0.850 |
ingen | -0.837 |
Token | could |
Token ID | 714 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Interstitial | +0.072 |
ovember | +0.066 |
DK | +0.065 |
ドラゴン | +0.060 |
ingen | +0.060 |
Neg logit contributions | |
manif | -0.072 |
incent | -0.068 |
ngth | -0.066 |
regulators | -0.062 |
undermin | -0.061 |
Token | be |
Token ID | 307 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
Interstitial | +0.103 |
DK | +0.095 |
ovember | +0.095 |
ドラゴン | +0.088 |
lan | +0.087 |
Neg logit contributions | |
manif | -0.091 |
incent | -0.086 |
ngth | -0.082 |
regulators | -0.077 |
equations | -0.076 |
Token | re |
Token ID | 302 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Interstitial | +0.079 |
ovember | +0.073 |
DK | +0.072 |
ドラゴン | +0.066 |
lan | +0.066 |
Neg logit contributions | |
manif | -0.078 |
incent | -0.073 |
ngth | -0.070 |
regulators | -0.067 |
undermin | -0.066 |
Token | ph |
Token ID | 746 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
manif | +0.243 |
incent | +0.229 |
ngth | +0.222 |
regulators | +0.208 |
equations | +0.205 |
Neg logit contributions | |
Interstitial | -0.250 |
DK | -0.228 |
ovember | -0.228 |
ドラゴン | -0.210 |
ingen | -0.207 |
Token | While |
Token ID | 2893 |
Feature activation | -8.79e-02 |
Pos logit contributions | |
manif | +0.171 |
incent | +0.164 |
ngth | +0.160 |
regulators | +0.153 |
equations | +0.150 |
Neg logit contributions | |
Interstitial | -0.136 |
ovember | -0.124 |
DK | -0.122 |
ドラゴン | -0.111 |
ingen | -0.111 |
Token | finding |
Token ID | 4917 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
Interstitial | +0.079 |
ovember | +0.072 |
DK | +0.072 |
ドラゴン | +0.067 |
ingen | +0.066 |
Neg logit contributions | |
manif | -0.071 |
incent | -0.067 |
ngth | -0.065 |
regulators | -0.061 |
undermin | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
Interstitial | +0.382 |
ovember | +0.349 |
DK | +0.348 |
ドラゴン | +0.321 |
ingen | +0.319 |
Neg logit contributions | |
manif | -0.360 |
incent | -0.340 |
ngth | -0.329 |
regulators | -0.309 |
equations | -0.304 |
Token | " |
Token ID | 366 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
manif | +0.038 |
incent | +0.035 |
ngth | +0.034 |
regulators | +0.031 |
equations | +0.031 |
Neg logit contributions | |
Interstitial | -0.058 |
ovember | -0.054 |
DK | -0.054 |
ドラゴン | -0.050 |
ingen | -0.050 |
Token | fail |
Token ID | 32165 |
Feature activation | +5.80e-02 |
Pos logit contributions | |
manif | +0.082 |
incent | +0.077 |
ngth | +0.075 |
regulators | +0.071 |
undermin | +0.070 |
Neg logit contributions | |
Interstitial | -0.075 |
ovember | -0.069 |
DK | -0.068 |
ドラゴン | -0.063 |
ingen | -0.062 |
Token | ure |
Token ID | 495 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
manif | +0.056 |
incent | +0.054 |
ngth | +0.052 |
regulators | +0.050 |
undermin | +0.049 |
Neg logit contributions | |
Interstitial | -0.042 |
ovember | -0.038 |
DK | -0.038 |
ドラゴン | -0.034 |
ingen | -0.034 |
Token | mode |
Token ID | 4235 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
manif | +1.162 |
incent | +1.097 |
ngth | +1.055 |
regulators | +1.003 |
equations | +0.989 |
Neg logit contributions | |
Interstitial | -1.136 |
ovember | -1.040 |
DK | -1.038 |
ドラゴン | -0.953 |
ingen | -0.944 |
Token | " |
Token ID | 1 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
manif | +0.042 |
incent | +0.040 |
ngth | +0.038 |
regulators | +0.036 |
equations | +0.036 |
Neg logit contributions | |
Interstitial | -0.043 |
ovember | -0.039 |
DK | -0.039 |
ドラゴン | -0.036 |
ingen | -0.035 |
Token | affected |
Token ID | 5676 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
manif | +0.209 |
incent | +0.198 |
ngth | +0.191 |
regulators | +0.180 |
undermin | +0.177 |
Neg logit contributions | |
Interstitial | -0.208 |
ovember | -0.190 |
DK | -0.189 |
ドラゴン | -0.174 |
ingen | -0.173 |
Token | the |
Token ID | 262 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
Interstitial | +0.084 |
ovember | +0.076 |
DK | +0.076 |
ドラゴン | +0.071 |
lan | +0.070 |
Neg logit contributions | |
manif | -0.080 |
incent | -0.075 |
ngth | -0.073 |
regulators | -0.068 |
undermin | -0.067 |
Token | air |
Token ID | 1633 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
manif | +0.123 |
incent | +0.116 |
ngth | +0.112 |
regulators | +0.102 |
undermin | +0.101 |
Neg logit contributions | |
Interstitial | -0.178 |
DK | -0.165 |
ovember | -0.165 |
ドラゴン | -0.154 |
lan | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
Interstitial | +0.113 |
ovember | +0.102 |
DK | +0.102 |
ドラゴン | +0.094 |
ingen | +0.093 |
Neg logit contributions | |
manif | -0.131 |
incent | -0.124 |
ngth | -0.120 |
regulators | -0.114 |
equations | -0.112 |
Token | initially |
Token ID | 7317 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Interstitial | +0.021 |
ovember | +0.019 |
DK | +0.019 |
ドラゴン | +0.018 |
ingen | +0.017 |
Neg logit contributions | |
manif | -0.018 |
incent | -0.017 |
ngth | -0.016 |
regulators | -0.015 |
undermin | -0.015 |
Token | failing |
Token ID | 9894 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
manif | +0.317 |
incent | +0.299 |
ngth | +0.287 |
regulators | +0.273 |
equations | +0.268 |
Neg logit contributions | |
Interstitial | -0.314 |
ovember | -0.287 |
DK | -0.285 |
ドラゴン | -0.264 |
ingen | -0.260 |
Token | , |
Token ID | 11 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
Interstitial | +0.065 |
ovember | +0.059 |
DK | +0.059 |
ドラゴン | +0.054 |
ingen | +0.053 |
Neg logit contributions | |
manif | -0.071 |
incent | -0.067 |
ngth | -0.065 |
regulators | -0.062 |
undermin | -0.061 |
Token | sec |
Token ID | 792 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
manif | +0.041 |
incent | +0.039 |
ngth | +0.037 |
regulators | +0.035 |
undermin | +0.034 |
Neg logit contributions | |
Interstitial | -0.046 |
ovember | -0.042 |
DK | -0.042 |
ドラゴン | -0.039 |
ingen | -0.039 |
Token | ures |
Token ID | 942 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
manif | +0.107 |
incent | +0.102 |
ngth | +0.099 |
regulators | +0.093 |
undermin | +0.092 |
Neg logit contributions | |
Interstitial | -0.095 |
ovember | -0.086 |
DK | -0.086 |
ドラゴン | -0.079 |
ingen | -0.078 |
Token | mark |
Token ID | 1317 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
manif | +1.117 |
incent | +1.049 |
ngth | +1.006 |
regulators | +0.959 |
equations | +0.939 |
Neg logit contributions | |
Interstitial | -1.187 |
ovember | -1.091 |
DK | -1.081 |
ドラゴン | -1.000 |
ingen | -0.993 |
Token | ( |
Token ID | 357 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
manif | +0.148 |
incent | +0.140 |
ngth | +0.136 |
regulators | +0.128 |
equations | +0.127 |
Neg logit contributions | |
Interstitial | -0.133 |
ovember | -0.120 |
DK | -0.120 |
ドラゴン | -0.110 |
ingen | -0.109 |
Token | 1 |
Token ID | 16 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
manif | +0.103 |
incent | +0.098 |
ngth | +0.096 |
regulators | +0.091 |
equations | +0.090 |
Neg logit contributions | |
Interstitial | -0.072 |
ovember | -0.065 |
DK | -0.064 |
ドラゴン | -0.058 |
ingen | -0.057 |
Token | – |
Token ID | 1906 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Interstitial | +0.040 |
ovember | +0.035 |
DK | +0.034 |
ドラゴン | +0.031 |
ingen | +0.030 |
Neg logit contributions | |
manif | -0.075 |
incent | -0.072 |
ngth | -0.070 |
regulators | -0.067 |
equations | -0.066 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
Interstitial | +0.198 |
ovember | +0.176 |
DK | +0.174 |
ドラゴン | +0.156 |
ingen | +0.155 |
Neg logit contributions | |
manif | -0.310 |
incent | -0.296 |
ngth | -0.290 |
regulators | -0.275 |
equations | -0.271 |
Token | sensor |
Token ID | 12694 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
manif | +0.112 |
incent | +0.105 |
ngth | +0.102 |
regulators | +0.095 |
undermin | +0.093 |
Neg logit contributions | |
Interstitial | -0.133 |
ovember | -0.122 |
DK | -0.122 |
ドラゴン | -0.113 |
ingen | -0.112 |
Token | at |
Token ID | 379 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
manif | +0.270 |
incent | +0.255 |
ngth | +0.247 |
regulators | +0.233 |
equations | +0.229 |
Neg logit contributions | |
Interstitial | -0.268 |
ovember | -0.245 |
DK | -0.244 |
ドラゴン | -0.225 |
ingen | -0.223 |
Token | all |
Token ID | 477 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
manif | +0.029 |
incent | +0.027 |
ngth | +0.026 |
regulators | +0.025 |
undermin | +0.024 |
Neg logit contributions | |
Interstitial | -0.029 |
ovember | -0.026 |
DK | -0.026 |
ドラゴン | -0.024 |
ingen | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
manif | +0.079 |
incent | +0.075 |
ngth | +0.072 |
regulators | +0.067 |
undermin | +0.066 |
Neg logit contributions | |
Interstitial | -0.101 |
ovember | -0.093 |
DK | -0.093 |
ドラゴン | -0.086 |
ingen | -0.085 |
Token | pert |
Token ID | 11766 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
manif | +0.070 |
incent | +0.067 |
ngth | +0.065 |
regulators | +0.061 |
equations | +0.061 |
Neg logit contributions | |
Interstitial | -0.056 |
ovember | -0.050 |
DK | -0.050 |
ドラゴン | -0.045 |
ingen | -0.045 |
Token | ures |
Token ID | 942 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
manif | +0.045 |
incent | +0.043 |
ngth | +0.041 |
regulators | +0.038 |
undermin | +0.038 |
Neg logit contributions | |
Interstitial | -0.048 |
ovember | -0.044 |
DK | -0.044 |
ドラゴン | -0.041 |
ingen | -0.041 |
Token | – |
Token ID | 784 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
manif | +1.223 |
incent | +1.157 |
ngth | +1.125 |
regulators | +1.071 |
ratios | +1.059 |
Neg logit contributions | |
Interstitial | -1.043 |
ovember | -0.939 |
DK | -0.933 |
ドラゴン | -0.853 |
ingen | -0.845 |
Token | but |
Token ID | 475 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
manif | +0.061 |
incent | +0.058 |
ngth | +0.056 |
regulators | +0.052 |
undermin | +0.052 |
Neg logit contributions | |
Interstitial | -0.069 |
ovember | -0.063 |
DK | -0.063 |
ドラゴン | -0.059 |
ingen | -0.058 |
Token | not |
Token ID | 407 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
manif | +0.020 |
incent | +0.019 |
ngth | +0.018 |
regulators | +0.017 |
undermin | +0.017 |
Neg logit contributions | |
Interstitial | -0.022 |
ovember | -0.020 |
DK | -0.020 |
ドラゴン | -0.019 |
ingen | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
manif | +0.038 |
incent | +0.036 |
ngth | +0.035 |
regulators | +0.033 |
undermin | +0.033 |
Neg logit contributions | |
Interstitial | -0.039 |
ovember | -0.036 |
DK | -0.036 |
ドラゴン | -0.033 |
ingen | -0.033 |
Token | great |
Token ID | 1049 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
manif | +0.248 |
incent | +0.234 |
ngth | +0.226 |
regulators | +0.212 |
undermin | +0.208 |
Neg logit contributions | |
Interstitial | -0.266 |
ovember | -0.244 |
DK | -0.243 |
ドラゴン | -0.224 |
ingen | -0.223 |
Token | accusations |
Token ID | 14227 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Interstitial | +0.799 |
ovember | +0.735 |
DK | +0.734 |
ドラゴン | +0.682 |
ingen | +0.677 |
Neg logit contributions | |
manif | -0.657 |
incent | -0.620 |
ngth | -0.601 |
regulators | -0.556 |
undermin | -0.549 |
Token | de |
Token ID | 390 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Interstitial | +0.135 |
ovember | +0.123 |
DK | +0.123 |
ドラゴン | +0.114 |
ingen | +0.112 |
Neg logit contributions | |
manif | -0.132 |
incent | -0.125 |
ngth | -0.119 |
regulators | -0.113 |
undermin | -0.111 |
Token | l |
Token ID | 300 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Interstitial | +0.078 |
ovember | +0.071 |
DK | +0.071 |
ドラゴン | +0.066 |
ingen | +0.065 |
Neg logit contributions | |
manif | -0.073 |
incent | -0.069 |
ngth | -0.067 |
regulators | -0.063 |
undermin | -0.062 |
Token | é |
Token ID | 2634 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Interstitial | +0.257 |
ovember | +0.229 |
DK | +0.228 |
ドラゴン | +0.208 |
ingen | +0.203 |
Neg logit contributions | |
manif | -0.357 |
incent | -0.342 |
ngth | -0.331 |
regulators | -0.315 |
undermin | -0.310 |
Token | git |
Token ID | 18300 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
manif | +0.116 |
incent | +0.111 |
ngth | +0.108 |
regulators | +0.101 |
undermin | +0.100 |
Neg logit contributions | |
Interstitial | -0.094 |
ovember | -0.084 |
DK | -0.084 |
ドラゴン | -0.077 |
ingen | -0.076 |
Token | im |
Token ID | 320 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Interstitial | +0.231 |
DK | +0.205 |
ovember | +0.204 |
ドラゴン | +0.183 |
ingen | +0.179 |
Neg logit contributions | |
manif | -0.366 |
incent | -0.351 |
ngth | -0.342 |
regulators | -0.325 |
undermin | -0.321 |
Token | ité |
Token ID | 43816 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
manif | +1.246 |
incent | +1.190 |
ngth | +1.157 |
regulators | +1.091 |
equations | +1.077 |
Neg logit contributions | |
Interstitial | -1.003 |
DK | -0.902 |
ovember | -0.899 |
ドラゴン | -0.815 |
ingen | -0.797 |
Token | , |
Token ID | 11 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
Interstitial | +0.525 |
ovember | +0.479 |
DK | +0.479 |
ドラゴン | +0.441 |
ingen | +0.436 |
Neg logit contributions | |
manif | -0.523 |
incent | -0.495 |
ngth | -0.477 |
regulators | -0.449 |
undermin | -0.444 |
Token | le |
Token ID | 443 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Interstitial | +0.075 |
ovember | +0.068 |
DK | +0.068 |
ドラゴン | +0.063 |
ingen | +0.062 |
Neg logit contributions | |
manif | -0.076 |
incent | -0.072 |
ngth | -0.069 |
regulators | -0.065 |
undermin | -0.064 |
Token | Command |
Token ID | 9455 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
manif | +0.011 |
incent | +0.010 |
ngth | +0.010 |
regulators | +0.009 |
undermin | +0.009 |
Neg logit contributions | |
Interstitial | -0.012 |
ovember | -0.011 |
DK | -0.011 |
ドラゴン | -0.010 |
ingen | -0.010 |
Token | ement |
Token ID | 972 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
manif | +0.012 |
incent | +0.012 |
ngth | +0.012 |
regulators | +0.011 |
equations | +0.011 |
Neg logit contributions | |
Interstitial | -0.002 |
DK | -0.001 |
ovember | -0.001 |
ドラゴン | -0.001 |
ingen | -0.001 |
Token | 2011 |
Token ID | 2813 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
manif | +0.032 |
incent | +0.030 |
ngth | +0.028 |
regulators | +0.027 |
equations | +0.026 |
Neg logit contributions | |
Interstitial | -0.046 |
ovember | -0.043 |
DK | -0.042 |
ドラゴン | -0.040 |
ingen | -0.039 |
Token | data |
Token ID | 1366 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
manif | +0.155 |
incent | +0.148 |
ngth | +0.143 |
regulators | +0.136 |
equations | +0.134 |
Neg logit contributions | |
Interstitial | -0.126 |
ovember | -0.113 |
DK | -0.113 |
ドラゴン | -0.103 |
ingen | -0.102 |
Token | : |
Token ID | 25 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
manif | +0.163 |
incent | +0.155 |
ngth | +0.149 |
regulators | +0.143 |
equations | +0.141 |
Neg logit contributions | |
Interstitial | -0.146 |
ovember | -0.131 |
DK | -0.131 |
ドラゴン | -0.120 |
ingen | -0.119 |
Token | alcohol |
Token ID | 5548 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
manif | +0.123 |
incent | +0.117 |
ngth | +0.113 |
regulators | +0.107 |
equations | +0.105 |
Neg logit contributions | |
Interstitial | -0.129 |
ovember | -0.118 |
DK | -0.118 |
ドラゴン | -0.109 |
ingen | -0.108 |
Token | - |
Token ID | 12 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
manif | +0.262 |
incent | +0.249 |
ngth | +0.240 |
regulators | +0.227 |
undermin | +0.223 |
Neg logit contributions | |
Interstitial | -0.251 |
ovember | -0.230 |
DK | -0.229 |
ドラゴン | -0.211 |
ingen | -0.209 |
Token | im |
Token ID | 320 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
manif | +0.026 |
incent | +0.025 |
ngth | +0.024 |
regulators | +0.023 |
undermin | +0.022 |
Neg logit contributions | |
Interstitial | -0.027 |
ovember | -0.025 |
DK | -0.025 |
ドラゴン | -0.023 |
ingen | -0.023 |
Token | pa |
Token ID | 8957 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
manif | +0.729 |
incent | +0.691 |
ngth | +0.646 |
regulators | +0.592 |
ratios | +0.570 |
Neg logit contributions | |
Interstitial | -1.477 |
DK | -1.377 |
ovember | -1.372 |
ドラゴン | -1.304 |
ingen | -1.285 |
Token | ired |
Token ID | 1202 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
manif | +0.596 |
incent | +0.572 |
ngth | +0.555 |
regulators | +0.532 |
ratios | +0.525 |
Neg logit contributions | |
Interstitial | -0.383 |
ovember | -0.339 |
DK | -0.339 |
ドラゴン | -0.304 |
lan | -0.299 |
Token | driving |
Token ID | 5059 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
manif | +0.091 |
incent | +0.082 |
ngth | +0.076 |
regulators | +0.068 |
equations | +0.065 |
Neg logit contributions | |
Interstitial | -0.239 |
ovember | -0.226 |
DK | -0.225 |
ドラゴン | -0.213 |
ingen | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
manif | +0.240 |
incent | +0.227 |
ngth | +0.219 |
regulators | +0.205 |
undermin | +0.202 |
Neg logit contributions | |
Interstitial | -0.260 |
ovember | -0.238 |
DK | -0.238 |
ドラゴン | -0.220 |
ingen | -0.218 |
Token | Washington |
Token ID | 2669 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
manif | +0.193 |
incent | +0.185 |
ngth | +0.179 |
regulators | +0.170 |
equations | +0.168 |
Neg logit contributions | |
Interstitial | -0.170 |
ovember | -0.154 |
DK | -0.152 |
ドラゴン | -0.140 |
ingen | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Interstitial | +0.063 |
ovember | +0.057 |
DK | +0.057 |
ドラゴン | +0.052 |
ingen | +0.051 |
Neg logit contributions | |
manif | -0.075 |
incent | -0.071 |
ngth | -0.069 |
regulators | -0.066 |
equations | -0.064 |
Token | There |
Token ID | 1318 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
manif | +0.111 |
incent | +0.106 |
ngth | +0.103 |
regulators | +0.099 |
equations | +0.097 |
Neg logit contributions | |
Interstitial | -0.081 |
ovember | -0.074 |
DK | -0.072 |
ドラゴン | -0.066 |
ingen | -0.065 |
Token | are |
Token ID | 389 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
Interstitial | +0.102 |
ovember | +0.093 |
DK | +0.093 |
ドラゴン | +0.085 |
ingen | +0.085 |
Neg logit contributions | |
manif | -0.099 |
incent | -0.093 |
ngth | -0.091 |
regulators | -0.086 |
undermin | -0.084 |
Token | t |
Token ID | 256 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
manif | +0.075 |
incent | +0.071 |
ngth | +0.068 |
regulators | +0.064 |
undermin | +0.063 |
Neg logit contributions | |
Interstitial | -0.088 |
ovember | -0.081 |
DK | -0.081 |
ドラゴン | -0.075 |
ingen | -0.074 |
Token | inct |
Token ID | 4612 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
manif | +0.254 |
incent | +0.242 |
ngth | +0.236 |
regulators | +0.224 |
undermin | +0.221 |
Neg logit contributions | |
Interstitial | -0.178 |
ovember | -0.160 |
DK | -0.159 |
ドラゴン | -0.144 |
ingen | -0.142 |
Token | ures |
Token ID | 942 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Interstitial | +0.348 |
DK | +0.318 |
ovember | +0.318 |
ドラゴン | +0.295 |
ingen | +0.291 |
Neg logit contributions | |
manif | -0.312 |
incent | -0.294 |
ngth | -0.285 |
regulators | -0.266 |
equations | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
manif | +1.159 |
incent | +1.097 |
ngth | +1.065 |
regulators | +1.015 |
ratios | +0.997 |
Neg logit contributions | |
Interstitial | -1.045 |
ovember | -0.947 |
DK | -0.940 |
ドラゴン | -0.870 |
ingen | -0.850 |
Token | You |
Token ID | 921 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
manif | +0.099 |
incent | +0.094 |
ngth | +0.092 |
regulators | +0.088 |
equations | +0.086 |
Neg logit contributions | |
Interstitial | -0.069 |
ovember | -0.062 |
DK | -0.061 |
ドラゴン | -0.055 |
ingen | -0.055 |
Token | can |
Token ID | 460 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
manif | +0.116 |
incent | +0.110 |
ngth | +0.106 |
regulators | +0.099 |
equations | +0.098 |
Neg logit contributions | |
Interstitial | -0.122 |
ovember | -0.112 |
DK | -0.111 |
ドラゴン | -0.103 |
ingen | -0.102 |
Token | put |
Token ID | 1234 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
manif | +0.110 |
incent | +0.103 |
ngth | +0.099 |
regulators | +0.093 |
equations | +0.091 |
Neg logit contributions | |
Interstitial | -0.132 |
DK | -0.122 |
ovember | -0.122 |
ドラゴン | -0.113 |
ingen | -0.112 |
Token | a |
Token ID | 257 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
manif | +0.160 |
incent | +0.151 |
ngth | +0.146 |
regulators | +0.137 |
equations | +0.135 |
Neg logit contributions | |
Interstitial | -0.172 |
ovember | -0.158 |
DK | -0.157 |
ドラゴン | -0.146 |
ingen | -0.144 |
Token | tens |
Token ID | 11192 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
manif | +0.089 |
incent | +0.084 |
ngth | +0.081 |
regulators | +0.077 |
equations | +0.075 |
Neg logit contributions | |
Interstitial | -0.099 |
ovember | -0.091 |
DK | -0.090 |
ドラゴン | -0.084 |
ingen | -0.083 |
Token | of |
Token ID | 286 |
Feature activation | +9.65e-02 |
Pos logit contributions | |
Interstitial | +0.208 |
ovember | +0.189 |
DK | +0.187 |
ドラゴン | +0.173 |
ingen | +0.171 |
Neg logit contributions | |
manif | -0.218 |
incent | -0.207 |
ngth | -0.202 |
regulators | -0.189 |
undermin | -0.186 |
Token | thousands |
Token ID | 4138 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
manif | +0.071 |
incent | +0.067 |
ngth | +0.063 |
regulators | +0.060 |
equations | +0.059 |
Neg logit contributions | |
Interstitial | -0.093 |
ovember | -0.086 |
DK | -0.085 |
ドラゴン | -0.079 |
ingen | -0.079 |
Token | of |
Token ID | 286 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
manif | +0.085 |
incent | +0.081 |
ngth | +0.078 |
regulators | +0.074 |
undermin | +0.073 |
Neg logit contributions | |
Interstitial | -0.081 |
ovember | -0.073 |
DK | -0.073 |
ドラゴン | -0.067 |
ingen | -0.066 |
Token | broch |
Token ID | 41978 |
Feature activation | -4.23e-01 |
Pos logit contributions | |
manif | +0.037 |
incent | +0.035 |
ngth | +0.033 |
regulators | +0.031 |
equations | +0.031 |
Neg logit contributions | |
Interstitial | -0.050 |
ovember | -0.046 |
DK | -0.046 |
ドラゴン | -0.043 |
ingen | -0.043 |
Token | ures |
Token ID | 942 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Interstitial | +0.378 |
ovember | +0.346 |
DK | +0.345 |
ドラゴン | +0.320 |
ingen | +0.316 |
Neg logit contributions | |
manif | -0.343 |
incent | -0.323 |
ngth | -0.313 |
regulators | -0.292 |
equations | -0.287 |
Token | to |
Token ID | 284 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
manif | +1.039 |
incent | +0.975 |
ngth | +0.935 |
regulators | +0.897 |
equations | +0.871 |
Neg logit contributions | |
Interstitial | -1.165 |
ovember | -1.064 |
DK | -1.054 |
ドラゴン | -0.986 |
ingen | -0.967 |
Token | gun |
Token ID | 2485 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Interstitial | +0.015 |
ovember | +0.013 |
DK | +0.013 |
ドラゴン | +0.012 |
ingen | +0.012 |
Neg logit contributions | |
manif | -0.013 |
incent | -0.012 |
ngth | -0.012 |
regulators | -0.011 |
undermin | -0.011 |
Token | owners |
Token ID | 4393 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
Interstitial | +0.029 |
ovember | +0.027 |
DK | +0.027 |
ドラゴン | +0.025 |
ingen | +0.025 |
Neg logit contributions | |
manif | -0.023 |
incent | -0.022 |
ngth | -0.021 |
regulators | -0.020 |
undermin | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
Interstitial | +0.018 |
ovember | +0.016 |
DK | +0.016 |
ドラゴン | +0.015 |
lan | +0.015 |
Neg logit contributions | |
manif | -0.018 |
incent | -0.017 |
ngth | -0.016 |
regulators | -0.015 |
undermin | -0.015 |
Token | like |
Token ID | 588 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
Interstitial | +0.011 |
ovember | +0.010 |
DK | +0.010 |
ドラゴン | +0.009 |
ingen | +0.009 |
Neg logit contributions | |
manif | -0.008 |
incent | -0.008 |
ngth | -0.007 |
regulators | -0.007 |
undermin | -0.007 |
Token | months |
Token ID | 1933 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Interstitial | +0.068 |
ovember | +0.062 |
DK | +0.062 |
ドラゴン | +0.058 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.064 |
incent | -0.060 |
ngth | -0.058 |
regulators | -0.055 |
undermin | -0.054 |
Token | after |
Token ID | 706 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Interstitial | +0.151 |
ovember | +0.139 |
DK | +0.138 |
ドラゴン | +0.128 |
ingen | +0.127 |
Neg logit contributions | |
manif | -0.133 |
incent | -0.126 |
ngth | -0.122 |
regulators | -0.114 |
undermin | -0.112 |
Token | Pract |
Token ID | 13672 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Interstitial | +0.110 |
ovember | +0.100 |
DK | +0.100 |
ドラゴン | +0.093 |
ingen | +0.091 |
Neg logit contributions | |
manif | -0.110 |
incent | -0.105 |
ngth | -0.101 |
regulators | -0.095 |
undermin | -0.094 |
Token | icing |
Token ID | 6345 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Interstitial | +0.013 |
DK | +0.012 |
ovember | +0.012 |
ドラゴン | +0.011 |
ingen | +0.011 |
Neg logit contributions | |
manif | -0.012 |
incent | -0.011 |
ngth | -0.011 |
regulators | -0.010 |
undermin | -0.010 |
Token | Prof |
Token ID | 4415 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
manif | +0.293 |
incent | +0.278 |
ngth | +0.269 |
regulators | +0.256 |
undermin | +0.252 |
Neg logit contributions | |
Interstitial | -0.234 |
ovember | -0.211 |
DK | -0.210 |
ドラゴン | -0.193 |
ingen | -0.189 |
Token | icient |
Token ID | 11373 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Interstitial | +0.335 |
ovember | +0.303 |
DK | +0.302 |
ドラゴン | +0.279 |
lan | +0.273 |
Neg logit contributions | |
manif | -0.373 |
incent | -0.355 |
ngth | -0.345 |
regulators | -0.324 |
undermin | -0.320 |
Token | ly |
Token ID | 306 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
manif | +1.212 |
incent | +1.146 |
ngth | +1.118 |
regulators | +1.058 |
undermin | +1.044 |
Neg logit contributions | |
Interstitial | -0.969 |
ovember | -0.880 |
DK | -0.870 |
ドラゴン | -0.802 |
ingen | -0.781 |
Token | , |
Token ID | 11 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
Interstitial | +0.042 |
ovember | +0.038 |
DK | +0.037 |
ドラゴン | +0.034 |
ingen | +0.034 |
Neg logit contributions | |
manif | -0.054 |
incent | -0.051 |
ngth | -0.050 |
regulators | -0.047 |
undermin | -0.046 |
Token | you |
Token ID | 345 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
manif | +0.040 |
incent | +0.038 |
ngth | +0.036 |
regulators | +0.034 |
undermin | +0.034 |
Neg logit contributions | |
Interstitial | -0.045 |
ovember | -0.041 |
DK | -0.041 |
ドラゴン | -0.038 |
ingen | -0.038 |
Token | no |
Token ID | 645 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
manif | +0.152 |
incent | +0.144 |
ngth | +0.138 |
regulators | +0.130 |
equations | +0.127 |
Neg logit contributions | |
Interstitial | -0.173 |
ovember | -0.158 |
DK | -0.158 |
ドラゴン | -0.147 |
ingen | -0.145 |
Token | longer |
Token ID | 2392 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
manif | +0.255 |
incent | +0.241 |
ngth | +0.233 |
regulators | +0.217 |
undermin | +0.213 |
Neg logit contributions | |
Interstitial | -0.307 |
ovember | -0.282 |
DK | -0.281 |
ドラゴン | -0.262 |
ingen | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
Interstitial | +0.138 |
ovember | +0.124 |
DK | +0.124 |
ドラゴン | +0.112 |
ingen | +0.111 |
Neg logit contributions | |
manif | -0.185 |
incent | -0.177 |
ngth | -0.172 |
regulators | -0.163 |
undermin | -0.161 |
Token | initially |
Token ID | 7317 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
Interstitial | +0.054 |
ovember | +0.050 |
DK | +0.050 |
ドラゴン | +0.047 |
lan | +0.046 |
Neg logit contributions | |
manif | -0.039 |
incent | -0.037 |
ngth | -0.035 |
regulators | -0.033 |
undermin | -0.032 |
Token | failing |
Token ID | 9894 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
manif | +0.196 |
incent | +0.183 |
ngth | +0.172 |
regulators | +0.162 |
undermin | +0.158 |
Neg logit contributions | |
Interstitial | -0.310 |
ovember | -0.288 |
DK | -0.288 |
ドラゴン | -0.269 |
ingen | -0.267 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
Interstitial | +0.085 |
ovember | +0.076 |
DK | +0.076 |
ドラゴン | +0.069 |
ingen | +0.068 |
Neg logit contributions | |
manif | -0.117 |
incent | -0.112 |
ngth | -0.109 |
regulators | -0.103 |
undermin | -0.102 |
Token | sec |
Token ID | 792 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Interstitial | +0.020 |
DK | +0.018 |
ovember | +0.018 |
ドラゴン | +0.016 |
ingen | +0.016 |
Neg logit contributions | |
manif | -0.021 |
incent | -0.020 |
ngth | -0.019 |
regulators | -0.018 |
undermin | -0.018 |
Token | ures |
Token ID | 942 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
manif | +0.080 |
incent | +0.074 |
ngth | +0.072 |
regulators | +0.068 |
equations | +0.067 |
Neg logit contributions | |
Interstitial | -0.097 |
DK | -0.089 |
ovember | -0.088 |
ドラゴン | -0.083 |
lan | -0.081 |
Token | mark |
Token ID | 1317 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
manif | +1.224 |
incent | +1.163 |
ngth | +1.128 |
regulators | +1.069 |
undermin | +1.060 |
Neg logit contributions | |
Interstitial | -0.959 |
DK | -0.860 |
ovember | -0.857 |
ドラゴン | -0.779 |
ingen | -0.771 |
Token | ( |
Token ID | 357 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
manif | +0.075 |
incent | +0.071 |
ngth | +0.069 |
regulators | +0.065 |
undermin | +0.064 |
Neg logit contributions | |
Interstitial | -0.070 |
ovember | -0.064 |
DK | -0.064 |
ドラゴン | -0.058 |
ingen | -0.058 |
Token | 1 |
Token ID | 16 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
manif | +0.092 |
incent | +0.087 |
ngth | +0.086 |
regulators | +0.081 |
equations | +0.080 |
Neg logit contributions | |
Interstitial | -0.066 |
ovember | -0.059 |
DK | -0.058 |
ドラゴン | -0.053 |
ingen | -0.053 |
Token | – |
Token ID | 1906 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Interstitial | +0.063 |
ovember | +0.058 |
DK | +0.058 |
ドラゴン | +0.053 |
ingen | +0.053 |
Neg logit contributions | |
manif | -0.060 |
incent | -0.057 |
ngth | -0.055 |
regulators | -0.051 |
undermin | -0.051 |
Token | 4 |
Token ID | 19 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Interstitial | +0.228 |
ovember | +0.203 |
DK | +0.201 |
ingen | +0.179 |
ドラゴン | +0.179 |
Neg logit contributions | |
manif | -0.360 |
incent | -0.343 |
ngth | -0.336 |
regulators | -0.319 |
equations | -0.315 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
manif | +0.316 |
incent | +0.301 |
ngth | +0.290 |
regulators | +0.276 |
equations | +0.270 |
Neg logit contributions | |
Interstitial | -0.291 |
ovember | -0.265 |
DK | -0.263 |
ドラゴン | -0.242 |
ingen | -0.240 |
Token | Rail |
Token ID | 12950 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
manif | +0.114 |
incent | +0.109 |
ngth | +0.106 |
regulators | +0.101 |
equations | +0.099 |
Neg logit contributions | |
Interstitial | -0.089 |
ovember | -0.081 |
DK | -0.080 |
ingen | -0.073 |
ドラゴン | -0.073 |
Token | ways |
Token ID | 1322 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
manif | +0.302 |
incent | +0.284 |
ngth | +0.275 |
regulators | +0.260 |
equations | +0.254 |
Neg logit contributions | |
Interstitial | -0.338 |
ovember | -0.309 |
DK | -0.307 |
ドラゴン | -0.285 |
ingen | -0.283 |
Token | Minister |
Token ID | 4139 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
manif | +0.299 |
incent | +0.283 |
ngth | +0.270 |
regulators | +0.257 |
equations | +0.251 |
Neg logit contributions | |
Interstitial | -0.342 |
ovember | -0.312 |
DK | -0.310 |
ドラゴン | -0.289 |
ingen | -0.286 |
Token | S |
Token ID | 311 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
manif | +0.089 |
incent | +0.084 |
ngth | +0.081 |
regulators | +0.077 |
equations | +0.076 |
Neg logit contributions | |
Interstitial | -0.085 |
ovember | -0.078 |
DK | -0.077 |
ドラゴン | -0.071 |
ingen | -0.070 |
Token | ures |
Token ID | 942 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
manif | +0.282 |
incent | +0.267 |
ngth | +0.260 |
regulators | +0.245 |
equations | +0.241 |
Neg logit contributions | |
Interstitial | -0.246 |
ovember | -0.223 |
DK | -0.223 |
ドラゴン | -0.205 |
ingen | -0.202 |
Token | h |
Token ID | 71 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
manif | +1.087 |
incent | +1.028 |
ngth | +1.002 |
regulators | +0.956 |
equations | +0.939 |
Neg logit contributions | |
Interstitial | -1.074 |
ovember | -0.979 |
DK | -0.933 |
ドラゴン | -0.905 |
ingen | -0.882 |
Token | Pr |
Token ID | 1736 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
manif | +0.677 |
incent | +0.645 |
ngth | +0.627 |
regulators | +0.609 |
equations | +0.603 |
Neg logit contributions | |
Interstitial | -0.304 |
ovember | -0.263 |
DK | -0.259 |
ingen | -0.233 |
ドラゴン | -0.229 |
Token | ab |
Token ID | 397 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
manif | +0.064 |
incent | +0.061 |
ngth | +0.060 |
regulators | +0.057 |
equations | +0.057 |
Neg logit contributions | |
Interstitial | -0.022 |
ovember | -0.018 |
DK | -0.018 |
ドラゴン | -0.017 |
ingen | -0.015 |
Token | hu |
Token ID | 13415 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
Interstitial | +0.222 |
ovember | +0.187 |
DK | +0.184 |
ドラゴン | +0.167 |
ゼウス | +0.157 |
Neg logit contributions | |
manif | -0.469 |
incent | -0.450 |
ngth | -0.443 |
regulators | -0.423 |
equations | -0.418 |
Token | estimates |
Token ID | 7746 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
manif | +0.171 |
incent | +0.162 |
ngth | +0.157 |
regulators | +0.149 |
equations | +0.146 |
Neg logit contributions | |
Interstitial | -0.151 |
ovember | -0.136 |
DK | -0.136 |
ドラゴン | -0.124 |
ingen | -0.123 |
Token | shutdown |
Token ID | 18325 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Interstitial | +0.229 |
ovember | +0.213 |
DK | +0.213 |
ドラゴン | +0.200 |
ingen | +0.199 |
Neg logit contributions | |
manif | -0.131 |
incent | -0.122 |
ngth | -0.116 |
regulators | -0.106 |
undermin | -0.104 |
Token | that |
Token ID | 326 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
manif | +0.244 |
incent | +0.231 |
ngth | +0.222 |
regulators | +0.209 |
undermin | +0.205 |
Neg logit contributions | |
Interstitial | -0.269 |
ovember | -0.246 |
DK | -0.246 |
ドラゴン | -0.228 |
ingen | -0.225 |
Token | began |
Token ID | 2540 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
manif | +0.020 |
incent | +0.019 |
ngth | +0.019 |
regulators | +0.018 |
undermin | +0.017 |
Neg logit contributions | |
Interstitial | -0.022 |
ovember | -0.020 |
DK | -0.020 |
ドラゴン | -0.018 |
ingen | -0.018 |
Token | Tuesday |
Token ID | 3431 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
manif | +0.210 |
incent | +0.199 |
ngth | +0.192 |
regulators | +0.184 |
equations | +0.180 |
Neg logit contributions | |
Interstitial | -0.175 |
DK | -0.157 |
ovember | -0.157 |
ドラゴン | -0.144 |
ingen | -0.142 |
Token | dr |
Token ID | 1553 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
manif | +0.074 |
incent | +0.070 |
ngth | +0.067 |
regulators | +0.063 |
equations | +0.062 |
Neg logit contributions | |
Interstitial | -0.085 |
ovember | -0.078 |
DK | -0.077 |
ドラゴン | -0.072 |
ingen | -0.071 |
Token | ags |
Token ID | 3775 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
manif | +0.273 |
incent | +0.256 |
ngth | +0.248 |
regulators | +0.233 |
equations | +0.231 |
Neg logit contributions | |
Interstitial | -0.260 |
DK | -0.234 |
ovember | -0.232 |
ドラゴン | -0.218 |
lan | -0.210 |
Token | on |
Token ID | 319 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
manif | +1.217 |
incent | +1.136 |
ngth | +1.108 |
regulators | +1.072 |
equations | +1.050 |
Neg logit contributions | |
Interstitial | -0.965 |
DK | -0.866 |
ovember | -0.865 |
ドラゴン | -0.792 |
ingen | -0.780 |
Token | . |
Token ID | 13 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
Interstitial | +0.021 |
ovember | +0.019 |
DK | +0.019 |
ドラゴン | +0.018 |
ingen | +0.018 |
Neg logit contributions | |
manif | -0.023 |
incent | -0.022 |
ngth | -0.021 |
regulators | -0.020 |
undermin | -0.020 |
Token | In |
Token ID | 554 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
manif | +0.022 |
incent | +0.021 |
ngth | +0.020 |
regulators | +0.019 |
equations | +0.019 |
Neg logit contributions | |
Interstitial | -0.018 |
ovember | -0.016 |
DK | -0.016 |
ingen | -0.014 |
ドラゴン | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Interstitial | +0.032 |
DK | +0.029 |
ovember | +0.029 |
ドラゴン | +0.027 |
ingen | +0.026 |
Neg logit contributions | |
manif | -0.031 |
incent | -0.030 |
ngth | -0.028 |
regulators | -0.027 |
equations | -0.026 |
Token | letter |
Token ID | 3850 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
manif | +0.038 |
incent | +0.036 |
ngth | +0.034 |
regulators | +0.032 |
equations | +0.031 |
Neg logit contributions | |
Interstitial | -0.049 |
DK | -0.045 |
ovember | -0.045 |
ドラゴン | -0.042 |
ingen | -0.042 |
Token | Ab |
Token ID | 4826 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Interstitial | +0.042 |
ovember | +0.038 |
DK | +0.037 |
ドラゴン | +0.033 |
ingen | +0.033 |
Neg logit contributions | |
manif | -0.064 |
incent | -0.061 |
ngth | -0.060 |
regulators | -0.057 |
undermin | -0.056 |
Token | d |
Token ID | 67 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
Interstitial | +0.024 |
ovember | +0.022 |
DK | +0.021 |
ドラゴン | +0.019 |
ingen | +0.018 |
Neg logit contributions | |
manif | -0.041 |
incent | -0.039 |
ngth | -0.038 |
regulators | -0.036 |
equations | -0.036 |
Token | as |
Token ID | 355 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
Interstitial | +0.290 |
ovember | +0.257 |
DK | +0.255 |
ドラゴン | +0.234 |
ingen | +0.227 |
Neg logit contributions | |
manif | -0.398 |
incent | -0.378 |
ngth | -0.370 |
regulators | -0.352 |
equations | -0.345 |
Token | - |
Token ID | 12 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
manif | +0.049 |
incent | +0.046 |
ngth | +0.045 |
regulators | +0.042 |
undermin | +0.042 |
Neg logit contributions | |
Interstitial | -0.045 |
ovember | -0.041 |
DK | -0.040 |
ドラゴン | -0.037 |
ingen | -0.037 |
Token | Sal |
Token ID | 19221 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
manif | +0.116 |
incent | +0.110 |
ngth | +0.107 |
regulators | +0.102 |
undermin | +0.100 |
Neg logit contributions | |
Interstitial | -0.084 |
ovember | -0.076 |
DK | -0.074 |
ドラゴン | -0.068 |
ingen | -0.068 |
Token | im |
Token ID | 320 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Interstitial | +0.137 |
ovember | +0.124 |
DK | +0.123 |
ドラゴン | +0.114 |
ingen | +0.111 |
Neg logit contributions | |
manif | -0.162 |
incent | -0.154 |
ngth | -0.150 |
regulators | -0.141 |
equations | -0.139 |
Token | al |
Token ID | 435 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
manif | +1.149 |
incent | +1.087 |
ngth | +1.053 |
regulators | +0.996 |
equations | +0.983 |
Neg logit contributions | |
Interstitial | -1.026 |
ovember | -0.928 |
DK | -0.916 |
ドラゴン | -0.844 |
ingen | -0.829 |
Token | - |
Token ID | 12 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
manif | +0.226 |
incent | +0.213 |
ngth | +0.207 |
regulators | +0.194 |
undermin | +0.191 |
Neg logit contributions | |
Interstitial | -0.233 |
ovember | -0.213 |
DK | -0.211 |
ドラゴン | -0.196 |
ingen | -0.194 |
Token | H |
Token ID | 39 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
manif | +0.155 |
incent | +0.147 |
ngth | +0.144 |
regulators | +0.136 |
equations | +0.134 |
Neg logit contributions | |
Interstitial | -0.120 |
ovember | -0.110 |
DK | -0.107 |
ドラゴン | -0.099 |
ingen | -0.098 |
Token | aj |
Token ID | 1228 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
manif | +0.161 |
incent | +0.154 |
ngth | +0.150 |
regulators | +0.141 |
ratios | +0.139 |
Neg logit contributions | |
Interstitial | -0.128 |
DK | -0.115 |
ovember | -0.114 |
ドラゴン | -0.106 |
ingen | -0.102 |
Token | j |
Token ID | 73 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
manif | +0.125 |
incent | +0.120 |
ngth | +0.116 |
regulators | +0.110 |
ratios | +0.109 |
Neg logit contributions | |
Interstitial | -0.092 |
ovember | -0.083 |
DK | -0.082 |
ドラゴン | -0.075 |
ingen | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
Interstitial | +0.092 |
ovember | +0.083 |
DK | +0.082 |
ドラゴン | +0.075 |
ingen | +0.074 |
Neg logit contributions | |
manif | -0.121 |
incent | -0.115 |
ngth | -0.112 |
regulators | -0.106 |
undermin | -0.105 |
Token |
|
Token ID | 198 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Interstitial | +0.040 |
ovember | +0.036 |
DK | +0.036 |
ドラゴン | +0.033 |
ingen | +0.033 |
Neg logit contributions | |
manif | -0.050 |
incent | -0.048 |
ngth | -0.046 |
regulators | -0.044 |
equations | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
Interstitial | +0.023 |
ovember | +0.021 |
DK | +0.020 |
ドラゴン | +0.019 |
ingen | +0.019 |
Neg logit contributions | |
manif | -0.027 |
incent | -0.025 |
ngth | -0.024 |
regulators | -0.024 |
equations | -0.023 |
Token | Pro |
Token ID | 2964 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
Interstitial | +0.069 |
ovember | +0.063 |
DK | +0.062 |
ドラゴン | +0.057 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.083 |
incent | -0.079 |
ngth | -0.077 |
regulators | -0.073 |
equations | -0.071 |
Token | ced |
Token ID | 771 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
Interstitial | +0.260 |
ovember | +0.237 |
DK | +0.237 |
ドラゴン | +0.218 |
lan | +0.217 |
Neg logit contributions | |
manif | -0.243 |
incent | -0.230 |
ngth | -0.223 |
regulators | -0.208 |
undermin | -0.206 |
Token | ure |
Token ID | 495 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Interstitial | +0.052 |
ovember | +0.047 |
DK | +0.047 |
ドラゴン | +0.043 |
ingen | +0.042 |
Neg logit contributions | |
manif | -0.057 |
incent | -0.054 |
ngth | -0.052 |
regulators | -0.050 |
equations | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
manif | +1.111 |
incent | +1.055 |
ngth | +1.018 |
regulators | +0.969 |
equations | +0.954 |
Neg logit contributions | |
Interstitial | -1.045 |
ovember | -0.949 |
DK | -0.941 |
ドラゴン | -0.868 |
ingen | -0.860 |
Token | such |
Token ID | 884 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Interstitial | +0.002 |
ovember | +0.002 |
DK | +0.002 |
ドラゴン | +0.002 |
ingen | +0.002 |
Neg logit contributions | |
manif | -0.002 |
incent | -0.002 |
ngth | -0.002 |
regulators | -0.002 |
undermin | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
Interstitial | +0.235 |
ovember | +0.215 |
DK | +0.214 |
ドラゴン | +0.197 |
ingen | +0.195 |
Neg logit contributions | |
manif | -0.240 |
incent | -0.227 |
ngth | -0.218 |
regulators | -0.207 |
equations | -0.204 |
Token | mistake |
Token ID | 7457 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Interstitial | +0.072 |
ovember | +0.067 |
DK | +0.066 |
ドラゴン | +0.062 |
ingen | +0.061 |
Neg logit contributions | |
manif | -0.060 |
incent | -0.056 |
ngth | -0.054 |
regulators | -0.051 |
undermin | -0.050 |
Token | calls |
Token ID | 3848 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
Interstitial | +0.210 |
ovember | +0.190 |
DK | +0.189 |
ドラゴン | +0.173 |
ingen | +0.172 |
Neg logit contributions | |
manif | -0.234 |
incent | -0.222 |
ngth | -0.215 |
regulators | -0.203 |
equations | -0.200 |
Token | The |
Token ID | 383 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
Interstitial | +0.037 |
ovember | +0.034 |
DK | +0.033 |
ドラゴン | +0.030 |
ingen | +0.030 |
Neg logit contributions | |
manif | -0.047 |
incent | -0.045 |
ngth | -0.044 |
regulators | -0.042 |
equations | -0.041 |
Token | Dell |
Token ID | 23617 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Interstitial | +0.119 |
ovember | +0.109 |
DK | +0.108 |
ドラゴン | +0.100 |
ingen | +0.099 |
Neg logit contributions | |
manif | -0.115 |
incent | -0.108 |
ngth | -0.104 |
regulators | -0.099 |
equations | -0.097 |
Token | U |
Token ID | 471 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Interstitial | +0.166 |
ovember | +0.152 |
DK | +0.151 |
ドラゴン | +0.140 |
ingen | +0.139 |
Neg logit contributions | |
manif | -0.160 |
incent | -0.151 |
ngth | -0.146 |
regulators | -0.138 |
equations | -0.135 |
Token | 27 |
Token ID | 1983 |
Feature activation | +9.63e-02 |
Pos logit contributions | |
Interstitial | +0.327 |
ovember | +0.296 |
DK | +0.296 |
ドラゴン | +0.271 |
ingen | +0.269 |
Neg logit contributions | |
manif | -0.362 |
incent | -0.344 |
ngth | -0.333 |
regulators | -0.314 |
undermin | -0.310 |
Token | 13 |
Token ID | 1485 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
manif | +0.102 |
incent | +0.097 |
ngth | +0.095 |
regulators | +0.091 |
equations | +0.090 |
Neg logit contributions | |
Interstitial | -0.062 |
ovember | -0.054 |
DK | -0.054 |
ドラゴン | -0.048 |
ingen | -0.048 |
Token | HM |
Token ID | 36905 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Interstitial | +0.294 |
ovember | +0.266 |
DK | +0.264 |
ドラゴン | +0.242 |
ingen | +0.240 |
Neg logit contributions | |
manif | -0.344 |
incent | -0.327 |
ngth | -0.317 |
regulators | -0.300 |
equations | -0.295 |
Token | is |
Token ID | 318 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
Interstitial | +1.207 |
ovember | +1.100 |
DK | +1.100 |
ドラゴン | +1.011 |
ingen | +1.002 |
Neg logit contributions | |
manif | -1.238 |
incent | -1.174 |
ngth | -1.139 |
regulators | -1.067 |
undermin | -1.055 |
Token | a |
Token ID | 257 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Interstitial | +0.012 |
ovember | +0.011 |
DK | +0.011 |
ドラゴン | +0.010 |
ingen | +0.010 |
Neg logit contributions | |
manif | -0.011 |
incent | -0.010 |
ngth | -0.009 |
regulators | -0.009 |
equations | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Interstitial | +0.024 |
ovember | +0.022 |
DK | +0.022 |
ドラゴン | +0.021 |
ingen | +0.020 |
Neg logit contributions | |
manif | -0.021 |
incent | -0.020 |
ngth | -0.019 |
regulators | -0.018 |
ratios | -0.018 |
Token | faster |
Token ID | 5443 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Interstitial | +0.266 |
ovember | +0.245 |
DK | +0.244 |
ドラゴン | +0.227 |
ingen | +0.224 |
Neg logit contributions | |
manif | -0.224 |
incent | -0.211 |
ngth | -0.203 |
regulators | -0.190 |
undermin | -0.187 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Interstitial | +0.158 |
ovember | +0.144 |
DK | +0.143 |
ドラゴン | +0.131 |
ingen | +0.130 |
Neg logit contributions | |
manif | -0.172 |
incent | -0.164 |
ngth | -0.159 |
regulators | -0.149 |
undermin | -0.148 |
Token | (@ |
Token ID | 4275 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Interstitial | +0.724 |
ovember | +0.620 |
DK | +0.616 |
ドラゴン | +0.539 |
ingen | +0.525 |
Neg logit contributions | |
manif | -1.616 |
incent | -1.552 |
ngth | -1.521 |
regulators | -1.448 |
equations | -1.436 |
Token | C |
Token ID | 34 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
manif | +0.184 |
incent | +0.173 |
ngth | +0.170 |
regulators | +0.158 |
undermin | +0.156 |
Neg logit contributions | |
Interstitial | -0.169 |
ovember | -0.154 |
DK | -0.152 |
ドラゴン | -0.141 |
ingen | -0.139 |
Token | ody |
Token ID | 1118 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Interstitial | +0.222 |
ovember | +0.204 |
DK | +0.203 |
ドラゴン | +0.192 |
ingen | +0.188 |
Neg logit contributions | |
manif | -0.175 |
incent | -0.164 |
ngth | -0.159 |
regulators | -0.147 |
equations | -0.144 |
Token | W |
Token ID | 54 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Interstitial | +0.153 |
ovember | +0.137 |
DK | +0.135 |
ドラゴン | +0.126 |
ingen | +0.123 |
Neg logit contributions | |
manif | -0.189 |
incent | -0.179 |
ngth | -0.177 |
regulators | -0.165 |
undermin | -0.163 |
Token | ester |
Token ID | 7834 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Interstitial | +0.229 |
ovember | +0.202 |
DK | +0.196 |
ドラゴン | +0.184 |
ゼウス | +0.178 |
Neg logit contributions | |
manif | -0.354 |
incent | -0.342 |
ngth | -0.337 |
regulators | -0.319 |
ratios | -0.312 |
Token | lund |
Token ID | 37525 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Interstitial | +0.090 |
ovember | +0.076 |
DK | +0.074 |
ドラゴン | +0.065 |
ingen | +0.062 |
Neg logit contributions | |
manif | -0.240 |
incent | -0.230 |
ngth | -0.227 |
regulators | -0.217 |
equations | -0.215 |
Token | ) |
Token ID | 8 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Interstitial | +0.820 |
ovember | +0.714 |
DK | +0.705 |
ドラゴン | +0.632 |
ingen | +0.625 |
Neg logit contributions | |
manif | -1.573 |
incent | -1.504 |
ngth | -1.478 |
regulators | -1.401 |
equations | -1.386 |
Token | October |
Token ID | 3267 |
Feature activation | -8.99e-02 |
Pos logit contributions | |
Interstitial | +0.249 |
DK | +0.222 |
ovember | +0.221 |
ドラゴン | +0.200 |
ingen | +0.198 |
Neg logit contributions | |
manif | -0.368 |
incent | -0.348 |
ngth | -0.340 |
regulators | -0.328 |
ratios | -0.323 |
Token | 7 |
Token ID | 767 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
Interstitial | +0.070 |
ovember | +0.063 |
DK | +0.062 |
ドラゴン | +0.057 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.083 |
incent | -0.078 |
ngth | -0.076 |
regulators | -0.073 |
equations | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Interstitial | +0.246 |
ovember | +0.226 |
DK | +0.220 |
ドラゴン | +0.203 |
ingen | +0.200 |
Neg logit contributions | |
manif | -0.308 |
incent | -0.286 |
ngth | -0.282 |
regulators | -0.274 |
equations | -0.271 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Interstitial | +0.219 |
ovember | +0.198 |
DK | +0.194 |
ドラゴン | +0.178 |
ingen | +0.178 |
Neg logit contributions | |
manif | -0.279 |
incent | -0.260 |
ngth | -0.255 |
regulators | -0.248 |
equations | -0.246 |
Token | Bull |
Token ID | 39549 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Interstitial | +0.239 |
ovember | +0.212 |
DK | +0.210 |
ドラゴン | +0.193 |
ingen | +0.191 |
Neg logit contributions | |
manif | -0.328 |
incent | -0.312 |
ngth | -0.306 |
regulators | -0.288 |
undermin | -0.284 |
Token | s |
Token ID | 82 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
manif | +0.081 |
incent | +0.076 |
ngth | +0.073 |
regulators | +0.069 |
undermin | +0.067 |
Neg logit contributions | |
Interstitial | -0.100 |
ovember | -0.092 |
DK | -0.092 |
ドラゴン | -0.086 |
ingen | -0.084 |
Token | — |
Token ID | 851 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
manif | +0.167 |
incent | +0.158 |
ngth | +0.154 |
regulators | +0.146 |
undermin | +0.144 |
Neg logit contributions | |
Interstitial | -0.127 |
ovember | -0.113 |
DK | -0.112 |
ドラゴン | -0.103 |
ingen | -0.102 |
Token | Cody |
Token ID | 27035 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
Interstitial | +0.371 |
ovember | +0.329 |
DK | +0.326 |
ドラゴン | +0.295 |
ingen | +0.292 |
Neg logit contributions | |
manif | -0.550 |
incent | -0.525 |
ngth | -0.510 |
regulators | -0.486 |
equations | -0.480 |
Token | Wester |
Token ID | 32104 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
Interstitial | +0.186 |
DK | +0.166 |
ovember | +0.166 |
ドラゴン | +0.152 |
ingen | +0.149 |
Neg logit contributions | |
manif | -0.250 |
incent | -0.236 |
ngth | -0.234 |
regulators | -0.222 |
equations | -0.217 |
Token | lund |
Token ID | 37525 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Interstitial | +0.339 |
ovember | +0.308 |
DK | +0.305 |
ドラゴン | +0.282 |
ement | +0.275 |
Neg logit contributions | |
manif | -0.390 |
incent | -0.369 |
ngth | -0.358 |
regulators | -0.337 |
equations | -0.332 |
Token | (@ |
Token ID | 4275 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Interstitial | +0.724 |
ovember | +0.620 |
DK | +0.616 |
ドラゴン | +0.539 |
ingen | +0.525 |
Neg logit contributions | |
manif | -1.616 |
incent | -1.552 |
ngth | -1.521 |
regulators | -1.448 |
equations | -1.436 |
Token | C |
Token ID | 34 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
manif | +0.184 |
incent | +0.173 |
ngth | +0.170 |
regulators | +0.158 |
undermin | +0.156 |
Neg logit contributions | |
Interstitial | -0.169 |
ovember | -0.154 |
DK | -0.152 |
ドラゴン | -0.141 |
ingen | -0.139 |
Token | ody |
Token ID | 1118 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
Interstitial | +0.222 |
ovember | +0.204 |
DK | +0.203 |
ドラゴン | +0.192 |
ingen | +0.188 |
Neg logit contributions | |
manif | -0.175 |
incent | -0.164 |
ngth | -0.159 |
regulators | -0.147 |
equations | -0.144 |
Token | W |
Token ID | 54 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Interstitial | +0.153 |
ovember | +0.137 |
DK | +0.135 |
ドラゴン | +0.126 |
ingen | +0.123 |
Neg logit contributions | |
manif | -0.189 |
incent | -0.179 |
ngth | -0.177 |
regulators | -0.165 |
undermin | -0.163 |
Token | ester |
Token ID | 7834 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Interstitial | +0.229 |
ovember | +0.202 |
DK | +0.196 |
ドラゴン | +0.184 |
ゼウス | +0.178 |
Neg logit contributions | |
manif | -0.354 |
incent | -0.342 |
ngth | -0.337 |
regulators | -0.319 |
ratios | -0.312 |
Token | of |
Token ID | 286 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Interstitial | +0.668 |
DK | +0.609 |
ovember | +0.608 |
ドラゴン | +0.556 |
ingen | +0.552 |
Neg logit contributions | |
manif | -0.761 |
incent | -0.724 |
ngth | -0.703 |
regulators | -0.658 |
undermin | -0.654 |
Token | misconduct |
Token ID | 17063 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
manif | +0.078 |
incent | +0.074 |
ngth | +0.070 |
regulators | +0.067 |
equations | +0.065 |
Neg logit contributions | |
Interstitial | -0.097 |
ovember | -0.089 |
DK | -0.089 |
ドラゴン | -0.082 |
lan | -0.082 |
Token | as |
Token ID | 355 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
manif | +0.381 |
incent | +0.362 |
ngth | +0.351 |
regulators | +0.330 |
undermin | +0.327 |
Neg logit contributions | |
Interstitial | -0.337 |
ovember | -0.306 |
DK | -0.305 |
ドラゴン | -0.279 |
ingen | -0.277 |
Token | " |
Token ID | 366 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
manif | +0.040 |
incent | +0.038 |
ngth | +0.036 |
regulators | +0.034 |
undermin | +0.034 |
Neg logit contributions | |
Interstitial | -0.040 |
ovember | -0.036 |
DK | -0.036 |
ドラゴン | -0.033 |
ingen | -0.033 |
Token | fab |
Token ID | 36434 |
Feature activation | +6.37e-02 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.099 |
ngth | +0.096 |
regulators | +0.091 |
undermin | +0.090 |
Neg logit contributions | |
Interstitial | -0.092 |
ovember | -0.083 |
DK | -0.083 |
ドラゴン | -0.076 |
ingen | -0.075 |
Token | ric |
Token ID | 1173 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
manif | +0.078 |
incent | +0.076 |
ngth | +0.074 |
regulators | +0.071 |
equations | +0.070 |
Neg logit contributions | |
Interstitial | -0.030 |
ovember | -0.025 |
DK | -0.025 |
ドラゴン | -0.022 |
ingen | -0.021 |
Token | ation |
Token ID | 341 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
Interstitial | +1.097 |
ovember | +1.000 |
DK | +0.997 |
ドラゴン | +0.916 |
ingen | +0.909 |
Neg logit contributions | |
manif | -1.157 |
incent | -1.098 |
ngth | -1.066 |
regulators | -0.999 |
undermin | -0.988 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Interstitial | +0.594 |
ovember | +0.541 |
DK | +0.540 |
ドラゴン | +0.497 |
ingen | +0.492 |
Neg logit contributions | |
manif | -0.619 |
incent | -0.588 |
ngth | -0.570 |
regulators | -0.535 |
undermin | -0.528 |
Token | fals |
Token ID | 27807 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
manif | +0.086 |
incent | +0.080 |
ngth | +0.077 |
regulators | +0.071 |
undermin | +0.070 |
Neg logit contributions | |
Interstitial | -0.119 |
ovember | -0.110 |
DK | -0.110 |
ドラゴン | -0.103 |
lan | -0.101 |
Token | ification |
Token ID | 2649 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
manif | +0.154 |
incent | +0.147 |
ngth | +0.143 |
regulators | +0.136 |
ratios | +0.134 |
Neg logit contributions | |
Interstitial | -0.114 |
DK | -0.101 |
ovember | -0.101 |
ドラゴン | -0.093 |
ingen | -0.090 |
Token | or |
Token ID | 393 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
manif | +0.172 |
incent | +0.164 |
ngth | +0.159 |
regulators | +0.150 |
undermin | +0.149 |
Neg logit contributions | |
Interstitial | -0.133 |
ovember | -0.120 |
DK | -0.120 |
ドラゴン | -0.109 |
ingen | -0.107 |
Token | by |
Token ID | 416 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Interstitial | +0.292 |
ovember | +0.264 |
DK | +0.264 |
ドラゴン | +0.241 |
ingen | +0.239 |
Neg logit contributions | |
manif | -0.343 |
incent | -0.326 |
ngth | -0.317 |
regulators | -0.299 |
undermin | -0.295 |
Token | everyone |
Token ID | 2506 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
manif | +0.143 |
incent | +0.135 |
ngth | +0.130 |
regulators | +0.123 |
undermin | +0.121 |
Neg logit contributions | |
Interstitial | -0.165 |
ovember | -0.150 |
DK | -0.150 |
ドラゴン | -0.139 |
ingen | -0.138 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
manif | +0.084 |
incent | +0.080 |
ngth | +0.077 |
regulators | +0.073 |
undermin | +0.072 |
Neg logit contributions | |
Interstitial | -0.076 |
ovember | -0.069 |
DK | -0.069 |
ドラゴン | -0.063 |
ingen | -0.062 |
Token | including |
Token ID | 1390 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
manif | +0.016 |
incent | +0.015 |
ngth | +0.014 |
regulators | +0.014 |
undermin | +0.013 |
Neg logit contributions | |
Interstitial | -0.018 |
ovember | -0.017 |
DK | -0.017 |
ドラゴン | -0.015 |
ingen | -0.015 |
Token | Steve |
Token ID | 6542 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
manif | +0.050 |
incent | +0.048 |
ngth | +0.046 |
regulators | +0.044 |
undermin | +0.043 |
Neg logit contributions | |
Interstitial | -0.046 |
ovember | -0.041 |
DK | -0.041 |
ドラゴン | -0.038 |
ingen | -0.037 |
Token | Sail |
Token ID | 27783 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Interstitial | +0.186 |
DK | +0.165 |
ovember | +0.165 |
ドラゴン | +0.151 |
ingen | +0.148 |
Neg logit contributions | |
manif | -0.239 |
incent | -0.227 |
ngth | -0.221 |
regulators | -0.210 |
undermin | -0.207 |
Token | er |
Token ID | 263 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Interstitial | +0.488 |
DK | +0.402 |
ovember | +0.398 |
ingen | +0.321 |
ドラゴン | +0.321 |
Neg logit contributions | |
manif | -1.656 |
incent | -1.611 |
ngth | -1.580 |
regulators | -1.512 |
undermin | -1.503 |
Token | , |
Token ID | 11 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
Interstitial | +0.025 |
ovember | +0.022 |
DK | +0.022 |
ドラゴン | +0.020 |
ingen | +0.020 |
Neg logit contributions | |
manif | -0.030 |
incent | -0.029 |
ngth | -0.028 |
regulators | -0.026 |
undermin | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
manif | +0.056 |
incent | +0.053 |
ngth | +0.051 |
regulators | +0.048 |
undermin | +0.048 |
Neg logit contributions | |
Interstitial | -0.055 |
ovember | -0.050 |
DK | -0.050 |
ドラゴン | -0.046 |
ingen | -0.045 |
Token | that |
Token ID | 326 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
manif | +0.044 |
incent | +0.041 |
ngth | +0.040 |
regulators | +0.038 |
undermin | +0.037 |
Neg logit contributions | |
Interstitial | -0.049 |
ovember | -0.045 |
DK | -0.045 |
ドラゴン | -0.042 |
ingen | -0.041 |
Token | is |
Token ID | 318 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
manif | +0.039 |
incent | +0.037 |
ngth | +0.036 |
regulators | +0.034 |
undermin | +0.033 |
Neg logit contributions | |
Interstitial | -0.033 |
ovember | -0.030 |
DK | -0.030 |
ドラゴン | -0.027 |
ingen | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
Interstitial | +0.019 |
ovember | +0.018 |
DK | +0.018 |
ドラゴン | +0.016 |
ingen | +0.016 |
Neg logit contributions | |
manif | -0.020 |
incent | -0.019 |
ngth | -0.019 |
regulators | -0.018 |
ratios | -0.017 |
Token | evolve |
Token ID | 18101 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
manif | +0.067 |
incent | +0.063 |
ngth | +0.061 |
regulators | +0.057 |
undermin | +0.056 |
Neg logit contributions | |
Interstitial | -0.079 |
DK | -0.073 |
ovember | -0.073 |
ドラゴン | -0.068 |
ingen | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | -7.68e-03 |
Pos logit contributions | |
Interstitial | +0.042 |
ovember | +0.038 |
DK | +0.038 |
ドラゴン | +0.035 |
ingen | +0.034 |
Neg logit contributions | |
manif | -0.044 |
incent | -0.042 |
ngth | -0.040 |
regulators | -0.038 |
equations | -0.038 |
Token | fill |
Token ID | 6070 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
Interstitial | +0.007 |
ovember | +0.006 |
DK | +0.006 |
ドラゴン | +0.006 |
ingen | +0.006 |
Neg logit contributions | |
manif | -0.006 |
incent | -0.006 |
ngth | -0.006 |
regulators | -0.005 |
undermin | -0.005 |
Token | ecological |
Token ID | 25047 |
Feature activation | -6.38e-02 |
Pos logit contributions | |
Interstitial | +0.046 |
DK | +0.043 |
ovember | +0.042 |
ドラゴン | +0.039 |
ingen | +0.039 |
Neg logit contributions | |
manif | -0.044 |
incent | -0.041 |
ngth | -0.040 |
regulators | -0.038 |
equations | -0.037 |
Token | nic |
Token ID | 9200 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Interstitial | +0.051 |
DK | +0.046 |
ovember | +0.046 |
ドラゴン | +0.042 |
ingen | +0.042 |
Neg logit contributions | |
manif | -0.058 |
incent | -0.055 |
ngth | -0.053 |
regulators | -0.051 |
equations | -0.050 |
Token | hes |
Token ID | 956 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
Interstitial | +0.942 |
ovember | +0.846 |
DK | +0.846 |
ドラゴン | +0.769 |
ingen | +0.759 |
Neg logit contributions | |
manif | -1.213 |
incent | -1.156 |
ngth | -1.123 |
regulators | -1.063 |
undermin | -1.049 |
Token | left |
Token ID | 1364 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
Interstitial | +0.304 |
ovember | +0.275 |
DK | +0.274 |
ドラゴン | +0.251 |
ingen | +0.247 |
Neg logit contributions | |
manif | -0.350 |
incent | -0.332 |
ngth | -0.322 |
regulators | -0.306 |
equations | -0.300 |
Token | vacant |
Token ID | 23957 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Interstitial | +0.028 |
ovember | +0.026 |
DK | +0.026 |
ドラゴン | +0.024 |
ingen | +0.024 |
Neg logit contributions | |
manif | -0.028 |
incent | -0.026 |
ngth | -0.026 |
regulators | -0.024 |
undermin | -0.024 |
Token | after |
Token ID | 706 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Interstitial | +0.233 |
ovember | +0.213 |
DK | +0.213 |
ドラゴン | +0.196 |
ingen | +0.195 |
Neg logit contributions | |
manif | -0.226 |
incent | -0.215 |
ngth | -0.208 |
regulators | -0.194 |
undermin | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | +8.04e-02 |
Pos logit contributions | |
Interstitial | +0.199 |
ovember | +0.184 |
DK | +0.183 |
ドラゴン | +0.170 |
ingen | +0.168 |
Neg logit contributions | |
manif | -0.177 |
incent | -0.167 |
ngth | -0.161 |
regulators | -0.152 |
equations | -0.149 |
Token | 29 |
Token ID | 1959 |
Feature activation | -6.92e-02 |
Pos logit contributions | |
Interstitial | +0.129 |
ovember | +0.117 |
DK | +0.114 |
ドラゴン | +0.104 |
ingen | +0.104 |
Neg logit contributions | |
manif | -0.176 |
incent | -0.167 |
ngth | -0.162 |
regulators | -0.156 |
equations | -0.154 |
Token | PM |
Token ID | 3122 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Interstitial | +0.054 |
ovember | +0.050 |
DK | +0.049 |
ドラゴン | +0.046 |
ingen | +0.045 |
Neg logit contributions | |
manif | -0.063 |
incent | -0.060 |
ngth | -0.058 |
regulators | -0.055 |
undermin | -0.054 |
Token |
|
Token ID | 198 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
manif | +0.038 |
incent | +0.037 |
ngth | +0.035 |
regulators | +0.034 |
equations | +0.033 |
Neg logit contributions | |
Interstitial | -0.035 |
ovember | -0.033 |
DK | -0.032 |
ドラゴン | -0.030 |
ingen | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
manif | +0.063 |
incent | +0.059 |
ngth | +0.057 |
regulators | +0.056 |
equations | +0.055 |
Neg logit contributions | |
Interstitial | -0.054 |
ovember | -0.049 |
DK | -0.048 |
ドラゴン | -0.045 |
ingen | -0.044 |
Token | Ar |
Token ID | 3163 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
manif | +0.014 |
incent | +0.014 |
ngth | +0.013 |
regulators | +0.013 |
equations | +0.012 |
Neg logit contributions | |
Interstitial | -0.010 |
ovember | -0.010 |
DK | -0.009 |
ドラゴン | -0.009 |
ingen | -0.008 |
Token | rest |
Token ID | 2118 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
manif | +0.165 |
incent | +0.156 |
ngth | +0.155 |
regulators | +0.144 |
ratios | +0.142 |
Neg logit contributions | |
Interstitial | -0.124 |
ovember | -0.112 |
DK | -0.111 |
ドラゴン | -0.103 |
ingen | -0.098 |
Token | ing |
Token ID | 278 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Interstitial | +0.740 |
ovember | +0.645 |
DK | +0.644 |
ドラゴン | +0.568 |
ingen | +0.560 |
Neg logit contributions | |
manif | -1.403 |
incent | -1.346 |
ngth | -1.314 |
regulators | -1.254 |
undermin | -1.241 |
Token | Agency |
Token ID | 7732 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
Interstitial | +0.462 |
DK | +0.416 |
ovember | +0.416 |
ドラゴン | +0.381 |
ingen | +0.380 |
Neg logit contributions | |
manif | -0.518 |
incent | -0.492 |
ngth | -0.476 |
regulators | -0.450 |
equations | -0.445 |
Token | : |
Token ID | 25 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
manif | +0.081 |
incent | +0.077 |
ngth | +0.075 |
regulators | +0.071 |
equations | +0.070 |
Neg logit contributions | |
Interstitial | -0.068 |
ovember | -0.061 |
DK | -0.061 |
ドラゴン | -0.056 |
ingen | -0.055 |
Token | TT |
Token ID | 26653 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Interstitial | +0.187 |
ovember | +0.169 |
DK | +0.167 |
ドラゴン | +0.152 |
ingen | +0.150 |
Neg logit contributions | |
manif | -0.244 |
incent | -0.234 |
ngth | -0.228 |
regulators | -0.216 |
equations | -0.212 |
Token | PD |
Token ID | 5760 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
manif | +0.356 |
incent | +0.340 |
ngth | +0.332 |
regulators | +0.313 |
undermin | +0.307 |
Neg logit contributions | |
Interstitial | -0.282 |
ovember | -0.255 |
DK | -0.252 |
ドラゴン | -0.232 |
ingen | -0.228 |
Token | � |
Token ID | 247 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
Interstitial | +0.031 |
ovember | +0.029 |
DK | +0.029 |
ドラゴン | +0.026 |
ingen | +0.026 |
Neg logit contributions | |
manif | -0.033 |
incent | -0.031 |
ngth | -0.030 |
regulators | -0.028 |
ratios | -0.028 |
Token | m |
Token ID | 76 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Interstitial | +0.039 |
ovember | +0.036 |
DK | +0.036 |
ドラゴン | +0.033 |
ingen | +0.033 |
Neg logit contributions | |
manif | -0.040 |
incent | -0.038 |
ngth | -0.037 |
regulators | -0.034 |
equations | -0.033 |
Token | pro |
Token ID | 386 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.098 |
ngth | +0.095 |
regulators | +0.089 |
undermin | +0.088 |
Neg logit contributions | |
Interstitial | -0.107 |
ovember | -0.098 |
DK | -0.098 |
ドラゴン | -0.091 |
ingen | -0.089 |
Token | - |
Token ID | 12 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
manif | +0.086 |
incent | +0.081 |
ngth | +0.079 |
regulators | +0.074 |
undermin | +0.073 |
Neg logit contributions | |
Interstitial | -0.087 |
ovember | -0.080 |
DK | -0.080 |
ドラゴン | -0.073 |
ingen | -0.073 |
Token | lab |
Token ID | 23912 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Interstitial | +0.003 |
ovember | +0.002 |
DK | +0.002 |
ドラゴン | +0.002 |
ingen | +0.002 |
Neg logit contributions | |
manif | -0.003 |
incent | -0.003 |
ngth | -0.003 |
regulators | -0.003 |
undermin | -0.002 |
Token | our |
Token ID | 454 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Interstitial | +0.117 |
ovember | +0.101 |
DK | +0.101 |
ドラゴン | +0.087 |
ingen | +0.086 |
Neg logit contributions | |
manif | -0.250 |
incent | -0.241 |
ngth | -0.235 |
regulators | -0.224 |
undermin | -0.222 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
Interstitial | +0.961 |
DK | +0.871 |
ovember | +0.866 |
ドラゴン | +0.795 |
lan | +0.788 |
Neg logit contributions | |
manif | -1.154 |
incent | -1.096 |
ngth | -1.069 |
regulators | -1.003 |
undermin | -0.994 |
Token | pro |
Token ID | 386 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
manif | +0.032 |
incent | +0.030 |
ngth | +0.029 |
regulators | +0.028 |
undermin | +0.027 |
Neg logit contributions | |
Interstitial | -0.030 |
ovember | -0.027 |
DK | -0.027 |
ドラゴン | -0.025 |
ingen | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
manif | +0.050 |
incent | +0.047 |
ngth | +0.046 |
regulators | +0.043 |
undermin | +0.042 |
Neg logit contributions | |
Interstitial | -0.049 |
ovember | -0.045 |
DK | -0.045 |
ドラゴン | -0.041 |
ingen | -0.041 |
Token | worker |
Token ID | 28816 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
Interstitial | +0.030 |
ovember | +0.027 |
DK | +0.027 |
ドラゴン | +0.025 |
ingen | +0.025 |
Neg logit contributions | |
manif | -0.031 |
incent | -0.029 |
ngth | -0.029 |
regulators | -0.027 |
undermin | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
manif | +0.054 |
incent | +0.051 |
ngth | +0.050 |
regulators | +0.047 |
undermin | +0.046 |
Neg logit contributions | |
Interstitial | -0.044 |
ovember | -0.040 |
DK | -0.040 |
ドラゴン | -0.037 |
ingen | -0.036 |
Token | man |
Token ID | 805 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Interstitial | +0.448 |
ovember | +0.402 |
DK | +0.402 |
ドラゴン | +0.365 |
ingen | +0.358 |
Neg logit contributions | |
manif | -0.586 |
incent | -0.558 |
ngth | -0.544 |
regulators | -0.513 |
undermin | -0.507 |
Token | abad |
Token ID | 17325 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Interstitial | +0.140 |
ovember | +0.127 |
DK | +0.127 |
ドラゴン | +0.117 |
ingen | +0.114 |
Neg logit contributions | |
manif | -0.154 |
incent | -0.146 |
ngth | -0.141 |
regulators | -0.134 |
equations | -0.131 |
Token | districts |
Token ID | 12815 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
manif | +0.290 |
incent | +0.274 |
ngth | +0.265 |
regulators | +0.250 |
equations | +0.246 |
Neg logit contributions | |
Interstitial | -0.293 |
ovember | -0.267 |
DK | -0.266 |
ドラゴン | -0.247 |
ingen | -0.242 |
Token | alleging |
Token ID | 26116 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Interstitial | +0.442 |
ovember | +0.403 |
DK | +0.402 |
ドラゴン | +0.372 |
ingen | +0.367 |
Neg logit contributions | |
manif | -0.439 |
incent | -0.416 |
ngth | -0.402 |
regulators | -0.378 |
undermin | -0.372 |
Token | " |
Token ID | 366 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
Interstitial | +0.192 |
ovember | +0.177 |
DK | +0.176 |
ドラゴン | +0.164 |
ingen | +0.162 |
Neg logit contributions | |
manif | -0.162 |
incent | -0.152 |
ngth | -0.147 |
regulators | -0.138 |
undermin | -0.135 |
Token | gross |
Token ID | 47181 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Interstitial | +0.130 |
ovember | +0.119 |
DK | +0.118 |
ドラゴン | +0.108 |
ingen | +0.107 |
Neg logit contributions | |
manif | -0.144 |
incent | -0.136 |
ngth | -0.132 |
regulators | -0.125 |
undermin | -0.123 |
Token | abuse |
Token ID | 5076 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Interstitial | +1.200 |
ovember | +1.103 |
DK | +1.101 |
ドラゴン | +1.026 |
ingen | +1.026 |
Neg logit contributions | |
manif | -0.901 |
incent | -0.847 |
ngth | -0.822 |
regulators | -0.753 |
undermin | -0.742 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
manif | +0.048 |
incent | +0.045 |
ngth | +0.044 |
regulators | +0.042 |
undermin | +0.041 |
Neg logit contributions | |
Interstitial | -0.041 |
ovember | -0.038 |
DK | -0.037 |
ドラゴン | -0.034 |
ingen | -0.034 |
Token | power |
Token ID | 1176 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.097 |
ngth | +0.093 |
regulators | +0.087 |
undermin | +0.085 |
Neg logit contributions | |
Interstitial | -0.142 |
ovember | -0.131 |
DK | -0.131 |
ドラゴン | -0.122 |
ingen | -0.121 |
Token | " |
Token ID | 1 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
manif | +0.171 |
incent | +0.162 |
ngth | +0.157 |
regulators | +0.147 |
undermin | +0.145 |
Neg logit contributions | |
Interstitial | -0.165 |
ovember | -0.150 |
DK | -0.150 |
ドラゴン | -0.138 |
ingen | -0.137 |
Token | by |
Token ID | 416 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
manif | +0.158 |
incent | +0.150 |
ngth | +0.145 |
regulators | +0.136 |
undermin | +0.134 |
Neg logit contributions | |
Interstitial | -0.162 |
ovember | -0.148 |
DK | -0.147 |
ドラゴン | -0.136 |
ingen | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | -8.95e-02 |
Pos logit contributions | |
Interstitial | +0.100 |
ovember | +0.092 |
DK | +0.091 |
ドラゴン | +0.084 |
ingen | +0.083 |
Neg logit contributions | |
manif | -0.103 |
incent | -0.097 |
ngth | -0.094 |
regulators | -0.089 |
undermin | -0.087 |
Token | See |
Token ID | 4091 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
Interstitial | +0.066 |
ovember | +0.059 |
DK | +0.059 |
ドラゴン | +0.054 |
ingen | +0.053 |
Neg logit contributions | |
manif | -0.086 |
incent | -0.082 |
ngth | -0.080 |
regulators | -0.076 |
undermin | -0.075 |
Token | more |
Token ID | 517 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
manif | +0.190 |
incent | +0.180 |
ngth | +0.174 |
regulators | +0.163 |
undermin | +0.160 |
Neg logit contributions | |
Interstitial | -0.213 |
ovember | -0.196 |
DK | -0.196 |
ドラゴン | -0.181 |
ingen | -0.180 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Interstitial | +0.028 |
ovember | +0.025 |
DK | +0.025 |
ドラゴン | +0.022 |
ingen | +0.022 |
Neg logit contributions | |
manif | -0.042 |
incent | -0.040 |
ngth | -0.039 |
regulators | -0.037 |
undermin | -0.036 |
Token | Dub |
Token ID | 37590 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Interstitial | +0.097 |
ovember | +0.088 |
DK | +0.087 |
ドラゴン | +0.079 |
ingen | +0.078 |
Neg logit contributions | |
manif | -0.129 |
incent | -0.123 |
ngth | -0.120 |
regulators | -0.114 |
equations | -0.112 |
Token | lin |
Token ID | 2815 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Interstitial | +0.007 |
ovember | +0.007 |
DK | +0.007 |
ドラゴン | +0.006 |
ingen | +0.006 |
Neg logit contributions | |
manif | -0.010 |
incent | -0.009 |
ngth | -0.009 |
regulators | -0.009 |
undermin | -0.009 |
Token | is |
Token ID | 318 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
Interstitial | +0.992 |
ovember | +0.899 |
DK | +0.898 |
ドラゴン | +0.824 |
ingen | +0.813 |
Neg logit contributions | |
manif | -1.096 |
incent | -1.039 |
ngth | -1.007 |
regulators | -0.954 |
undermin | -0.936 |
Token | a |
Token ID | 257 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
manif | +0.032 |
incent | +0.030 |
ngth | +0.028 |
regulators | +0.027 |
undermin | +0.026 |
Neg logit contributions | |
Interstitial | -0.037 |
ovember | -0.033 |
DK | -0.033 |
ドラゴン | -0.031 |
ingen | -0.031 |
Token | small |
Token ID | 1402 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
manif | +0.019 |
incent | +0.018 |
ngth | +0.017 |
regulators | +0.016 |
undermin | +0.016 |
Neg logit contributions | |
Interstitial | -0.021 |
ovember | -0.019 |
DK | -0.019 |
ドラゴン | -0.018 |
ingen | -0.018 |
Token | town |
Token ID | 3240 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Interstitial | +0.460 |
ovember | +0.419 |
DK | +0.419 |
ドラゴン | +0.386 |
ingen | +0.379 |
Neg logit contributions | |
manif | -0.450 |
incent | -0.425 |
ngth | -0.410 |
regulators | -0.388 |
equations | -0.380 |
Token | ( |
Token ID | 357 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Interstitial | +0.239 |
ovember | +0.217 |
DK | +0.214 |
ドラゴン | +0.198 |
ingen | +0.194 |
Neg logit contributions | |
manif | -0.260 |
incent | -0.245 |
ngth | -0.236 |
regulators | -0.225 |
equations | -0.221 |
Token | f |
Token ID | 69 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Interstitial | +0.296 |
ovember | +0.266 |
DK | +0.265 |
ドラゴン | +0.242 |
ingen | +0.239 |
Neg logit contributions | |
manif | -0.382 |
incent | -0.365 |
ngth | -0.354 |
regulators | -0.335 |
equations | -0.330 |
Token | — |
Token ID | 851 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Interstitial | +0.135 |
ovember | +0.121 |
DK | +0.121 |
ドラゴン | +0.110 |
ingen | +0.108 |
Neg logit contributions | |
manif | -0.181 |
incent | -0.173 |
ngth | -0.168 |
regulators | -0.159 |
equations | -0.157 |
Token | / |
Token ID | 14 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
Interstitial | +0.283 |
ovember | +0.254 |
DK | +0.253 |
ドラゴン | +0.229 |
ingen | +0.227 |
Neg logit contributions | |
manif | -0.385 |
incent | -0.369 |
ngth | -0.358 |
regulators | -0.340 |
equations | -0.335 |
Token | prom |
Token ID | 16963 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
manif | +0.067 |
incent | +0.063 |
ngth | +0.061 |
regulators | +0.058 |
undermin | +0.057 |
Neg logit contributions | |
Interstitial | -0.063 |
ovember | -0.057 |
DK | -0.057 |
ドラゴン | -0.052 |
ingen | -0.052 |
Token | pt |
Token ID | 457 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
manif | +0.086 |
incent | +0.083 |
ngth | +0.080 |
regulators | +0.076 |
ratios | +0.074 |
Neg logit contributions | |
Interstitial | -0.069 |
DK | -0.062 |
ovember | -0.061 |
ドラゴン | -0.056 |
ingen | -0.055 |
Token | log |
Token ID | 6404 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Interstitial | +0.194 |
ovember | +0.177 |
DK | +0.176 |
ドラゴン | +0.162 |
ingen | +0.160 |
Neg logit contributions | |
manif | -0.211 |
incent | -0.200 |
ngth | -0.194 |
regulators | -0.183 |
undermin | -0.180 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Interstitial | +0.984 |
ovember | +0.893 |
DK | +0.892 |
ドラゴン | +0.818 |
ingen | +0.808 |
Neg logit contributions | |
manif | -1.098 |
incent | -1.044 |
ngth | -1.012 |
regulators | -0.953 |
undermin | -0.941 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Interstitial | +0.171 |
ovember | +0.156 |
DK | +0.153 |
ドラゴン | +0.141 |
ingen | +0.139 |
Neg logit contributions | |
manif | -0.207 |
incent | -0.194 |
ngth | -0.190 |
regulators | -0.183 |
equations | -0.180 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Interstitial | +0.190 |
ovember | +0.172 |
DK | +0.171 |
ドラゴン | +0.156 |
ingen | +0.153 |
Neg logit contributions | |
manif | -0.253 |
incent | -0.241 |
ngth | -0.235 |
regulators | -0.222 |
undermin | -0.219 |
Token | 38 |
Token ID | 2548 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Interstitial | +0.190 |
ovember | +0.170 |
DK | +0.169 |
ドラゴン | +0.156 |
ingen | +0.153 |
Neg logit contributions | |
manif | -0.237 |
incent | -0.227 |
ngth | -0.220 |
regulators | -0.208 |
equations | -0.205 |
Token | ac |
Token ID | 330 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Interstitial | +0.241 |
ovember | +0.216 |
DK | +0.216 |
ドラゴン | +0.197 |
ingen | +0.196 |
Neg logit contributions | |
manif | -0.290 |
incent | -0.277 |
ngth | -0.267 |
regulators | -0.254 |
equations | -0.250 |
Token | ven |
Token ID | 574 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
manif | +0.198 |
incent | +0.188 |
ngth | +0.182 |
regulators | +0.171 |
undermin | +0.169 |
Neg logit contributions | |
Interstitial | -0.190 |
ovember | -0.173 |
DK | -0.173 |
ドラゴン | -0.159 |
ingen | -0.158 |
Token | Miner |
Token ID | 29295 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
manif | +0.447 |
incent | +0.425 |
ngth | +0.413 |
regulators | +0.391 |
undermin | +0.385 |
Neg logit contributions | |
Interstitial | -0.356 |
ovember | -0.320 |
DK | -0.318 |
ドラゴン | -0.291 |
ingen | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Interstitial | +0.100 |
ovember | +0.089 |
DK | +0.089 |
ドラゴン | +0.081 |
ingen | +0.080 |
Neg logit contributions | |
manif | -0.125 |
incent | -0.119 |
ngth | -0.116 |
regulators | -0.109 |
undermin | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
Interstitial | +0.035 |
ovember | +0.032 |
DK | +0.031 |
ドラゴン | +0.029 |
ingen | +0.029 |
Neg logit contributions | |
manif | -0.041 |
incent | -0.039 |
ngth | -0.038 |
regulators | -0.037 |
equations | -0.036 |
Token | Fab |
Token ID | 43957 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
Interstitial | +0.055 |
ovember | +0.050 |
DK | +0.049 |
ドラゴン | +0.045 |
ingen | +0.044 |
Neg logit contributions | |
manif | -0.077 |
incent | -0.074 |
ngth | -0.072 |
regulators | -0.068 |
equations | -0.067 |
Token | ric |
Token ID | 1173 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
manif | +0.030 |
incent | +0.029 |
ngth | +0.028 |
regulators | +0.027 |
equations | +0.027 |
Neg logit contributions | |
Interstitial | -0.018 |
ovember | -0.016 |
DK | -0.016 |
ドラゴン | -0.014 |
ingen | -0.014 |
Token | ate |
Token ID | 378 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Interstitial | +0.945 |
ovember | +0.856 |
DK | +0.854 |
ドラゴン | +0.780 |
ingen | +0.771 |
Neg logit contributions | |
manif | -1.120 |
incent | -1.067 |
ngth | -1.036 |
regulators | -0.976 |
undermin | -0.966 |
Token | vs |
Token ID | 3691 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Interstitial | +0.071 |
ovember | +0.064 |
DK | +0.063 |
ドラゴン | +0.057 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.101 |
incent | -0.097 |
ngth | -0.094 |
regulators | -0.089 |
undermin | -0.088 |
Token | Ever |
Token ID | 10776 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Interstitial | +0.211 |
ovember | +0.191 |
DK | +0.188 |
ドラゴン | +0.172 |
ingen | +0.170 |
Neg logit contributions | |
manif | -0.265 |
incent | -0.252 |
ngth | -0.245 |
regulators | -0.232 |
equations | -0.228 |
Token | gl |
Token ID | 4743 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
manif | +0.213 |
incent | +0.202 |
ngth | +0.200 |
regulators | +0.187 |
equations | +0.184 |
Neg logit contributions | |
Interstitial | -0.173 |
ovember | -0.155 |
DK | -0.154 |
ドラゴン | -0.141 |
ingen | -0.139 |
Token | ove |
Token ID | 659 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
manif | +0.117 |
incent | +0.110 |
ngth | +0.108 |
regulators | +0.102 |
ratios | +0.101 |
Neg logit contributions | |
Interstitial | -0.089 |
ovember | -0.079 |
DK | -0.079 |
ドラゴン | -0.074 |
ゼウス | -0.070 |
Token | different |
Token ID | 1180 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
manif | +0.165 |
incent | +0.155 |
ngth | +0.148 |
regulators | +0.140 |
equations | +0.138 |
Neg logit contributions | |
Interstitial | -0.190 |
DK | -0.174 |
ovember | -0.174 |
ドラゴン | -0.161 |
ingen | -0.159 |
Token | concepts |
Token ID | 10838 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
Interstitial | +0.234 |
DK | +0.217 |
ovember | +0.217 |
ドラゴン | +0.201 |
ingen | +0.200 |
Neg logit contributions | |
manif | -0.176 |
incent | -0.164 |
ngth | -0.157 |
regulators | -0.147 |
equations | -0.144 |
Token | from |
Token ID | 422 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
Interstitial | +0.006 |
DK | +0.005 |
ovember | +0.005 |
ドラゴン | +0.005 |
ingen | +0.004 |
Neg logit contributions | |
manif | -0.007 |
incent | -0.007 |
ngth | -0.007 |
regulators | -0.006 |
equations | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Interstitial | +0.039 |
DK | +0.035 |
ovember | +0.035 |
ドラゴン | +0.032 |
ingen | +0.032 |
Neg logit contributions | |
manif | -0.043 |
incent | -0.040 |
ngth | -0.039 |
regulators | -0.037 |
equations | -0.036 |
Token | arg |
Token ID | 1822 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
Interstitial | +0.098 |
DK | +0.089 |
ovember | +0.089 |
ドラゴン | +0.082 |
ingen | +0.081 |
Neg logit contributions | |
manif | -0.095 |
incent | -0.090 |
ngth | -0.087 |
regulators | -0.082 |
equations | -0.081 |
Token | uable |
Token ID | 7153 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
manif | +0.053 |
incent | +0.051 |
ngth | +0.049 |
regulators | +0.046 |
equations | +0.046 |
Neg logit contributions | |
Interstitial | -0.046 |
ovember | -0.041 |
DK | -0.041 |
ドラゴン | -0.038 |
ingen | -0.037 |
Token | king |
Token ID | 5822 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Interstitial | +1.054 |
ovember | +0.964 |
DK | +0.963 |
ドラゴン | +0.888 |
ingen | +0.880 |
Neg logit contributions | |
manif | -1.001 |
incent | -0.947 |
ngth | -0.915 |
regulators | -0.858 |
undermin | -0.846 |
Token | of |
Token ID | 286 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
manif | +0.265 |
incent | +0.249 |
ngth | +0.242 |
regulators | +0.228 |
equations | +0.226 |
Neg logit contributions | |
Interstitial | -0.251 |
DK | -0.228 |
ovember | -0.225 |
ドラゴン | -0.207 |
lan | -0.204 |
Token | curse |
Token ID | 17328 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
Interstitial | +0.098 |
DK | +0.090 |
ovember | +0.089 |
ドラゴン | +0.081 |
lan | +0.080 |
Neg logit contributions | |
manif | -0.109 |
incent | -0.102 |
ngth | -0.098 |
regulators | -0.094 |
equations | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
manif | +0.006 |
incent | +0.006 |
ngth | +0.006 |
regulators | +0.005 |
ratios | +0.005 |
Neg logit contributions | |
Interstitial | -0.007 |
DK | -0.006 |
ovember | -0.006 |
ドラゴン | -0.006 |
ingen | -0.006 |
Token | Scott |
Token ID | 4746 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Interstitial | +0.047 |
DK | +0.043 |
ovember | +0.043 |
ドラゴン | +0.039 |
ingen | +0.038 |
Neg logit contributions | |
manif | -0.062 |
incent | -0.059 |
ngth | -0.057 |
regulators | -0.054 |
undermin | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Interstitial | +0.114 |
ovember | +0.103 |
DK | +0.102 |
ドラゴン | +0.094 |
ingen | +0.093 |
Neg logit contributions | |
manif | -0.136 |
incent | -0.130 |
ngth | -0.126 |
regulators | -0.120 |
equations | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
Interstitial | +0.112 |
ovember | +0.102 |
DK | +0.100 |
ドラゴン | +0.093 |
ingen | +0.091 |
Neg logit contributions | |
manif | -0.133 |
incent | -0.124 |
ngth | -0.121 |
regulators | -0.117 |
equations | -0.116 |
Token | Chest |
Token ID | 45170 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Interstitial | +0.141 |
ovember | +0.128 |
DK | +0.125 |
ドラゴン | +0.115 |
ingen | +0.113 |
Neg logit contributions | |
manif | -0.184 |
incent | -0.175 |
ngth | -0.171 |
regulators | -0.161 |
equations | -0.159 |
Token | nut |
Token ID | 14930 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
Interstitial | +0.376 |
ovember | +0.345 |
DK | +0.345 |
ドラゴン | +0.321 |
ingen | +0.318 |
Neg logit contributions | |
manif | -0.302 |
incent | -0.284 |
ngth | -0.275 |
regulators | -0.255 |
undermin | -0.250 |
Token | Fl |
Token ID | 1610 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Interstitial | +0.044 |
ovember | +0.040 |
DK | +0.039 |
ドラゴン | +0.036 |
ingen | +0.036 |
Neg logit contributions | |
manif | -0.055 |
incent | -0.053 |
ngth | -0.051 |
regulators | -0.048 |
undermin | -0.048 |
Token | our |
Token ID | 454 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Interstitial | +0.017 |
DK | +0.014 |
ovember | +0.014 |
ドラゴン | +0.013 |
ingen | +0.012 |
Neg logit contributions | |
manif | -0.034 |
incent | -0.032 |
ngth | -0.032 |
regulators | -0.030 |
equations | -0.030 |
Token | — |
Token ID | 960 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
Interstitial | +0.981 |
ovember | +0.892 |
DK | +0.889 |
ドラゴン | +0.816 |
ingen | +0.809 |
Neg logit contributions | |
manif | -1.064 |
incent | -1.010 |
ngth | -0.981 |
regulators | -0.921 |
undermin | -0.909 |
Token | This |
Token ID | 1212 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
Interstitial | +0.190 |
ovember | +0.172 |
DK | +0.171 |
ドラゴン | +0.157 |
ingen | +0.156 |
Neg logit contributions | |
manif | -0.219 |
incent | -0.208 |
ngth | -0.202 |
regulators | -0.190 |
undermin | -0.188 |
Token | can |
Token ID | 460 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Interstitial | +0.035 |
ovember | +0.031 |
DK | +0.031 |
ドラゴン | +0.029 |
ingen | +0.029 |
Neg logit contributions | |
manif | -0.034 |
incent | -0.032 |
ngth | -0.031 |
regulators | -0.029 |
equations | -0.028 |
Token | also |
Token ID | 635 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
Interstitial | +0.160 |
ovember | +0.146 |
DK | +0.146 |
ドラゴン | +0.135 |
ingen | +0.134 |
Neg logit contributions | |
manif | -0.141 |
incent | -0.134 |
ngth | -0.129 |
regulators | -0.121 |
ratios | -0.119 |
Token | be |
Token ID | 307 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
Interstitial | +0.007 |
ovember | +0.006 |
DK | +0.006 |
ドラゴン | +0.006 |
ingen | +0.006 |
Neg logit contributions | |
manif | -0.006 |
incent | -0.006 |
ngth | -0.006 |
regulators | -0.006 |
ratios | -0.005 |
Token | Cl |
Token ID | 2601 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
manif | +0.032 |
incent | +0.030 |
ngth | +0.029 |
regulators | +0.028 |
equations | +0.028 |
Neg logit contributions | |
Interstitial | -0.022 |
ovember | -0.020 |
DK | -0.020 |
ドラゴン | -0.018 |
ingen | -0.018 |
Token | over |
Token ID | 2502 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
Interstitial | +0.161 |
DK | +0.143 |
ovember | +0.142 |
ドラゴン | +0.133 |
lan | +0.127 |
Neg logit contributions | |
manif | -0.207 |
incent | -0.196 |
ngth | -0.192 |
regulators | -0.182 |
ratios | -0.179 |
Token | field |
Token ID | 3245 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Interstitial | +0.142 |
DK | +0.126 |
ovember | +0.126 |
ドラゴン | +0.116 |
ingen | +0.113 |
Neg logit contributions | |
manif | -0.189 |
incent | -0.179 |
ngth | -0.175 |
regulators | -0.166 |
ratios | -0.163 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
manif | +0.294 |
incent | +0.278 |
ngth | +0.269 |
regulators | +0.257 |
equations | +0.252 |
Neg logit contributions | |
Interstitial | -0.252 |
ovember | -0.227 |
DK | -0.226 |
ドラゴン | -0.209 |
ingen | -0.206 |
Token | Cand |
Token ID | 41572 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Interstitial | +0.013 |
ovember | +0.011 |
DK | +0.011 |
ドラゴン | +0.010 |
ingen | +0.010 |
Neg logit contributions | |
manif | -0.018 |
incent | -0.017 |
ngth | -0.016 |
regulators | -0.016 |
equations | -0.015 |
Token | idate |
Token ID | 20540 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
manif | +0.527 |
incent | +0.506 |
ngth | +0.493 |
regulators | +0.470 |
undermin | +0.462 |
Neg logit contributions | |
Interstitial | -0.351 |
DK | -0.310 |
ovember | -0.307 |
ドラゴン | -0.285 |
ingen | -0.273 |
Token | Theme |
Token ID | 26729 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Interstitial | +0.886 |
ovember | +0.797 |
DK | +0.796 |
ドラゴン | +0.724 |
ingen | +0.716 |
Neg logit contributions | |
manif | -1.137 |
incent | -1.084 |
ngth | -1.054 |
regulators | -0.996 |
undermin | -0.985 |
Token | Songs |
Token ID | 31772 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
manif | +0.156 |
incent | +0.148 |
ngth | +0.143 |
regulators | +0.134 |
ratios | +0.132 |
Neg logit contributions | |
Interstitial | -0.161 |
DK | -0.147 |
ovember | -0.146 |
ドラゴン | -0.136 |
ingen | -0.134 |
Token | - |
Token ID | 12 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Interstitial | +0.256 |
ovember | +0.233 |
DK | +0.233 |
ドラゴン | +0.214 |
ingen | +0.212 |
Neg logit contributions | |
manif | -0.261 |
incent | -0.248 |
ngth | -0.240 |
regulators | -0.225 |
undermin | -0.222 |
Token | Scient |
Token ID | 23010 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.099 |
ngth | +0.096 |
regulators | +0.092 |
equations | +0.090 |
Neg logit contributions | |
Interstitial | -0.073 |
ovember | -0.066 |
DK | -0.065 |
ドラゴン | -0.059 |
ingen | -0.059 |
Token | log |
Token ID | 6404 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
manif | +0.218 |
incent | +0.206 |
ngth | +0.198 |
regulators | +0.184 |
undermin | +0.182 |
Neg logit contributions | |
Interstitial | -0.269 |
ovember | -0.248 |
DK | -0.248 |
ドラゴン | -0.230 |
ingen | -0.228 |
Token | from |
Token ID | 422 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
manif | +0.165 |
incent | +0.157 |
ngth | +0.152 |
regulators | +0.144 |
undermin | +0.142 |
Neg logit contributions | |
Interstitial | -0.139 |
ovember | -0.125 |
DK | -0.125 |
ドラゴン | -0.114 |
ingen | -0.113 |
Token | Pam |
Token ID | 24497 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
manif | +0.069 |
incent | +0.066 |
ngth | +0.064 |
regulators | +0.060 |
undermin | +0.059 |
Neg logit contributions | |
Interstitial | -0.059 |
ovember | -0.053 |
DK | -0.053 |
ドラゴン | -0.049 |
ingen | -0.048 |
Token | Oliver |
Token ID | 15416 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
manif | +0.282 |
incent | +0.268 |
ngth | +0.260 |
regulators | +0.246 |
undermin | +0.242 |
Neg logit contributions | |
Interstitial | -0.242 |
ovember | -0.219 |
DK | -0.218 |
ドラゴン | -0.199 |
ingen | -0.198 |
Token | to |
Token ID | 284 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
Interstitial | +0.038 |
ovember | +0.035 |
DK | +0.035 |
ドラゴン | +0.032 |
ingen | +0.032 |
Neg logit contributions | |
manif | -0.041 |
incent | -0.039 |
ngth | -0.038 |
regulators | -0.036 |
equations | -0.035 |
Token | Erin |
Token ID | 28894 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
manif | +0.042 |
incent | +0.040 |
ngth | +0.039 |
regulators | +0.037 |
undermin | +0.036 |
Neg logit contributions | |
Interstitial | -0.029 |
ovember | -0.025 |
DK | -0.025 |
ドラゴン | -0.023 |
ingen | -0.023 |
Token | Andrews |
Token ID | 26414 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Interstitial | +0.329 |
ovember | +0.293 |
DK | +0.291 |
ドラゴン | +0.264 |
ingen | +0.259 |
Neg logit contributions | |
manif | -0.472 |
incent | -0.450 |
ngth | -0.440 |
regulators | -0.417 |
undermin | -0.411 |
Token | . |
Token ID | 13 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Interstitial | +0.886 |
ovember | +0.799 |
DK | +0.797 |
ドラゴン | +0.725 |
ingen | +0.717 |
Neg logit contributions | |
manif | -1.115 |
incent | -1.062 |
ngth | -1.033 |
regulators | -0.975 |
undermin | -0.964 |
Token | Having |
Token ID | 11136 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Interstitial | +0.057 |
ovember | +0.052 |
DK | +0.051 |
ドラゴン | +0.047 |
ingen | +0.046 |
Neg logit contributions | |
manif | -0.076 |
incent | -0.073 |
ngth | -0.071 |
regulators | -0.068 |
equations | -0.067 |
Token | worked |
Token ID | 3111 |
Feature activation | -5.86e-02 |
Pos logit contributions | |
Interstitial | +0.187 |
ovember | +0.170 |
DK | +0.169 |
ドラゴン | +0.156 |
ingen | +0.154 |
Neg logit contributions | |
manif | -0.193 |
incent | -0.182 |
ngth | -0.176 |
regulators | -0.167 |
equations | -0.164 |
Token | with |
Token ID | 351 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
Interstitial | +0.043 |
ovember | +0.038 |
DK | +0.038 |
ドラゴン | +0.035 |
ingen | +0.034 |
Neg logit contributions | |
manif | -0.057 |
incent | -0.054 |
ngth | -0.053 |
regulators | -0.050 |
ratios | -0.050 |
Token | Pam |
Token ID | 24497 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
manif | +0.001 |
incent | +0.001 |
ngth | +0.001 |
regulators | +0.001 |
equations | +0.001 |
Neg logit contributions | |
Interstitial | -0.001 |
ovember | -0.001 |
DK | -0.001 |
ドラゴン | -0.001 |
ingen | -0.001 |
Token | F |
Token ID | 376 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Interstitial | +0.066 |
ovember | +0.060 |
DK | +0.060 |
ドラゴン | +0.055 |
ingen | +0.055 |
Neg logit contributions | |
manif | -0.065 |
incent | -0.061 |
ngth | -0.059 |
regulators | -0.056 |
undermin | -0.055 |
Token | ACT |
Token ID | 10659 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
Interstitial | +0.249 |
DK | +0.231 |
ovember | +0.230 |
ドラゴン | +0.219 |
ingen | +0.215 |
Neg logit contributions | |
manif | -0.136 |
incent | -0.127 |
ngth | -0.122 |
regulators | -0.111 |
equations | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
manif | +0.224 |
incent | +0.212 |
ngth | +0.204 |
regulators | +0.193 |
undermin | +0.189 |
Neg logit contributions | |
Interstitial | -0.239 |
ovember | -0.217 |
DK | -0.216 |
ドラゴン | -0.200 |
ingen | -0.199 |
Token | La |
Token ID | 4689 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
Interstitial | +0.002 |
ovember | +0.002 |
DK | +0.002 |
ドラゴン | +0.002 |
ingen | +0.002 |
Neg logit contributions | |
manif | -0.002 |
incent | -0.002 |
ngth | -0.002 |
regulators | -0.002 |
undermin | -0.001 |
Token | Be |
Token ID | 3856 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
manif | +0.014 |
incent | +0.013 |
ngth | +0.013 |
regulators | +0.012 |
undermin | +0.012 |
Neg logit contributions | |
Interstitial | -0.011 |
DK | -0.010 |
ovember | -0.010 |
ドラゴン | -0.009 |
lan | -0.009 |
Token | ouf |
Token ID | 37116 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
manif | +0.067 |
incent | +0.064 |
ngth | +0.063 |
regulators | +0.061 |
equations | +0.060 |
Neg logit contributions | |
Interstitial | -0.017 |
DK | -0.013 |
ovember | -0.013 |
ドラゴン | -0.011 |
ingen | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Interstitial | +1.021 |
ovember | +0.930 |
DK | +0.928 |
ドラゴン | +0.858 |
ingen | +0.850 |
Neg logit contributions | |
manif | -0.985 |
incent | -0.931 |
ngth | -0.899 |
regulators | -0.847 |
undermin | -0.832 |
Token | R |
Token ID | 371 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Interstitial | +0.178 |
ovember | +0.163 |
DK | +0.163 |
ドラゴン | +0.151 |
ingen | +0.149 |
Neg logit contributions | |
manif | -0.158 |
incent | -0.149 |
ngth | -0.144 |
regulators | -0.135 |
undermin | -0.133 |
Token | ön |
Token ID | 48863 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Interstitial | +0.059 |
DK | +0.053 |
ovember | +0.053 |
ドラゴン | +0.049 |
ingen | +0.048 |
Neg logit contributions | |
manif | -0.073 |
incent | -0.069 |
ngth | -0.068 |
regulators | -0.064 |
undermin | -0.063 |
Token | kk |
Token ID | 28747 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
Interstitial | +0.098 |
ovember | +0.088 |
DK | +0.088 |
ドラゴン | +0.080 |
ingen | +0.079 |
Neg logit contributions | |
manif | -0.127 |
incent | -0.121 |
ngth | -0.118 |
regulators | -0.111 |
undermin | -0.110 |
Token | ö |
Token ID | 9101 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Interstitial | +0.082 |
ovember | +0.072 |
DK | +0.072 |
ドラゴン | +0.065 |
ingen | +0.063 |
Neg logit contributions | |
manif | -0.127 |
incent | -0.121 |
ngth | -0.118 |
regulators | -0.112 |
equations | -0.110 |
Token | < |
Token ID | 1279 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Interstitial | +0.087 |
ovember | +0.076 |
DK | +0.072 |
ドラゴン | +0.060 |
ingen | +0.060 |
Neg logit contributions | |
manif | -0.239 |
incent | -0.228 |
ngth | -0.223 |
regulators | -0.218 |
equations | -0.216 |
Token | ' |
Token ID | 705 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Interstitial | +0.410 |
ovember | +0.370 |
DK | +0.367 |
ドラゴン | +0.334 |
ingen | +0.330 |
Neg logit contributions | |
manif | -0.549 |
incent | -0.524 |
ngth | -0.509 |
regulators | -0.485 |
equations | -0.478 |
Token | a |
Token ID | 64 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Interstitial | +0.412 |
ovember | +0.372 |
DK | +0.370 |
ドラゴン | +0.338 |
ingen | +0.332 |
Neg logit contributions | |
manif | -0.522 |
incent | -0.495 |
ngth | -0.483 |
regulators | -0.457 |
equations | -0.450 |
Token | , |
Token ID | 837 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
manif | +0.267 |
incent | +0.252 |
ngth | +0.244 |
regulators | +0.234 |
equations | +0.230 |
Neg logit contributions | |
Interstitial | -0.257 |
ovember | -0.238 |
DK | -0.233 |
ドラゴン | -0.215 |
ingen | -0.214 |
Token | T |
Token ID | 309 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
manif | +0.030 |
incent | +0.029 |
ngth | +0.028 |
regulators | +0.026 |
equations | +0.026 |
Neg logit contributions | |
Interstitial | -0.034 |
ovember | -0.031 |
DK | -0.031 |
ドラゴン | -0.029 |
ingen | -0.029 |
Token | > |
Token ID | 1875 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Interstitial | +0.096 |
ovember | +0.083 |
DK | +0.080 |
ドラゴン | +0.069 |
ingen | +0.068 |
Neg logit contributions | |
manif | -0.234 |
incent | -0.225 |
ngth | -0.219 |
regulators | -0.213 |
equations | -0.210 |
Token | { |
Token ID | 1391 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
Interstitial | +0.778 |
ovember | +0.695 |
DK | +0.685 |
ドラゴン | +0.617 |
ingen | +0.610 |
Neg logit contributions | |
manif | -1.202 |
incent | -1.146 |
ngth | -1.115 |
regulators | -1.072 |
equations | -1.058 |
Token | type |
Token ID | 2099 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Interstitial | +0.068 |
ovember | +0.061 |
DK | +0.061 |
ドラゴン | +0.056 |
ingen | +0.055 |
Neg logit contributions | |
manif | -0.080 |
incent | -0.076 |
ngth | -0.073 |
regulators | -0.071 |
equations | -0.070 |
Token | Target |
Token ID | 12744 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Interstitial | +0.333 |
ovember | +0.296 |
DK | +0.292 |
ドラゴン | +0.265 |
ingen | +0.262 |
Neg logit contributions | |
manif | -0.503 |
incent | -0.484 |
ngth | -0.468 |
regulators | -0.448 |
equations | -0.441 |
Token | = |
Token ID | 796 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
Interstitial | +0.191 |
ovember | +0.170 |
DK | +0.161 |
ドラゴン | +0.140 |
ingen | +0.140 |
Neg logit contributions | |
manif | -0.431 |
incent | -0.413 |
ngth | -0.403 |
regulators | -0.391 |
equations | -0.387 |
Token | & |
Token ID | 1222 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Interstitial | +0.232 |
ovember | +0.210 |
DK | +0.208 |
ドラゴン | +0.190 |
ingen | +0.189 |
Neg logit contributions | |
manif | -0.278 |
incent | -0.267 |
ngth | -0.257 |
regulators | -0.244 |
undermin | -0.242 |
Token |
|
Token ID | 198 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Interstitial | +0.054 |
ovember | +0.049 |
DK | +0.048 |
ドラゴン | +0.044 |
ingen | +0.044 |
Neg logit contributions | |
manif | -0.064 |
incent | -0.060 |
ngth | -0.058 |
regulators | -0.056 |
equations | -0.056 |
Token | Sun |
Token ID | 16012 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
Interstitial | +0.092 |
ovember | +0.084 |
DK | +0.082 |
ドラゴン | +0.075 |
ingen | +0.074 |
Neg logit contributions | |
manif | -0.121 |
incent | -0.115 |
ngth | -0.112 |
regulators | -0.106 |
equations | -0.105 |
Token | flower |
Token ID | 25547 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
Interstitial | +0.337 |
ovember | +0.312 |
DK | +0.312 |
ドラゴン | +0.292 |
ingen | +0.289 |
Neg logit contributions | |
manif | -0.234 |
incent | -0.219 |
ngth | -0.210 |
regulators | -0.194 |
undermin | -0.191 |
Token | Seed |
Token ID | 23262 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
Interstitial | +0.265 |
ovember | +0.238 |
DK | +0.237 |
ドラゴン | +0.215 |
ingen | +0.213 |
Neg logit contributions | |
manif | -0.355 |
incent | -0.339 |
ngth | -0.330 |
regulators | -0.312 |
undermin | -0.308 |
Token | Fl |
Token ID | 1610 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
manif | +0.437 |
incent | +0.416 |
ngth | +0.405 |
regulators | +0.383 |
undermin | +0.377 |
Neg logit contributions | |
Interstitial | -0.351 |
ovember | -0.317 |
DK | -0.315 |
ドラゴン | -0.289 |
ingen | -0.284 |
Token | our |
Token ID | 454 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Interstitial | +0.004 |
ovember | +0.004 |
DK | +0.004 |
ドラゴン | +0.003 |
ingen | +0.003 |
Neg logit contributions | |
manif | -0.009 |
incent | -0.009 |
ngth | -0.008 |
regulators | -0.008 |
equations | -0.008 |
Token | — |
Token ID | 960 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Interstitial | +0.951 |
ovember | +0.864 |
DK | +0.861 |
ドラゴン | +0.791 |
ingen | +0.783 |
Neg logit contributions | |
manif | -1.036 |
incent | -0.983 |
ngth | -0.956 |
regulators | -0.897 |
undermin | -0.885 |
Token | For |
Token ID | 1890 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Interstitial | +0.174 |
ovember | +0.158 |
DK | +0.157 |
ドラゴン | +0.144 |
ingen | +0.143 |
Neg logit contributions | |
manif | -0.199 |
incent | -0.189 |
ngth | -0.183 |
regulators | -0.173 |
undermin | -0.170 |
Token | those |
Token ID | 883 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
manif | +0.146 |
incent | +0.137 |
ngth | +0.133 |
regulators | +0.125 |
ratios | +0.123 |
Neg logit contributions | |
Interstitial | -0.165 |
ovember | -0.151 |
DK | -0.150 |
ドラゴン | -0.139 |
ingen | -0.138 |
Token | allergic |
Token ID | 31856 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
Interstitial | +0.335 |
ovember | +0.306 |
DK | +0.305 |
ドラゴン | +0.283 |
lan | +0.280 |
Neg logit contributions | |
manif | -0.301 |
incent | -0.284 |
ngth | -0.274 |
regulators | -0.257 |
equations | -0.253 |
Token | to |
Token ID | 284 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
Interstitial | +0.495 |
DK | +0.449 |
ovember | +0.448 |
ドラゴン | +0.411 |
ingen | +0.406 |
Neg logit contributions | |
manif | -0.554 |
incent | -0.528 |
ngth | -0.512 |
regulators | -0.480 |
undermin | -0.475 |
Token | freely |
Token ID | 12748 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
manif | +0.043 |
incent | +0.040 |
ngth | +0.039 |
regulators | +0.037 |
equations | +0.036 |
Neg logit contributions | |
Interstitial | -0.043 |
ovember | -0.040 |
DK | -0.039 |
ドラゴン | -0.036 |
ingen | -0.036 |
Token | during |
Token ID | 1141 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
Interstitial | +0.104 |
ovember | +0.094 |
DK | +0.094 |
ドラゴン | +0.086 |
ingen | +0.085 |
Neg logit contributions | |
manif | -0.114 |
incent | -0.108 |
ngth | -0.104 |
regulators | -0.099 |
equations | -0.097 |
Token | these |
Token ID | 777 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Interstitial | +0.253 |
ovember | +0.230 |
DK | +0.229 |
ドラゴン | +0.212 |
ingen | +0.211 |
Neg logit contributions | |
manif | -0.250 |
incent | -0.236 |
ngth | -0.227 |
regulators | -0.215 |
equations | -0.211 |
Token | events |
Token ID | 2995 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Interstitial | +0.265 |
ovember | +0.245 |
DK | +0.245 |
ドラゴン | +0.228 |
ingen | +0.226 |
Neg logit contributions | |
manif | -0.198 |
incent | -0.186 |
ngth | -0.177 |
regulators | -0.166 |
undermin | -0.163 |
Token | to |
Token ID | 284 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
Interstitial | +0.173 |
ovember | +0.156 |
DK | +0.155 |
ドラゴン | +0.142 |
ingen | +0.140 |
Neg logit contributions | |
manif | -0.211 |
incent | -0.201 |
ngth | -0.194 |
regulators | -0.185 |
equations | -0.182 |
Token | prep |
Token ID | 3143 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Interstitial | +0.088 |
ovember | +0.081 |
DK | +0.080 |
ドラゴン | +0.075 |
ingen | +0.074 |
Neg logit contributions | |
manif | -0.074 |
incent | -0.070 |
ngth | -0.066 |
regulators | -0.063 |
undermin | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
Interstitial | +1.048 |
ovember | +0.956 |
DK | +0.954 |
ドラゴン | +0.888 |
ingen | +0.880 |
Neg logit contributions | |
manif | -0.931 |
incent | -0.877 |
ngth | -0.847 |
regulators | -0.797 |
undermin | -0.782 |
Token | party |
Token ID | 2151 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
Interstitial | +0.125 |
ovember | +0.115 |
DK | +0.114 |
ドラゴン | +0.107 |
ingen | +0.106 |
Neg logit contributions | |
manif | -0.098 |
incent | -0.092 |
ngth | -0.089 |
regulators | -0.083 |
undermin | -0.081 |
Token | � |
Token ID | 447 |
Feature activation | -8.26e-02 |
Pos logit contributions | |
manif | +0.041 |
incent | +0.039 |
ngth | +0.038 |
regulators | +0.036 |
equations | +0.035 |
Neg logit contributions | |
Interstitial | -0.043 |
ovember | -0.040 |
DK | -0.039 |
ドラゴン | -0.037 |
ingen | -0.036 |
Token | � |
Token ID | 247 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
Interstitial | +0.068 |
ovember | +0.062 |
DK | +0.062 |
ドラゴン | +0.057 |
ingen | +0.056 |
Neg logit contributions | |
manif | -0.072 |
incent | -0.068 |
ngth | -0.066 |
regulators | -0.063 |
equations | -0.062 |
Token | s |
Token ID | 82 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
Interstitial | +0.062 |
ovember | +0.057 |
DK | +0.056 |
ドラゴン | +0.053 |
ingen | +0.052 |
Neg logit contributions | |
manif | -0.055 |
incent | -0.052 |
ngth | -0.050 |
regulators | -0.047 |
equations | -0.046 |
Token | ard |
Token ID | 446 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Interstitial | +0.087 |
ovember | +0.076 |
DK | +0.075 |
ドラゴン | +0.068 |
ingen | +0.065 |
Neg logit contributions | |
manif | -0.155 |
incent | -0.147 |
ngth | -0.145 |
regulators | -0.138 |
equations | -0.136 |
Token | has |
Token ID | 468 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
Interstitial | +0.212 |
ovember | +0.192 |
DK | +0.191 |
ドラゴン | +0.176 |
ingen | +0.174 |
Neg logit contributions | |
manif | -0.228 |
incent | -0.217 |
ngth | -0.209 |
regulators | -0.198 |
equations | -0.195 |
Token | supported |
Token ID | 4855 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
manif | +0.100 |
incent | +0.094 |
ngth | +0.089 |
regulators | +0.086 |
equations | +0.085 |
Neg logit contributions | |
Interstitial | -0.105 |
DK | -0.095 |
ovember | -0.095 |
ドラゴン | -0.088 |
ingen | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
manif | +0.117 |
incent | +0.110 |
ngth | +0.105 |
regulators | +0.099 |
undermin | +0.097 |
Neg logit contributions | |
Interstitial | -0.150 |
DK | -0.137 |
ovember | -0.137 |
ドラゴン | -0.128 |
ingen | -0.126 |
Token | Industrial |
Token ID | 19034 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
manif | +0.107 |
incent | +0.100 |
ngth | +0.095 |
regulators | +0.091 |
equations | +0.088 |
Neg logit contributions | |
Interstitial | -0.135 |
DK | -0.123 |
ovember | -0.123 |
ドラゴン | -0.115 |
ingen | -0.114 |
Token | Hemp |
Token ID | 50060 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
manif | +0.157 |
incent | +0.148 |
ngth | +0.142 |
regulators | +0.133 |
equations | +0.130 |
Neg logit contributions | |
Interstitial | -0.191 |
ovember | -0.175 |
DK | -0.174 |
ドラゴン | -0.162 |
ingen | -0.161 |
Token | Farming |
Token ID | 39831 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
manif | +1.223 |
incent | +1.161 |
ngth | +1.117 |
regulators | +1.069 |
equations | +1.043 |
Neg logit contributions | |
Interstitial | -1.206 |
ovember | -1.086 |
DK | -1.085 |
ドラゴン | -1.006 |
ingen | -0.991 |
Token | Act |
Token ID | 2191 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
manif | +0.880 |
incent | +0.834 |
ngth | +0.786 |
regulators | +0.751 |
equations | +0.733 |
Neg logit contributions | |
Interstitial | -1.126 |
ovember | -1.036 |
DK | -1.032 |
ドラゴン | -0.964 |
ingen | -0.951 |
Token | that |
Token ID | 326 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
manif | +0.267 |
incent | +0.254 |
ngth | +0.247 |
regulators | +0.232 |
undermin | +0.230 |
Neg logit contributions | |
Interstitial | -0.239 |
ovember | -0.217 |
DK | -0.216 |
ドラゴン | -0.198 |
ingen | -0.196 |
Token | would |
Token ID | 561 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
manif | +0.022 |
incent | +0.021 |
ngth | +0.020 |
regulators | +0.019 |
undermin | +0.019 |
Neg logit contributions | |
Interstitial | -0.024 |
ovember | -0.022 |
DK | -0.022 |
ドラゴン | -0.020 |
ingen | -0.020 |
Token | allow |
Token ID | 1249 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
manif | +0.133 |
incent | +0.123 |
ngth | +0.119 |
regulators | +0.108 |
undermin | +0.107 |
Neg logit contributions | |
Interstitial | -0.208 |
ovember | -0.193 |
DK | -0.193 |
ドラゴン | -0.181 |
ingen | -0.179 |
Token | Guy |
Token ID | 13145 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Interstitial | +0.004 |
ovember | +0.004 |
DK | +0.004 |
ドラゴン | +0.003 |
ingen | +0.003 |
Neg logit contributions | |
manif | -0.005 |
incent | -0.004 |
ngth | -0.004 |
regulators | -0.004 |
undermin | -0.004 |
Token | - |
Token ID | 12 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
Interstitial | +0.354 |
ovember | +0.322 |
DK | +0.322 |
ドラゴン | +0.297 |
ingen | +0.293 |
Neg logit contributions | |
manif | -0.379 |
incent | -0.359 |
ngth | -0.348 |
regulators | -0.328 |
equations | -0.323 |
Token | E |
Token ID | 36 |
Feature activation | -8.40e-02 |
Pos logit contributions | |
manif | +0.004 |
incent | +0.004 |
ngth | +0.004 |
regulators | +0.004 |
equations | +0.004 |
Neg logit contributions | |
Interstitial | -0.003 |
ovember | -0.003 |
DK | -0.003 |
ドラゴン | -0.002 |
ingen | -0.002 |
Token | ps |
Token ID | 862 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Interstitial | +0.057 |
ovember | +0.051 |
DK | +0.050 |
ドラゴン | +0.046 |
ingen | +0.045 |
Neg logit contributions | |
manif | -0.086 |
incent | -0.082 |
ngth | -0.080 |
regulators | -0.076 |
undermin | -0.075 |
Token | ch |
Token ID | 354 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Interstitial | +0.138 |
ovember | +0.125 |
DK | +0.125 |
ドラゴン | +0.116 |
ingen | +0.113 |
Neg logit contributions | |
manif | -0.143 |
incent | -0.135 |
ngth | -0.131 |
regulators | -0.123 |
undermin | -0.121 |
Token | tein |
Token ID | 22006 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
manif | +0.429 |
incent | +0.398 |
ngth | +0.390 |
regulators | +0.359 |
equations | +0.352 |
Neg logit contributions | |
Interstitial | -0.602 |
ovember | -0.558 |
DK | -0.557 |
ドラゴン | -0.526 |
ement | -0.511 |
Token | Pt |
Token ID | 34352 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
manif | +1.013 |
incent | +0.966 |
ngth | +0.939 |
regulators | +0.893 |
equations | +0.881 |
Neg logit contributions | |
Interstitial | -0.700 |
DK | -0.621 |
ovember | -0.621 |
ドラゴン | -0.568 |
ingen | -0.557 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
manif | +0.052 |
incent | +0.050 |
ngth | +0.048 |
regulators | +0.046 |
ratios | +0.045 |
Neg logit contributions | |
Interstitial | -0.041 |
DK | -0.036 |
ovember | -0.036 |
ドラゴン | -0.034 |
ingen | -0.033 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
Interstitial | +0.023 |
ovember | +0.021 |
DK | +0.021 |
ドラゴン | +0.019 |
ingen | +0.019 |
Neg logit contributions | |
manif | -0.023 |
incent | -0.022 |
ngth | -0.021 |
regulators | -0.020 |
undermin | -0.020 |
Token | 01 |
Token ID | 486 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Interstitial | +0.065 |
ovember | +0.061 |
DK | +0.060 |
ドラゴン | +0.055 |
ingen | +0.054 |
Neg logit contributions | |
manif | -0.068 |
incent | -0.064 |
ngth | -0.061 |
regulators | -0.059 |
equations | -0.059 |
Token | 10 |
Token ID | 940 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
Interstitial | +0.233 |
ovember | +0.208 |
DK | +0.206 |
ドラゴン | +0.188 |
ingen | +0.184 |
Neg logit contributions | |
manif | -0.371 |
incent | -0.354 |
ngth | -0.344 |
regulators | -0.330 |
equations | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
manif | +0.122 |
incent | +0.116 |
ngth | +0.113 |
regulators | +0.107 |
undermin | +0.105 |
Neg logit contributions | |
Interstitial | -0.098 |
ovember | -0.088 |
DK | -0.088 |
ドラゴン | -0.080 |
ingen | -0.079 |
Token | � |
Token ID | 447 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
manif | +0.007 |
incent | +0.007 |
ngth | +0.007 |
regulators | +0.006 |
undermin | +0.006 |
Neg logit contributions | |
Interstitial | -0.008 |
ovember | -0.007 |
DK | -0.007 |
ドラゴン | -0.007 |
ingen | -0.007 |
Token | � |
Token ID | 251 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
manif | +0.017 |
incent | +0.016 |
ngth | +0.015 |
regulators | +0.014 |
undermin | +0.014 |
Neg logit contributions | |
Interstitial | -0.015 |
ovember | -0.014 |
DK | -0.014 |
ドラゴン | -0.013 |
ingen | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
manif | +0.146 |
incent | +0.137 |
ngth | +0.133 |
regulators | +0.124 |
undermin | +0.122 |
Neg logit contributions | |
Interstitial | -0.164 |
ovember | -0.151 |
DK | -0.150 |
ドラゴン | -0.139 |
ingen | -0.138 |
Token | Daily |
Token ID | 6714 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
manif | +0.009 |
incent | +0.009 |
ngth | +0.009 |
regulators | +0.008 |
undermin | +0.008 |
Neg logit contributions | |
Interstitial | -0.010 |
ovember | -0.009 |
DK | -0.009 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | Beast |
Token ID | 10984 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Interstitial | +0.046 |
ovember | +0.042 |
DK | +0.041 |
ingen | +0.038 |
ドラゴン | +0.038 |
Neg logit contributions | |
manif | -0.050 |
incent | -0.047 |
ngth | -0.045 |
regulators | -0.043 |
equations | -0.043 |
Token | � |
Token ID | 447 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
manif | +0.883 |
incent | +0.830 |
ngth | +0.803 |
regulators | +0.766 |
equations | +0.753 |
Neg logit contributions | |
Interstitial | -0.823 |
ovember | -0.747 |
DK | -0.740 |
ドラゴン | -0.680 |
ingen | -0.673 |
Token | � |
Token ID | 247 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
Interstitial | +0.033 |
ovember | +0.030 |
DK | +0.030 |
ドラゴン | +0.027 |
ingen | +0.027 |
Neg logit contributions | |
manif | -0.036 |
incent | -0.034 |
ngth | -0.033 |
regulators | -0.031 |
equations | -0.031 |
Token | s |
Token ID | 82 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
manif | +0.008 |
incent | +0.007 |
ngth | +0.007 |
regulators | +0.007 |
equations | +0.007 |
Neg logit contributions | |
Interstitial | -0.009 |
ovember | -0.008 |
DK | -0.008 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
manif | +0.098 |
incent | +0.094 |
ngth | +0.091 |
regulators | +0.087 |
equations | +0.086 |
Neg logit contributions | |
Interstitial | -0.065 |
ovember | -0.058 |
DK | -0.058 |
ドラゴン | -0.052 |
ingen | -0.051 |
Token | Mak |
Token ID | 15841 |
Feature activation | +9.98e-02 |
Pos logit contributions | |
manif | +0.351 |
incent | +0.334 |
ngth | +0.324 |
regulators | +0.309 |
ratios | +0.303 |
Neg logit contributions | |
Interstitial | -0.270 |
ovember | -0.237 |
DK | -0.237 |
ドラゴン | -0.218 |
ingen | -0.211 |
Token | oots |
Token ID | 13880 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
manif | +0.561 |
incent | +0.540 |
ngth | +0.530 |
regulators | +0.508 |
equations | +0.503 |
Neg logit contributions | |
Interstitial | -0.230 |
ovember | -0.192 |
DK | -0.192 |
ドラゴン | -0.169 |
ingen | -0.159 |
Token | without |
Token ID | 1231 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Interstitial | +0.158 |
ovember | +0.144 |
DK | +0.143 |
ドラゴン | +0.132 |
ingen | +0.130 |
Neg logit contributions | |
manif | -0.166 |
incent | -0.158 |
ngth | -0.153 |
regulators | -0.144 |
undermin | -0.142 |
Token | spending |
Token ID | 4581 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Interstitial | +0.162 |
DK | +0.149 |
ovember | +0.149 |
ドラゴン | +0.138 |
lan | +0.138 |
Neg logit contributions | |
manif | -0.130 |
incent | -0.122 |
ngth | -0.119 |
regulators | -0.109 |
undermin | -0.109 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
manif | +0.368 |
incent | +0.347 |
ngth | +0.333 |
regulators | +0.312 |
equations | +0.306 |
Neg logit contributions | |
Interstitial | -0.453 |
ovember | -0.416 |
DK | -0.414 |
ドラゴン | -0.386 |
ingen | -0.384 |
Token | DE |
Token ID | 5550 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
manif | +0.133 |
incent | +0.125 |
ngth | +0.120 |
regulators | +0.113 |
equations | +0.111 |
Neg logit contributions | |
Interstitial | -0.160 |
ovember | -0.147 |
DK | -0.146 |
ドラゴン | -0.136 |
ingen | -0.135 |
Token | FAULT |
Token ID | 38865 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
manif | +0.231 |
incent | +0.218 |
ngth | +0.212 |
regulators | +0.198 |
undermin | +0.196 |
Neg logit contributions | |
Interstitial | -0.239 |
DK | -0.219 |
ovember | -0.218 |
ドラゴン | -0.201 |
lan | -0.199 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
manif | +0.994 |
incent | +0.944 |
ngth | +0.910 |
regulators | +0.856 |
equations | +0.839 |
Neg logit contributions | |
Interstitial | -1.068 |
ovember | -0.971 |
DK | -0.966 |
ドラゴン | -0.897 |
ingen | -0.890 |
Token | second |
Token ID | 1218 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
manif | +0.045 |
incent | +0.043 |
ngth | +0.041 |
regulators | +0.039 |
undermin | +0.038 |
Neg logit contributions | |
Interstitial | -0.050 |
ovember | -0.045 |
DK | -0.045 |
ドラゴン | -0.042 |
ingen | -0.042 |
Token | delay |
Token ID | 5711 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
manif | +0.286 |
incent | +0.271 |
ngth | +0.262 |
regulators | +0.248 |
equations | +0.243 |
Neg logit contributions | |
Interstitial | -0.274 |
ovember | -0.250 |
DK | -0.249 |
ドラゴン | -0.231 |
ingen | -0.227 |
Token | before |
Token ID | 878 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
manif | +0.330 |
incent | +0.315 |
ngth | +0.304 |
regulators | +0.289 |
equations | +0.283 |
Neg logit contributions | |
Interstitial | -0.284 |
ovember | -0.258 |
DK | -0.256 |
ドラゴン | -0.236 |
ingen | -0.233 |
Token | reb |
Token ID | 3405 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
manif | +0.008 |
incent | +0.008 |
ngth | +0.007 |
regulators | +0.007 |
undermin | +0.007 |
Neg logit contributions | |
Interstitial | -0.010 |
ovember | -0.009 |
DK | -0.009 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | Life |
Token ID | 5155 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
Interstitial | +0.027 |
ovember | +0.024 |
DK | +0.024 |
ドラゴン | +0.021 |
ingen | +0.021 |
Neg logit contributions | |
manif | -0.045 |
incent | -0.043 |
ngth | -0.042 |
regulators | -0.040 |
equations | -0.040 |
Token | / |
Token ID | 1220 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
manif | +0.008 |
incent | +0.007 |
ngth | +0.007 |
regulators | +0.007 |
equations | +0.007 |
Neg logit contributions | |
Interstitial | -0.006 |
DK | -0.005 |
ovember | -0.005 |
ドラゴン | -0.005 |
ingen | -0.005 |
Token | P |
Token ID | 350 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
manif | +0.318 |
incent | +0.303 |
ngth | +0.295 |
regulators | +0.280 |
equations | +0.276 |
Neg logit contributions | |
Interstitial | -0.245 |
ovember | -0.220 |
DK | -0.219 |
ドラゴン | -0.200 |
ingen | -0.198 |
Token | CC |
Token ID | 4093 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
manif | +0.367 |
incent | +0.351 |
ngth | +0.341 |
regulators | +0.322 |
undermin | +0.316 |
Neg logit contributions | |
Interstitial | -0.302 |
DK | -0.271 |
ovember | -0.271 |
ドラゴン | -0.249 |
ingen | -0.245 |
Token | Natural |
Token ID | 12068 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
manif | +0.113 |
incent | +0.108 |
ngth | +0.104 |
regulators | +0.100 |
equations | +0.098 |
Neg logit contributions | |
Interstitial | -0.092 |
ovember | -0.082 |
DK | -0.082 |
ドラゴン | -0.075 |
ingen | -0.074 |
Token | Markets |
Token ID | 30251 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
manif | +0.575 |
incent | +0.547 |
ngth | +0.531 |
regulators | +0.503 |
undermin | +0.496 |
Neg logit contributions | |
Interstitial | -0.464 |
ovember | -0.417 |
DK | -0.417 |
ドラゴン | -0.380 |
ingen | -0.376 |
Token | will |
Token ID | 481 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
manif | +0.926 |
incent | +0.887 |
ngth | +0.850 |
regulators | +0.823 |
equations | +0.806 |
Neg logit contributions | |
Interstitial | -0.743 |
ovember | -0.664 |
DK | -0.661 |
ドラゴン | -0.608 |
ingen | -0.595 |
Token | open |
Token ID | 1280 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
manif | +0.132 |
incent | +0.125 |
ngth | +0.119 |
regulators | +0.113 |
equations | +0.110 |
Neg logit contributions | |
Interstitial | -0.153 |
DK | -0.140 |
ovember | -0.140 |
ドラゴン | -0.130 |
ingen | -0.129 |
Token | new |
Token ID | 649 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
manif | +0.063 |
incent | +0.060 |
ngth | +0.058 |
regulators | +0.055 |
equations | +0.054 |
Neg logit contributions | |
Interstitial | -0.060 |
DK | -0.054 |
ovember | -0.054 |
ドラゴン | -0.050 |
ingen | -0.049 |
Token | store |
Token ID | 3650 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Interstitial | +0.129 |
DK | +0.119 |
ovember | +0.118 |
ドラゴン | +0.110 |
ingen | +0.108 |
Neg logit contributions | |
manif | -0.111 |
incent | -0.105 |
ngth | -0.100 |
regulators | -0.095 |
equations | -0.093 |
Token | at |
Token ID | 379 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
Interstitial | +0.268 |
DK | +0.242 |
ovember | +0.242 |
ドラゴン | +0.222 |
ingen | +0.220 |
Neg logit contributions | |
manif | -0.306 |
incent | -0.292 |
ngth | -0.282 |
regulators | -0.267 |
equations | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
manif | +0.439 |
incent | +0.415 |
ngth | +0.401 |
regulators | +0.383 |
equations | +0.377 |
Neg logit contributions | |
Interstitial | -0.384 |
ovember | -0.346 |
DK | -0.343 |
ドラゴン | -0.314 |
ingen | -0.310 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
manif | +0.133 |
incent | +0.126 |
ngth | +0.123 |
regulators | +0.117 |
equations | +0.116 |
Neg logit contributions | |
Interstitial | -0.109 |
ovember | -0.099 |
DK | -0.097 |
ドラゴン | -0.089 |
ingen | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
manif | +0.109 |
incent | +0.101 |
ngth | +0.099 |
regulators | +0.096 |
equations | +0.095 |
Neg logit contributions | |
Interstitial | -0.094 |
ovember | -0.086 |
DK | -0.083 |
ドラゴン | -0.077 |
ingen | -0.076 |
Token | Although |
Token ID | 7003 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
manif | +0.053 |
incent | +0.050 |
ngth | +0.049 |
regulators | +0.046 |
equations | +0.045 |
Neg logit contributions | |
Interstitial | -0.039 |
ovember | -0.036 |
DK | -0.035 |
ドラゴン | -0.032 |
ingen | -0.032 |
Token | some |
Token ID | 617 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
manif | +0.229 |
incent | +0.217 |
ngth | +0.210 |
regulators | +0.200 |
equations | +0.197 |
Neg logit contributions | |
Interstitial | -0.200 |
ovember | -0.181 |
DK | -0.180 |
ドラゴン | -0.165 |
ingen | -0.163 |
Token | believe |
Token ID | 1975 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
manif | +0.278 |
incent | +0.261 |
ngth | +0.252 |
regulators | +0.235 |
undermin | +0.231 |
Neg logit contributions | |
Interstitial | -0.348 |
ovember | -0.320 |
DK | -0.320 |
ドラゴン | -0.298 |
ingen | -0.295 |
Token | that |
Token ID | 326 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
manif | +0.450 |
incent | +0.424 |
ngth | +0.411 |
regulators | +0.389 |
equations | +0.383 |
Neg logit contributions | |
Interstitial | -0.454 |
ovember | -0.413 |
DK | -0.411 |
ドラゴン | -0.380 |
ingen | -0.375 |
Token | the |
Token ID | 262 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
Interstitial | +0.033 |
ovember | +0.030 |
DK | +0.030 |
ドラゴン | +0.027 |
ingen | +0.027 |
Neg logit contributions | |
manif | -0.035 |
incent | -0.033 |
ngth | -0.032 |
regulators | -0.030 |
equations | -0.030 |
Token | Syrian |
Token ID | 6318 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Interstitial | +0.036 |
ovember | +0.033 |
DK | +0.033 |
ドラゴン | +0.030 |
ingen | +0.030 |
Neg logit contributions | |
manif | -0.035 |
incent | -0.033 |
ngth | -0.032 |
regulators | -0.030 |
undermin | -0.030 |
Token | government |
Token ID | 1230 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
manif | +0.211 |
incent | +0.198 |
ngth | +0.190 |
regulators | +0.176 |
undermin | +0.173 |
Neg logit contributions | |
Interstitial | -0.298 |
ovember | -0.276 |
DK | -0.275 |
ドラゴン | -0.257 |
ingen | -0.255 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Interstitial | +0.231 |
ovember | +0.210 |
DK | +0.209 |
ドラゴン | +0.193 |
ingen | +0.191 |
Neg logit contributions | |
manif | -0.236 |
incent | -0.224 |
ngth | -0.217 |
regulators | -0.204 |
undermin | -0.201 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
manif | +0.038 |
incent | +0.035 |
ngth | +0.034 |
regulators | +0.033 |
equations | +0.033 |
Neg logit contributions | |
Interstitial | -0.038 |
ovember | -0.035 |
DK | -0.034 |
ドラゴン | -0.032 |
ingen | -0.031 |
Token | discriminate |
Token ID | 28433 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
Interstitial | +0.099 |
ovember | +0.090 |
DK | +0.090 |
ドラゴン | +0.084 |
ingen | +0.082 |
Neg logit contributions | |
manif | -0.090 |
incent | -0.085 |
ngth | -0.081 |
regulators | -0.077 |
equations | -0.076 |
Token | between |
Token ID | 1022 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Interstitial | +0.397 |
ovember | +0.364 |
DK | +0.363 |
ドラゴン | +0.336 |
ingen | +0.333 |
Neg logit contributions | |
manif | -0.357 |
incent | -0.337 |
ngth | -0.323 |
regulators | -0.305 |
equations | -0.300 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Interstitial | +0.173 |
ovember | +0.160 |
DK | +0.159 |
ドラゴン | +0.148 |
ingen | +0.147 |
Neg logit contributions | |
manif | -0.137 |
incent | -0.129 |
ngth | -0.123 |
regulators | -0.116 |
equations | -0.114 |
Token | distinct |
Token ID | 7310 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Interstitial | +0.140 |
ovember | +0.129 |
DK | +0.129 |
ドラゴン | +0.120 |
ingen | +0.119 |
Neg logit contributions | |
manif | -0.102 |
incent | -0.096 |
ngth | -0.092 |
regulators | -0.085 |
equations | -0.084 |
Token | spatial |
Token ID | 21739 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Interstitial | +0.575 |
ovember | +0.536 |
DK | +0.535 |
ドラゴン | +0.501 |
ingen | +0.498 |
Neg logit contributions | |
manif | -0.339 |
incent | -0.314 |
ngth | -0.299 |
regulators | -0.275 |
equations | -0.269 |
Token | navigation |
Token ID | 16408 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
manif | +0.178 |
incent | +0.164 |
ngth | +0.154 |
regulators | +0.143 |
equations | +0.140 |
Neg logit contributions | |
Interstitial | -0.329 |
ovember | -0.307 |
DK | -0.306 |
ドラゴン | -0.288 |
ingen | -0.286 |
Token | strategies |
Token ID | 10064 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
Interstitial | +0.188 |
ovember | +0.176 |
DK | +0.175 |
ドラゴン | +0.165 |
ingen | +0.164 |
Neg logit contributions | |
manif | -0.093 |
incent | -0.086 |
ngth | -0.081 |
regulators | -0.074 |
equations | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
Interstitial | +0.060 |
ovember | +0.054 |
DK | +0.054 |
ドラゴン | +0.050 |
ingen | +0.049 |
Neg logit contributions | |
manif | -0.065 |
incent | -0.062 |
ngth | -0.060 |
regulators | -0.057 |
equations | -0.056 |
Token | depending |
Token ID | 6906 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
manif | +0.008 |
incent | +0.008 |
ngth | +0.007 |
regulators | +0.007 |
equations | +0.007 |
Neg logit contributions | |
Interstitial | -0.009 |
ovember | -0.009 |
DK | -0.008 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
Interstitial | +0.028 |
DK | +0.025 |
ovember | +0.025 |
ドラゴン | +0.023 |
ingen | +0.022 |
Neg logit contributions | |
manif | -0.037 |
incent | -0.036 |
ngth | -0.035 |
regulators | -0.033 |
undermin | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
manif | +0.207 |
incent | +0.197 |
ngth | +0.192 |
regulators | +0.183 |
undermin | +0.180 |
Neg logit contributions | |
Interstitial | -0.146 |
ovember | -0.131 |
DK | -0.131 |
ドラゴン | -0.118 |
ingen | -0.117 |
Token | moves |
Token ID | 6100 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Interstitial | +0.002 |
ovember | +0.002 |
DK | +0.002 |
ドラゴン | +0.002 |
ingen | +0.002 |
Neg logit contributions | |
manif | -0.002 |
incent | -0.002 |
ngth | -0.002 |
regulators | -0.002 |
equations | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
manif | +0.010 |
incent | +0.009 |
ngth | +0.009 |
regulators | +0.009 |
equations | +0.009 |
Neg logit contributions | |
Interstitial | -0.009 |
ovember | -0.008 |
DK | -0.008 |
ドラゴン | -0.007 |
ingen | -0.007 |
Token | space |
Token ID | 2272 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
manif | +0.041 |
incent | +0.039 |
ngth | +0.037 |
regulators | +0.035 |
equations | +0.035 |
Neg logit contributions | |
Interstitial | -0.042 |
ovember | -0.039 |
DK | -0.039 |
ドラゴン | -0.036 |
ingen | -0.035 |
Token | relative |
Token ID | 3585 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Interstitial | +0.148 |
ovember | +0.134 |
DK | +0.133 |
ドラゴン | +0.122 |
ingen | +0.120 |
Neg logit contributions | |
manif | -0.182 |
incent | -0.173 |
ngth | -0.169 |
regulators | -0.159 |
undermin | -0.157 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
manif | +0.058 |
incent | +0.054 |
ngth | +0.052 |
regulators | +0.050 |
equations | +0.049 |
Neg logit contributions | |
Interstitial | -0.055 |
ovember | -0.050 |
DK | -0.050 |
ドラゴン | -0.046 |
ingen | -0.045 |
Token | other |
Token ID | 584 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
manif | +0.104 |
incent | +0.098 |
ngth | +0.095 |
regulators | +0.089 |
undermin | +0.088 |
Neg logit contributions | |
Interstitial | -0.109 |
ovember | -0.100 |
DK | -0.100 |
ドラゴン | -0.092 |
ingen | -0.092 |
Token | galaxies |
Token ID | 27982 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
manif | +0.093 |
incent | +0.087 |
ngth | +0.083 |
regulators | +0.074 |
undermin | +0.074 |
Neg logit contributions | |
Interstitial | -0.177 |
ovember | -0.165 |
DK | -0.165 |
ドラゴン | -0.155 |
lan | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
manif | +0.149 |
incent | +0.141 |
ngth | +0.138 |
regulators | +0.130 |
equations | +0.128 |
Neg logit contributions | |
Interstitial | -0.119 |
ovember | -0.108 |
DK | -0.107 |
ドラゴン | -0.098 |
ingen | -0.096 |
Token | In |
Token ID | 554 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
manif | +0.050 |
incent | +0.048 |
ngth | +0.047 |
regulators | +0.044 |
equations | +0.044 |
Neg logit contributions | |
Interstitial | -0.041 |
ovember | -0.037 |
DK | -0.037 |
ドラゴン | -0.034 |
ingen | -0.033 |
Token | about |
Token ID | 546 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
manif | +0.024 |
incent | +0.023 |
ngth | +0.022 |
regulators | +0.021 |
equations | +0.021 |
Neg logit contributions | |
Interstitial | -0.026 |
ovember | -0.023 |
DK | -0.023 |
ドラゴン | -0.021 |
ingen | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
Interstitial | +0.136 |
ovember | +0.123 |
DK | +0.122 |
ドラゴン | +0.112 |
ingen | +0.110 |
Neg logit contributions | |
manif | -0.164 |
incent | -0.156 |
ngth | -0.151 |
regulators | -0.143 |
undermin | -0.141 |
Token | though |
Token ID | 996 |
Feature activation | -7.90e-02 |
Pos logit contributions | |
Interstitial | +0.018 |
ovember | +0.017 |
DK | +0.017 |
ドラゴン | +0.015 |
ingen | +0.015 |
Neg logit contributions | |
manif | -0.017 |
incent | -0.016 |
ngth | -0.015 |
regulators | -0.014 |
undermin | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
Interstitial | +0.068 |
ovember | +0.062 |
DK | +0.062 |
ドラゴン | +0.058 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.067 |
incent | -0.063 |
ngth | -0.061 |
regulators | -0.057 |
equations | -0.056 |
Token | � |
Token ID | 447 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
manif | +0.013 |
incent | +0.012 |
ngth | +0.012 |
regulators | +0.011 |
equations | +0.011 |
Neg logit contributions | |
Interstitial | -0.010 |
ovember | -0.009 |
DK | -0.009 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | � |
Token ID | 250 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
manif | +0.018 |
incent | +0.017 |
ngth | +0.016 |
regulators | +0.015 |
ratios | +0.015 |
Neg logit contributions | |
Interstitial | -0.018 |
DK | -0.016 |
ovember | -0.016 |
ドラゴン | -0.015 |
ingen | -0.015 |
Token | Instead |
Token ID | 13193 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
Interstitial | +0.008 |
ovember | +0.008 |
DK | +0.008 |
ドラゴン | +0.007 |
ingen | +0.007 |
Neg logit contributions | |
manif | -0.011 |
incent | -0.010 |
ngth | -0.010 |
regulators | -0.009 |
equations | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
manif | +0.402 |
incent | +0.381 |
ngth | +0.372 |
regulators | +0.349 |
undermin | +0.345 |
Neg logit contributions | |
Interstitial | -0.361 |
ovember | -0.328 |
DK | -0.327 |
ドラゴン | -0.300 |
ingen | -0.296 |
Token | saying |
Token ID | 2282 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
manif | +0.013 |
incent | +0.012 |
ngth | +0.011 |
regulators | +0.011 |
equations | +0.011 |
Neg logit contributions | |
Interstitial | -0.014 |
ovember | -0.013 |
DK | -0.013 |
ドラゴン | -0.012 |
ingen | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
manif | +0.069 |
incent | +0.066 |
ngth | +0.063 |
regulators | +0.060 |
equations | +0.059 |
Neg logit contributions | |
Interstitial | -0.065 |
ovember | -0.060 |
DK | -0.060 |
ドラゴン | -0.055 |
ingen | -0.054 |
Token | black |
Token ID | 2042 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Interstitial | +0.079 |
ovember | +0.072 |
DK | +0.072 |
ドラゴン | +0.066 |
ingen | +0.065 |
Neg logit contributions | |
manif | -0.086 |
incent | -0.081 |
ngth | -0.079 |
regulators | -0.074 |
undermin | -0.073 |
Token | or |
Token ID | 393 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
manif | +0.048 |
incent | +0.045 |
ngth | +0.044 |
regulators | +0.042 |
equations | +0.041 |
Neg logit contributions | |
Interstitial | -0.049 |
DK | -0.045 |
ovember | -0.045 |
ドラゴン | -0.041 |
ingen | -0.041 |
Token | could |
Token ID | 714 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
manif | +0.161 |
incent | +0.153 |
ngth | +0.147 |
regulators | +0.139 |
equations | +0.137 |
Neg logit contributions | |
Interstitial | -0.154 |
ovember | -0.140 |
DK | -0.139 |
ドラゴン | -0.129 |
ingen | -0.127 |
Token | help |
Token ID | 1037 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Interstitial | +0.101 |
ovember | +0.093 |
DK | +0.093 |
ドラゴン | +0.087 |
ingen | +0.086 |
Neg logit contributions | |
manif | -0.078 |
incent | -0.073 |
ngth | -0.070 |
regulators | -0.065 |
undermin | -0.064 |
Token | get |
Token ID | 651 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Interstitial | +0.189 |
ovember | +0.173 |
DK | +0.172 |
ドラゴン | +0.160 |
ingen | +0.158 |
Neg logit contributions | |
manif | -0.181 |
incent | -0.171 |
ngth | -0.165 |
regulators | -0.155 |
undermin | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
manif | +0.198 |
incent | +0.187 |
ngth | +0.181 |
regulators | +0.171 |
equations | +0.167 |
Neg logit contributions | |
Interstitial | -0.208 |
ovember | -0.191 |
DK | -0.189 |
ドラゴン | -0.175 |
ingen | -0.174 |
Token | the |
Token ID | 262 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
manif | +0.048 |
incent | +0.046 |
ngth | +0.044 |
regulators | +0.042 |
equations | +0.041 |
Neg logit contributions | |
Interstitial | -0.051 |
ovember | -0.047 |
DK | -0.046 |
ドラゴン | -0.043 |
ingen | -0.043 |
Token | root |
Token ID | 6808 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
manif | +0.073 |
incent | +0.069 |
ngth | +0.066 |
regulators | +0.062 |
equations | +0.061 |
Neg logit contributions | |
Interstitial | -0.085 |
ovember | -0.079 |
DK | -0.078 |
ドラゴン | -0.073 |
ingen | -0.072 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
manif | +0.434 |
incent | +0.410 |
ngth | +0.396 |
regulators | +0.373 |
equations | +0.368 |
Neg logit contributions | |
Interstitial | -0.460 |
ovember | -0.421 |
DK | -0.418 |
ドラゴン | -0.387 |
ingen | -0.384 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
manif | +0.137 |
incent | +0.130 |
ngth | +0.125 |
regulators | +0.117 |
undermin | +0.115 |
Neg logit contributions | |
Interstitial | -0.154 |
ovember | -0.142 |
DK | -0.141 |
ドラゴン | -0.131 |
ingen | -0.130 |
Token | problem |
Token ID | 1917 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
manif | +0.094 |
incent | +0.087 |
ngth | +0.083 |
regulators | +0.077 |
undermin | +0.075 |
Neg logit contributions | |
Interstitial | -0.158 |
ovember | -0.147 |
DK | -0.147 |
ドラゴン | -0.138 |
ingen | -0.137 |
Token | , |
Token ID | 11 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
manif | +0.213 |
incent | +0.201 |
ngth | +0.196 |
regulators | +0.185 |
equations | +0.183 |
Neg logit contributions | |
Interstitial | -0.186 |
ovember | -0.169 |
DK | -0.168 |
ドラゴン | -0.154 |
ingen | -0.153 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
manif | +0.126 |
incent | +0.119 |
ngth | +0.115 |
regulators | +0.108 |
undermin | +0.106 |
Neg logit contributions | |
Interstitial | -0.140 |
ovember | -0.128 |
DK | -0.128 |
ドラゴン | -0.119 |
ingen | -0.117 |
Token | dain |
Token ID | 27162 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Interstitial | +0.225 |
ovember | +0.195 |
DK | +0.192 |
ドラゴン | +0.172 |
ingen | +0.165 |
Neg logit contributions | |
manif | -0.474 |
incent | -0.452 |
ngth | -0.444 |
regulators | -0.425 |
equations | -0.420 |
Token | at |
Token ID | 379 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
manif | +0.455 |
incent | +0.431 |
ngth | +0.417 |
regulators | +0.396 |
equations | +0.389 |
Neg logit contributions | |
Interstitial | -0.411 |
ovember | -0.372 |
DK | -0.371 |
ドラゴン | -0.341 |
ingen | -0.338 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Interstitial | +0.243 |
ovember | +0.221 |
DK | +0.221 |
ドラゴン | +0.203 |
ingen | +0.201 |
Neg logit contributions | |
manif | -0.263 |
incent | -0.249 |
ngth | -0.241 |
regulators | -0.228 |
equations | -0.224 |
Token | market |
Token ID | 1910 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Interstitial | +0.160 |
ovember | +0.146 |
DK | +0.145 |
ドラゴン | +0.133 |
ingen | +0.132 |
Neg logit contributions | |
manif | -0.174 |
incent | -0.165 |
ngth | -0.159 |
regulators | -0.152 |
equations | -0.149 |
Token | one |
Token ID | 530 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
manif | +0.285 |
incent | +0.270 |
ngth | +0.261 |
regulators | +0.248 |
equations | +0.243 |
Neg logit contributions | |
Interstitial | -0.267 |
DK | -0.242 |
ovember | -0.241 |
ドラゴン | -0.222 |
ingen | -0.219 |
Token | morning |
Token ID | 3329 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Interstitial | +0.518 |
DK | +0.472 |
ovember | +0.470 |
ドラゴン | +0.433 |
ingen | +0.429 |
Neg logit contributions | |
manif | -0.531 |
incent | -0.503 |
ngth | -0.487 |
regulators | -0.459 |
undermin | -0.452 |
Token | , |
Token ID | 11 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Interstitial | +0.230 |
ovember | +0.208 |
DK | +0.208 |
ドラゴン | +0.190 |
ingen | +0.188 |
Neg logit contributions | |
manif | -0.266 |
incent | -0.252 |
ngth | -0.245 |
regulators | -0.232 |
undermin | -0.228 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Interstitial | +0.209 |
ovember | +0.191 |
DK | +0.191 |
ドラゴン | +0.177 |
ingen | +0.175 |
Neg logit contributions | |
manif | -0.197 |
incent | -0.186 |
ngth | -0.179 |
regulators | -0.168 |
undermin | -0.166 |
Token | this |
Token ID | 428 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
Interstitial | +0.151 |
DK | +0.137 |
ovember | +0.137 |
ドラゴン | +0.127 |
ingen | +0.125 |
Neg logit contributions | |
manif | -0.154 |
incent | -0.145 |
ngth | -0.140 |
regulators | -0.133 |
equations | -0.130 |
Token | time |
Token ID | 640 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Interstitial | +0.107 |
DK | +0.098 |
ovember | +0.098 |
ドラゴン | +0.090 |
ingen | +0.088 |
Neg logit contributions | |
manif | -0.110 |
incent | -0.104 |
ngth | -0.100 |
regulators | -0.095 |
equations | -0.093 |
Token | I |
Token ID | 314 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
Interstitial | +0.120 |
DK | +0.109 |
ovember | +0.108 |
ドラゴン | +0.099 |
ingen | +0.098 |
Neg logit contributions | |
manif | -0.135 |
incent | -0.128 |
ngth | -0.124 |
regulators | -0.118 |
equations | -0.116 |
Token | more |
Token ID | 517 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
manif | +0.013 |
incent | +0.013 |
ngth | +0.012 |
regulators | +0.011 |
undermin | +0.011 |
Neg logit contributions | |
Interstitial | -0.016 |
ovember | -0.015 |
DK | -0.015 |
ドラゴン | -0.014 |
ingen | -0.013 |
Token | easily |
Token ID | 3538 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Interstitial | +0.086 |
ovember | +0.079 |
DK | +0.079 |
ドラゴン | +0.073 |
ingen | +0.072 |
Neg logit contributions | |
manif | -0.077 |
incent | -0.073 |
ngth | -0.071 |
regulators | -0.066 |
undermin | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
manif | +0.012 |
incent | +0.011 |
ngth | +0.011 |
regulators | +0.010 |
equations | +0.010 |
Neg logit contributions | |
Interstitial | -0.010 |
DK | -0.009 |
ovember | -0.009 |
ドラゴン | -0.008 |
ingen | -0.008 |
Token | � |
Token ID | 447 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
Interstitial | +0.010 |
ovember | +0.009 |
DK | +0.009 |
ドラゴン | +0.009 |
ingen | +0.008 |
Neg logit contributions | |
manif | -0.008 |
incent | -0.007 |
ngth | -0.007 |
regulators | -0.007 |
undermin | -0.006 |
Token | � |
Token ID | 251 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
manif | +0.028 |
incent | +0.026 |
ngth | +0.026 |
regulators | +0.024 |
equations | +0.024 |
Neg logit contributions | |
Interstitial | -0.028 |
ovember | -0.026 |
DK | -0.026 |
ドラゴン | -0.024 |
ingen | -0.023 |
Token | says |
Token ID | 1139 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
manif | +0.060 |
incent | +0.056 |
ngth | +0.054 |
regulators | +0.051 |
undermin | +0.050 |
Neg logit contributions | |
Interstitial | -0.067 |
ovember | -0.061 |
DK | -0.061 |
ドラゴン | -0.057 |
ingen | -0.056 |
Token | Ian |
Token ID | 12930 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
Interstitial | +0.005 |
ovember | +0.004 |
DK | +0.004 |
ドラゴン | +0.004 |
ingen | +0.004 |
Neg logit contributions | |
manif | -0.008 |
incent | -0.007 |
ngth | -0.007 |
regulators | -0.007 |
equations | -0.007 |
Token | J |
Token ID | 449 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
Interstitial | +0.292 |
ovember | +0.261 |
DK | +0.257 |
ドラゴン | +0.236 |
ingen | +0.233 |
Neg logit contributions | |
manif | -0.381 |
incent | -0.362 |
ngth | -0.353 |
regulators | -0.336 |
equations | -0.331 |
Token | ough |
Token ID | 619 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Interstitial | +0.243 |
DK | +0.215 |
ovember | +0.214 |
ドラゴン | +0.199 |
ingen | +0.191 |
Neg logit contributions | |
manif | -0.298 |
incent | -0.284 |
ngth | -0.279 |
regulators | -0.262 |
equations | -0.258 |
Token | in |
Token ID | 259 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
manif | +0.301 |
incent | +0.288 |
ngth | +0.279 |
regulators | +0.261 |
equations | +0.260 |
Neg logit contributions | |
Interstitial | -0.264 |
ovember | -0.238 |
DK | -0.238 |
ドラゴン | -0.222 |
ingen | -0.212 |
Token | , |
Token ID | 11 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
manif | +0.004 |
incent | +0.004 |
ngth | +0.004 |
regulators | +0.003 |
equations | +0.003 |
Neg logit contributions | |
Interstitial | -0.003 |
ovember | -0.003 |
DK | -0.003 |
ドラゴン | -0.002 |
ingen | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Interstitial | +0.014 |
ovember | +0.012 |
DK | +0.012 |
ドラゴン | +0.011 |
ingen | +0.011 |
Neg logit contributions | |
manif | -0.015 |
incent | -0.014 |
ngth | -0.013 |
regulators | -0.013 |
undermin | -0.012 |
Token | view |
Token ID | 1570 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Interstitial | +0.012 |
DK | +0.011 |
ovember | +0.011 |
ドラゴン | +0.010 |
ingen | +0.010 |
Neg logit contributions | |
manif | -0.013 |
incent | -0.012 |
ngth | -0.011 |
regulators | -0.011 |
equations | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Interstitial | +0.091 |
ovember | +0.083 |
DK | +0.082 |
ドラゴン | +0.076 |
ingen | +0.075 |
Neg logit contributions | |
manif | -0.095 |
incent | -0.090 |
ngth | -0.087 |
regulators | -0.083 |
equations | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +6.95e-02 |
Pos logit contributions | |
Interstitial | +0.016 |
ovember | +0.014 |
DK | +0.014 |
ドラゴン | +0.013 |
ingen | +0.013 |
Neg logit contributions | |
manif | -0.015 |
incent | -0.014 |
ngth | -0.014 |
regulators | -0.013 |
undermin | -0.013 |
Token | public |
Token ID | 1171 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
manif | +0.054 |
incent | +0.051 |
ngth | +0.049 |
regulators | +0.046 |
equations | +0.045 |
Neg logit contributions | |
Interstitial | -0.065 |
ovember | -0.060 |
DK | -0.059 |
ドラゴン | -0.055 |
ingen | -0.055 |
Token | as |
Token ID | 355 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
manif | +0.319 |
incent | +0.302 |
ngth | +0.293 |
regulators | +0.280 |
equations | +0.275 |
Neg logit contributions | |
Interstitial | -0.259 |
ovember | -0.234 |
DK | -0.233 |
ドラゴン | -0.212 |
ingen | -0.210 |
Token | well |
Token ID | 880 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Interstitial | +0.012 |
ovember | +0.011 |
DK | +0.011 |
ドラゴン | +0.010 |
ingen | +0.010 |
Neg logit contributions | |
manif | -0.013 |
incent | -0.012 |
ngth | -0.012 |
regulators | -0.011 |
equations | -0.011 |
Token | as |
Token ID | 355 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
Interstitial | +0.127 |
ovember | +0.114 |
DK | +0.113 |
ドラゴン | +0.104 |
ingen | +0.102 |
Neg logit contributions | |
manif | -0.153 |
incent | -0.143 |
ngth | -0.139 |
regulators | -0.135 |
equations | -0.133 |
Token | the |
Token ID | 262 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
Interstitial | +0.127 |
ovember | +0.115 |
DK | +0.115 |
ドラゴン | +0.106 |
ingen | +0.105 |
Neg logit contributions | |
manif | -0.130 |
incent | -0.122 |
ngth | -0.119 |
regulators | -0.113 |
equations | -0.110 |
Token | scientific |
Token ID | 5654 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
manif | +0.023 |
incent | +0.021 |
ngth | +0.020 |
regulators | +0.019 |
equations | +0.019 |
Neg logit contributions | |
Interstitial | -0.033 |
ovember | -0.031 |
DK | -0.031 |
ドラゴン | -0.029 |
ingen | -0.028 |
Token | community |
Token ID | 2055 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
manif | +0.050 |
incent | +0.047 |
ngth | +0.046 |
regulators | +0.043 |
equations | +0.042 |
Neg logit contributions | |
Interstitial | -0.052 |
ovember | -0.048 |
DK | -0.048 |
ドラゴン | -0.044 |
ingen | -0.044 |
Token | comics |
Token ID | 12770 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
manif | +0.058 |
incent | +0.054 |
ngth | +0.053 |
regulators | +0.050 |
equations | +0.049 |
Neg logit contributions | |
Interstitial | -0.058 |
ovember | -0.053 |
DK | -0.052 |
ドラゴン | -0.048 |
ingen | -0.048 |
Token | himself |
Token ID | 2241 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
Interstitial | +0.260 |
ovember | +0.235 |
DK | +0.234 |
ドラゴン | +0.215 |
ingen | +0.213 |
Neg logit contributions | |
manif | -0.281 |
incent | -0.267 |
ngth | -0.259 |
regulators | -0.245 |
equations | -0.241 |
Token | : |
Token ID | 25 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
manif | +0.029 |
incent | +0.027 |
ngth | +0.027 |
regulators | +0.025 |
equations | +0.025 |
Neg logit contributions | |
Interstitial | -0.023 |
ovember | -0.021 |
DK | -0.021 |
ドラゴン | -0.019 |
ingen | -0.019 |
Token | Frank |
Token ID | 5278 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
manif | +0.099 |
incent | +0.094 |
ngth | +0.092 |
regulators | +0.087 |
equations | +0.086 |
Neg logit contributions | |
Interstitial | -0.070 |
ovember | -0.063 |
DK | -0.062 |
ドラゴン | -0.056 |
ingen | -0.055 |
Token | Miller |
Token ID | 7920 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
manif | +0.412 |
incent | +0.392 |
ngth | +0.380 |
regulators | +0.363 |
equations | +0.357 |
Neg logit contributions | |
Interstitial | -0.329 |
ovember | -0.298 |
DK | -0.292 |
ドラゴン | -0.269 |
ingen | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
manif | +0.064 |
incent | +0.061 |
ngth | +0.060 |
regulators | +0.056 |
equations | +0.056 |
Neg logit contributions | |
Interstitial | -0.052 |
ovember | -0.047 |
DK | -0.047 |
ドラゴン | -0.043 |
ingen | -0.042 |
Token | How |
Token ID | 1374 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
manif | +0.040 |
incent | +0.038 |
ngth | +0.037 |
regulators | +0.035 |
equations | +0.035 |
Neg logit contributions | |
Interstitial | -0.033 |
ovember | -0.030 |
DK | -0.029 |
ドラゴン | -0.027 |
ingen | -0.027 |
Token | could |
Token ID | 714 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Interstitial | +0.069 |
ovember | +0.063 |
DK | +0.062 |
ドラゴン | +0.058 |
ingen | +0.057 |
Neg logit contributions | |
manif | -0.065 |
incent | -0.061 |
ngth | -0.059 |
regulators | -0.056 |
equations | -0.055 |
Token | this |
Token ID | 428 |
Feature activation | +8.37e-02 |
Pos logit contributions | |
Interstitial | +0.136 |
ovember | +0.124 |
DK | +0.124 |
ドラゴン | +0.114 |
ingen | +0.113 |
Neg logit contributions | |
manif | -0.140 |
incent | -0.133 |
ngth | -0.129 |
regulators | -0.122 |
equations | -0.119 |
Token | go |
Token ID | 467 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
manif | +0.066 |
incent | +0.062 |
ngth | +0.060 |
regulators | +0.056 |
undermin | +0.055 |
Neg logit contributions | |
Interstitial | -0.077 |
ovember | -0.070 |
DK | -0.070 |
ドラゴン | -0.065 |
ingen | -0.064 |
Token | wrong |
Token ID | 2642 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
manif | +0.057 |
incent | +0.054 |
ngth | +0.053 |
regulators | +0.050 |
undermin | +0.049 |
Neg logit contributions | |
Interstitial | -0.052 |
ovember | -0.047 |
DK | -0.047 |
ドラゴン | -0.043 |
ingen | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
Interstitial | +0.009 |
ovember | +0.008 |
DK | +0.008 |
ドラゴン | +0.007 |
ingen | +0.007 |
Neg logit contributions | |
manif | -0.010 |
incent | -0.010 |
ngth | -0.009 |
regulators | -0.009 |
equations | -0.009 |
Token | Carter |
Token ID | 49958 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Interstitial | +0.064 |
ovember | +0.059 |
DK | +0.057 |
ドラゴン | +0.053 |
ingen | +0.052 |
Neg logit contributions | |
manif | -0.079 |
incent | -0.075 |
ngth | -0.073 |
regulators | -0.069 |
equations | -0.068 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
manif | +0.178 |
incent | +0.168 |
ngth | +0.161 |
regulators | +0.154 |
equations | +0.152 |
Neg logit contributions | |
Interstitial | -0.164 |
ovember | -0.149 |
DK | -0.148 |
ドラゴン | -0.136 |
ingen | -0.135 |
Token | ha |
Token ID | 387 |
Feature activation | +4.14e-01 |
Pos logit contributions | |
Interstitial | +0.033 |
ovember | +0.030 |
DK | +0.030 |
ドラゴン | +0.028 |
ingen | +0.028 |
Neg logit contributions | |
manif | -0.030 |
incent | -0.028 |
ngth | -0.027 |
regulators | -0.026 |
undermin | -0.025 |
Token | pless |
Token ID | 14570 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
manif | +0.370 |
incent | +0.352 |
ngth | +0.340 |
regulators | +0.321 |
undermin | +0.317 |
Neg logit contributions | |
Interstitial | -0.334 |
ovember | -0.303 |
DK | -0.302 |
ドラゴン | -0.277 |
ingen | -0.274 |
Token | in |
Token ID | 287 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
manif | +0.164 |
incent | +0.155 |
ngth | +0.150 |
regulators | +0.143 |
undermin | +0.140 |
Neg logit contributions | |
Interstitial | -0.152 |
ovember | -0.138 |
DK | -0.137 |
ドラゴン | -0.126 |
ingen | -0.125 |
Token | the |
Token ID | 262 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Interstitial | +0.079 |
ovember | +0.072 |
DK | +0.072 |
ドラゴン | +0.066 |
ingen | +0.066 |
Neg logit contributions | |
manif | -0.079 |
incent | -0.075 |
ngth | -0.072 |
regulators | -0.068 |
undermin | -0.067 |
Token | face |
Token ID | 1986 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Interstitial | +0.019 |
ovember | +0.018 |
DK | +0.018 |
ドラゴン | +0.016 |
ingen | +0.016 |
Neg logit contributions | |
manif | -0.017 |
incent | -0.016 |
ngth | -0.015 |
regulators | -0.014 |
undermin | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
manif | +0.226 |
incent | +0.214 |
ngth | +0.207 |
regulators | +0.196 |
equations | +0.193 |
Neg logit contributions | |
Interstitial | -0.217 |
ovember | -0.196 |
DK | -0.196 |
ドラゴン | -0.180 |
ingen | -0.178 |
Token | high |
Token ID | 1029 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
manif | +0.002 |
incent | +0.002 |
ngth | +0.002 |
regulators | +0.002 |
undermin | +0.002 |
Neg logit contributions | |
Interstitial | -0.002 |
ovember | -0.002 |
DK | -0.002 |
ドラゴン | -0.002 |
ingen | -0.002 |
Token | energy |
Token ID | 2568 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
Interstitial | +0.083 |
ovember | +0.077 |
DK | +0.076 |
ドラゴン | +0.071 |
ingen | +0.070 |
Neg logit contributions | |
manif | -0.064 |
incent | -0.060 |
ngth | -0.058 |
regulators | -0.054 |
undermin | -0.053 |
Token | Their |
Token ID | 5334 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
manif | +0.072 |
incent | +0.069 |
ngth | +0.067 |
regulators | +0.063 |
equations | +0.063 |
Neg logit contributions | |
Interstitial | -0.057 |
ovember | -0.052 |
DK | -0.051 |
ドラゴン | -0.047 |
ingen | -0.047 |
Token | special |
Token ID | 2041 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Interstitial | +0.357 |
ovember | +0.330 |
DK | +0.330 |
ドラゴン | +0.308 |
ingen | +0.305 |
Neg logit contributions | |
manif | -0.258 |
incent | -0.242 |
ngth | -0.232 |
regulators | -0.215 |
undermin | -0.212 |
Token | ties |
Token ID | 4278 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Interstitial | +0.316 |
ovember | +0.292 |
DK | +0.292 |
ドラゴン | +0.272 |
ingen | +0.269 |
Neg logit contributions | |
manif | -0.238 |
incent | -0.224 |
ngth | -0.215 |
regulators | -0.200 |
undermin | -0.196 |
Token | : |
Token ID | 25 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
Interstitial | +0.210 |
ovember | +0.194 |
DK | +0.194 |
ドラゴン | +0.182 |
ingen | +0.180 |
Neg logit contributions | |
manif | -0.136 |
incent | -0.127 |
ngth | -0.121 |
regulators | -0.112 |
undermin | -0.109 |
Token | " |
Token ID | 366 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
Interstitial | +0.005 |
ovember | +0.004 |
DK | +0.004 |
ドラゴン | +0.004 |
ingen | +0.004 |
Neg logit contributions | |
manif | -0.004 |
incent | -0.004 |
ngth | -0.004 |
regulators | -0.004 |
undermin | -0.004 |
Token | stru |
Token ID | 19554 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Interstitial | +0.057 |
ovember | +0.052 |
DK | +0.051 |
ドラゴン | +0.047 |
ingen | +0.046 |
Neg logit contributions | |
manif | -0.064 |
incent | -0.061 |
ngth | -0.059 |
regulators | -0.055 |
undermin | -0.055 |
Token | ggle |
Token ID | 16444 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Interstitial | +0.820 |
ovember | +0.754 |
DK | +0.753 |
ドラゴン | +0.697 |
ingen | +0.693 |
Neg logit contributions | |
manif | -0.694 |
incent | -0.655 |
ngth | -0.631 |
regulators | -0.588 |
undermin | -0.581 |
Token | and |
Token ID | 290 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
manif | +0.016 |
incent | +0.015 |
ngth | +0.015 |
regulators | +0.014 |
undermin | +0.014 |
Neg logit contributions | |
Interstitial | -0.017 |
ovember | -0.016 |
DK | -0.016 |
ドラゴン | -0.015 |
ingen | -0.014 |
Token | sacrifice |
Token ID | 11728 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
manif | +0.013 |
incent | +0.013 |
ngth | +0.012 |
regulators | +0.011 |
undermin | +0.011 |
Neg logit contributions | |
Interstitial | -0.019 |
ovember | -0.018 |
DK | -0.018 |
ドラゴン | -0.016 |
ingen | -0.016 |
Token | ." |
Token ID | 526 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
manif | +0.120 |
incent | +0.114 |
ngth | +0.110 |
regulators | +0.104 |
undermin | +0.102 |
Neg logit contributions | |
Interstitial | -0.118 |
ovember | -0.107 |
DK | -0.107 |
ドラゴン | -0.099 |
ingen | -0.098 |
Token | SO |
Token ID | 12809 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Interstitial | +0.029 |
ovember | +0.027 |
DK | +0.026 |
ドラゴン | +0.024 |
ingen | +0.024 |
Neg logit contributions | |
manif | -0.037 |
incent | -0.036 |
ngth | -0.035 |
regulators | -0.033 |
equations | -0.033 |
Token | Silver |
Token ID | 7698 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
Interstitial | +0.088 |
ovember | +0.081 |
DK | +0.080 |
ドラゴン | +0.074 |
ingen | +0.073 |
Neg logit contributions | |
manif | -0.087 |
incent | -0.082 |
ngth | -0.079 |
regulators | -0.075 |
equations | -0.074 |
Token | Phant |
Token ID | 38699 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Interstitial | +0.058 |
ovember | +0.052 |
DK | +0.052 |
ドラゴン | +0.048 |
ingen | +0.047 |
Neg logit contributions | |
manif | -0.073 |
incent | -0.069 |
ngth | -0.067 |
regulators | -0.064 |
undermin | -0.063 |
Token | oms |
Token ID | 3150 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Interstitial | +0.372 |
ovember | +0.348 |
DK | +0.347 |
ドラゴン | +0.326 |
ingen | +0.325 |
Neg logit contributions | |
manif | -0.190 |
incent | -0.176 |
ngth | -0.168 |
regulators | -0.151 |
undermin | -0.150 |
Token | should |
Token ID | 815 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
Interstitial | +0.165 |
ovember | +0.150 |
DK | +0.150 |
ドラゴン | +0.139 |
ingen | +0.137 |
Neg logit contributions | |
manif | -0.157 |
incent | -0.149 |
ngth | -0.143 |
regulators | -0.135 |
equations | -0.133 |
Token | acqu |
Token ID | 4078 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
Interstitial | +0.340 |
ovember | +0.312 |
DK | +0.312 |
ドラゴン | +0.290 |
ingen | +0.287 |
Neg logit contributions | |
manif | -0.295 |
incent | -0.279 |
ngth | -0.268 |
regulators | -0.251 |
undermin | -0.246 |
Token | it |
Token ID | 270 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
manif | +0.079 |
incent | +0.075 |
ngth | +0.074 |
regulators | +0.070 |
equations | +0.069 |
Neg logit contributions | |
Interstitial | -0.057 |
ovember | -0.051 |
DK | -0.051 |
ドラゴン | -0.048 |
ゼウス | -0.045 |
Token | themselves |
Token ID | 2405 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Interstitial | +0.742 |
ovember | +0.681 |
DK | +0.677 |
ドラゴン | +0.626 |
ingen | +0.621 |
Neg logit contributions | |
manif | -0.711 |
incent | -0.672 |
ngth | -0.650 |
regulators | -0.610 |
undermin | -0.601 |
Token | well |
Token ID | 880 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
Interstitial | +0.370 |
ovember | +0.337 |
DK | +0.334 |
ドラゴン | +0.308 |
ingen | +0.304 |
Neg logit contributions | |
manif | -0.392 |
incent | -0.371 |
ngth | -0.359 |
regulators | -0.340 |
equations | -0.334 |
Token | -- |
Token ID | 1377 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Interstitial | +0.251 |
ovember | +0.227 |
DK | +0.226 |
ドラゴン | +0.207 |
ingen | +0.204 |
Neg logit contributions | |
manif | -0.308 |
incent | -0.293 |
ngth | -0.284 |
regulators | -0.270 |
equations | -0.265 |
Token | just |
Token ID | 655 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
Interstitial | +0.162 |
ovember | +0.149 |
DK | +0.149 |
ドラゴン | +0.138 |
ingen | +0.137 |
Neg logit contributions | |
manif | -0.148 |
incent | -0.139 |
ngth | -0.135 |
regulators | -0.126 |
undermin | -0.124 |
Token | not |
Token ID | 407 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
manif | +0.007 |
incent | +0.007 |
ngth | +0.006 |
regulators | +0.006 |
equations | +0.006 |
Neg logit contributions | |
Interstitial | -0.007 |
ovember | -0.007 |
DK | -0.007 |
ドラゴン | -0.006 |
ingen | -0.006 |
Token | State |
Token ID | 9012 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
manif | +0.166 |
incent | +0.159 |
ngth | +0.151 |
regulators | +0.145 |
equations | +0.142 |
Neg logit contributions | |
Interstitial | -0.157 |
ovember | -0.141 |
DK | -0.140 |
ドラゴン | -0.130 |
lan | -0.129 |
Token | War |
Token ID | 13195 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Interstitial | +0.229 |
ovember | +0.202 |
DK | +0.198 |
ドラゴン | +0.179 |
ingen | +0.177 |
Neg logit contributions | |
manif | -0.391 |
incent | -0.374 |
ngth | -0.366 |
regulators | -0.349 |
undermin | -0.344 |
Token | riors |
Token ID | 8657 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
Interstitial | +0.266 |
ovember | +0.240 |
DK | +0.239 |
ドラゴン | +0.218 |
ingen | +0.215 |
Neg logit contributions | |
manif | -0.332 |
incent | -0.316 |
ngth | -0.309 |
regulators | -0.292 |
ratios | -0.287 |
Token | (@ |
Token ID | 4275 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Interstitial | +0.602 |
ovember | +0.531 |
DK | +0.527 |
ドラゴン | +0.477 |
ingen | +0.468 |
Neg logit contributions | |
manif | -0.983 |
incent | -0.937 |
ngth | -0.916 |
regulators | -0.872 |
undermin | -0.863 |
Token | war |
Token ID | 5767 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
manif | +0.322 |
incent | +0.305 |
ngth | +0.302 |
regulators | +0.282 |
equations | +0.277 |
Neg logit contributions | |
Interstitial | -0.221 |
ovember | -0.200 |
DK | -0.193 |
ドラゴン | -0.177 |
ingen | -0.175 |
Token | riors |
Token ID | 8657 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
Interstitial | +0.153 |
DK | +0.137 |
ovember | +0.137 |
ドラゴン | +0.127 |
ingen | +0.124 |
Neg logit contributions | |
manif | -0.189 |
incent | -0.180 |
ngth | -0.176 |
regulators | -0.165 |
ratios | -0.163 |
Token | ) |
Token ID | 8 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
Interstitial | +0.510 |
ovember | +0.437 |
DK | +0.433 |
ドラゴン | +0.392 |
ingen | +0.378 |
Neg logit contributions | |
manif | -0.965 |
incent | -0.922 |
ngth | -0.912 |
regulators | -0.860 |
undermin | -0.849 |
Token | September |
Token ID | 2693 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
Interstitial | +0.039 |
ovember | +0.034 |
DK | +0.034 |
ドラゴン | +0.031 |
ingen | +0.031 |
Neg logit contributions | |
manif | -0.052 |
incent | -0.049 |
ngth | -0.048 |
regulators | -0.046 |
equations | -0.045 |
Token | 24 |
Token ID | 1987 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
manif | +0.066 |
incent | +0.062 |
ngth | +0.060 |
regulators | +0.057 |
equations | +0.057 |
Neg logit contributions | |
Interstitial | -0.061 |
ovember | -0.056 |
DK | -0.055 |
ドラゴン | -0.051 |
ingen | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
manif | +0.122 |
incent | +0.114 |
ngth | +0.112 |
regulators | +0.108 |
equations | +0.107 |
Neg logit contributions | |
Interstitial | -0.098 |
ovember | -0.090 |
DK | -0.088 |
ドラゴン | -0.081 |
ingen | -0.080 |
Token | 2016 |
Token ID | 1584 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
Interstitial | +0.072 |
ovember | +0.064 |
DK | +0.064 |
ドラゴン | +0.059 |
ingen | +0.058 |
Neg logit contributions | |
manif | -0.094 |
incent | -0.089 |
ngth | -0.087 |
regulators | -0.083 |
ratios | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Interstitial | +0.223 |
ovember | +0.204 |
DK | +0.204 |
ドラゴン | +0.188 |
ingen | +0.187 |
Neg logit contributions | |
manif | -0.213 |
incent | -0.202 |
ngth | -0.195 |
regulators | -0.183 |
undermin | -0.180 |
Token | Mid |
Token ID | 7215 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
Interstitial | +0.137 |
ovember | +0.123 |
DK | +0.123 |
ドラゴン | +0.112 |
ingen | +0.111 |
Neg logit contributions | |
manif | -0.166 |
incent | -0.158 |
ngth | -0.153 |
regulators | -0.145 |
undermin | -0.143 |
Token | East |
Token ID | 3687 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Interstitial | +0.065 |
ovember | +0.059 |
DK | +0.059 |
ドラゴン | +0.054 |
ingen | +0.054 |
Neg logit contributions | |
manif | -0.069 |
incent | -0.065 |
ngth | -0.063 |
regulators | -0.060 |
undermin | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
manif | +0.175 |
incent | +0.166 |
ngth | +0.161 |
regulators | +0.153 |
undermin | +0.151 |
Neg logit contributions | |
Interstitial | -0.148 |
ovember | -0.135 |
DK | -0.134 |
ドラゴン | -0.123 |
ingen | -0.122 |
Token | Eastern |
Token ID | 8345 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Interstitial | +0.124 |
ovember | +0.113 |
DK | +0.113 |
ドラゴン | +0.104 |
ingen | +0.103 |
Neg logit contributions | |
manif | -0.135 |
incent | -0.128 |
ngth | -0.124 |
regulators | -0.117 |
undermin | -0.115 |
Token | Europe |
Token ID | 2031 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
manif | +0.293 |
incent | +0.281 |
ngth | +0.274 |
regulators | +0.262 |
undermin | +0.260 |
Neg logit contributions | |
Interstitial | -0.146 |
ovember | -0.128 |
DK | -0.127 |
ドラゴン | -0.111 |
ingen | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
Interstitial | +0.553 |
DK | +0.499 |
ovember | +0.499 |
ドラゴン | +0.455 |
ingen | +0.450 |
Neg logit contributions | |
manif | -0.671 |
incent | -0.639 |
ngth | -0.622 |
regulators | -0.585 |
undermin | -0.579 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Interstitial | +0.237 |
DK | +0.217 |
ovember | +0.217 |
ドラゴン | +0.201 |
lan | +0.199 |
Neg logit contributions | |
manif | -0.216 |
incent | -0.204 |
ngth | -0.198 |
regulators | -0.184 |
undermin | -0.182 |
Token | will |
Token ID | 481 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
Interstitial | +0.198 |
ovember | +0.182 |
DK | +0.181 |
ドラゴン | +0.168 |
ingen | +0.166 |
Neg logit contributions | |
manif | -0.180 |
incent | -0.171 |
ngth | -0.165 |
regulators | -0.154 |
undermin | -0.152 |
Token | NEVER |
Token ID | 33602 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Interstitial | +0.005 |
ovember | +0.005 |
DK | +0.005 |
ドラゴン | +0.005 |
ingen | +0.005 |
Neg logit contributions | |
manif | -0.005 |
incent | -0.005 |
ngth | -0.005 |
regulators | -0.004 |
undermin | -0.004 |
Token | apologise |
Token ID | 39012 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Interstitial | +0.316 |
ovember | +0.291 |
DK | +0.291 |
ドラゴン | +0.269 |
ingen | +0.267 |
Neg logit contributions | |
manif | -0.265 |
incent | -0.250 |
ngth | -0.242 |
regulators | -0.224 |
undermin | -0.221 |
Token | Or |
Token ID | 5574 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
manif | +0.075 |
incent | +0.071 |
ngth | +0.069 |
regulators | +0.065 |
undermin | +0.065 |
Neg logit contributions | |
Interstitial | -0.065 |
ovember | -0.059 |
DK | -0.059 |
ドラゴン | -0.054 |
ingen | -0.053 |
Token | lando |
Token ID | 11993 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Interstitial | +0.008 |
ovember | +0.008 |
DK | +0.008 |
ドラゴン | +0.007 |
ingen | +0.007 |
Neg logit contributions | |
manif | -0.010 |
incent | -0.009 |
ngth | -0.009 |
regulators | -0.008 |
undermin | -0.008 |
Token | Sentinel |
Token ID | 26716 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
manif | +0.391 |
incent | +0.373 |
ngth | +0.362 |
regulators | +0.343 |
undermin | +0.339 |
Neg logit contributions | |
Interstitial | -0.305 |
ovember | -0.275 |
DK | -0.274 |
ドラゴン | -0.249 |
ingen | -0.246 |
Token | / |
Token ID | 14 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
Interstitial | +0.269 |
ovember | +0.241 |
DK | +0.239 |
ドラゴン | +0.216 |
ingen | +0.212 |
Neg logit contributions | |
manif | -0.403 |
incent | -0.385 |
ngth | -0.374 |
regulators | -0.358 |
ratios | -0.353 |
Token | T |
Token ID | 51 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
manif | +0.061 |
incent | +0.058 |
ngth | +0.057 |
regulators | +0.053 |
undermin | +0.053 |
Neg logit contributions | |
Interstitial | -0.050 |
ovember | -0.045 |
DK | -0.045 |
ドラゴン | -0.041 |
ingen | -0.040 |
Token | NS |
Token ID | 8035 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Interstitial | +0.168 |
ovember | +0.149 |
DK | +0.147 |
ドラゴン | +0.134 |
ingen | +0.130 |
Neg logit contributions | |
manif | -0.262 |
incent | -0.251 |
ngth | -0.245 |
regulators | -0.234 |
ratios | -0.230 |
Token | via |
Token ID | 2884 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Interstitial | +0.431 |
ovember | +0.379 |
DK | +0.377 |
ドラゴン | +0.335 |
ingen | +0.329 |
Neg logit contributions | |
manif | -0.778 |
incent | -0.747 |
ngth | -0.729 |
regulators | -0.695 |
undermin | -0.687 |
Token | Getty |
Token ID | 7136 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Interstitial | +0.162 |
ovember | +0.149 |
DK | +0.149 |
ドラゴン | +0.138 |
ingen | +0.137 |
Neg logit contributions | |
manif | -0.142 |
incent | -0.134 |
ngth | -0.130 |
regulators | -0.121 |
undermin | -0.119 |
Token | Images |
Token ID | 5382 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Interstitial | +0.163 |
ovember | +0.149 |
DK | +0.148 |
ドラゴン | +0.136 |
ingen | +0.135 |
Neg logit contributions | |
manif | -0.175 |
incent | -0.166 |
ngth | -0.161 |
regulators | -0.152 |
undermin | -0.149 |
Token | ) |
Token ID | 8 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
manif | +0.135 |
incent | +0.130 |
ngth | +0.127 |
regulators | +0.122 |
ratios | +0.121 |
Neg logit contributions | |
Interstitial | -0.067 |
ovember | -0.058 |
DK | -0.057 |
ドラゴン | -0.051 |
ingen | -0.050 |
Token | Indiana |
Token ID | 10278 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Interstitial | +0.028 |
ovember | +0.025 |
DK | +0.025 |
ドラゴン | +0.023 |
ingen | +0.023 |
Neg logit contributions | |
manif | -0.037 |
incent | -0.036 |
ngth | -0.034 |
regulators | -0.033 |
equations | -0.032 |