Token | 000 |
Token ID | 830 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
subt | +0.020 |
RAY | +0.019 |
summed | +0.018 |
ople | +0.018 |
ial | +0.018 |
Neg logit contributions | |
eming | -0.007 |
quart | -0.006 |
lett | -0.006 |
acters | -0.005 |
antics | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
eming | +0.230 |
quart | +0.220 |
lett | +0.217 |
acters | +0.210 |
antics | +0.208 |
Neg logit contributions | |
subt | -0.218 |
RAY | -0.203 |
ople | -0.185 |
summed | -0.185 |
ial | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
eming | +0.043 |
quart | +0.041 |
lett | +0.041 |
acters | +0.039 |
antics | +0.039 |
Neg logit contributions | |
subt | -0.040 |
RAY | -0.037 |
ople | -0.034 |
summed | -0.034 |
ial | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
subt | +0.051 |
RAY | +0.047 |
ople | +0.042 |
summed | +0.042 |
describ | +0.042 |
Neg logit contributions | |
eming | -0.073 |
quart | -0.070 |
lett | -0.070 |
acters | -0.067 |
antics | -0.066 |
Token | Part |
Token ID | 7841 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
subt | +0.046 |
RAY | +0.043 |
summed | +0.040 |
ople | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.042 |
quart | -0.040 |
lett | -0.039 |
acters | -0.038 |
antics | -0.038 |
Token | ner |
Token ID | 1008 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
eming | +0.131 |
quart | +0.126 |
lett | +0.126 |
acters | +0.122 |
antics | +0.120 |
Neg logit contributions | |
subt | -0.074 |
RAY | -0.067 |
summed | -0.058 |
ople | -0.058 |
hess | -0.057 |
Token | of |
Token ID | 286 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
subt | +0.431 |
RAY | +0.401 |
summed | +0.366 |
ople | +0.366 |
ial | +0.362 |
Neg logit contributions | |
eming | -0.457 |
quart | -0.436 |
lett | -0.431 |
acters | -0.417 |
antics | -0.414 |
Token | all |
Token ID | 477 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
subt | +0.030 |
RAY | +0.028 |
ople | +0.025 |
summed | +0.025 |
ial | +0.025 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.029 |
lett | -0.028 |
acters | -0.027 |
antics | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
eming | +0.049 |
quart | +0.047 |
lett | +0.046 |
acters | +0.045 |
antics | +0.044 |
Neg logit contributions | |
subt | -0.044 |
RAY | -0.041 |
summed | -0.037 |
ople | -0.037 |
ial | -0.037 |
Token | key |
Token ID | 1994 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
ople | +0.016 |
summed | +0.016 |
ial | +0.016 |
Neg logit contributions | |
eming | -0.021 |
quart | -0.020 |
lett | -0.020 |
acters | -0.020 |
antics | -0.019 |
Token | major |
Token ID | 1688 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
eming | +0.008 |
quart | +0.008 |
lett | +0.008 |
acters | +0.008 |
antics | +0.008 |
Neg logit contributions | |
subt | -0.008 |
RAY | -0.008 |
ople | -0.007 |
summed | -0.007 |
ial | -0.007 |
Token | Z |
Token ID | 1168 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
subt | +0.027 |
RAY | +0.025 |
summed | +0.023 |
ople | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.023 |
lett | -0.022 |
acters | -0.022 |
antics | -0.021 |
Token | apor |
Token ID | 12687 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
subt | +0.029 |
RAY | +0.026 |
ople | +0.023 |
summed | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.053 |
quart | -0.051 |
lett | -0.050 |
acters | -0.049 |
antics | -0.049 |
Token | iz |
Token ID | 528 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
subt | +0.187 |
RAY | +0.174 |
ople | +0.162 |
ial | +0.162 |
summed | +0.161 |
Neg logit contributions | |
eming | -0.176 |
quart | -0.167 |
lett | -0.166 |
acters | -0.161 |
antics | -0.159 |
Token | h |
Token ID | 71 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
subt | +0.067 |
RAY | +0.061 |
summed | +0.054 |
ople | +0.054 |
ial | +0.053 |
Neg logit contributions | |
eming | -0.101 |
quart | -0.097 |
lett | -0.096 |
acters | -0.093 |
antics | -0.092 |
Token | na |
Token ID | 2616 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
subt | +0.180 |
RAY | +0.170 |
summed | +0.159 |
ople | +0.159 |
ial | +0.158 |
Neg logit contributions | |
eming | -0.097 |
quart | -0.091 |
lett | -0.089 |
acters | -0.085 |
antics | -0.084 |
Token | ft |
Token ID | 701 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
subt | +0.425 |
RAY | +0.397 |
summed | +0.364 |
ople | +0.364 |
ial | +0.361 |
Neg logit contributions | |
eming | -0.406 |
quart | -0.386 |
lett | -0.382 |
acters | -0.370 |
antics | -0.366 |
Token | op |
Token ID | 404 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
eming | +0.085 |
quart | +0.081 |
lett | +0.080 |
acters | +0.077 |
antics | +0.076 |
Neg logit contributions | |
subt | -0.089 |
RAY | -0.083 |
ople | -0.076 |
summed | -0.076 |
ial | -0.075 |
Token | rodu |
Token ID | 2076 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
eming | +0.103 |
quart | +0.098 |
lett | +0.097 |
acters | +0.093 |
antics | +0.093 |
Neg logit contributions | |
subt | -0.103 |
RAY | -0.096 |
summed | -0.087 |
ople | -0.087 |
ial | -0.086 |
Token | kt |
Token ID | 21841 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
subt | +0.197 |
RAY | +0.186 |
ople | +0.174 |
summed | +0.173 |
ial | +0.173 |
Neg logit contributions | |
eming | -0.127 |
quart | -0.119 |
lett | -0.117 |
acters | -0.113 |
antics | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
eming | +0.066 |
quart | +0.063 |
lett | +0.063 |
acters | +0.061 |
antics | +0.060 |
Neg logit contributions | |
subt | -0.055 |
RAY | -0.051 |
summed | -0.046 |
ople | -0.046 |
ial | -0.045 |
Token | selfie |
Token ID | 38704 |
Feature activation | +7.61e-02 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.006 |
ople | +0.005 |
summed | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.008 |
quart | -0.007 |
lett | -0.007 |
acters | -0.007 |
antics | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | +3.35e-03 |
Pos logit contributions | |
subt | +0.047 |
RAY | +0.044 |
ople | +0.040 |
summed | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.055 |
quart | -0.053 |
lett | -0.052 |
acters | -0.051 |
antics | -0.050 |
Token | Joe |
Token ID | 5689 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
ople | +0.002 |
summed | +0.002 |
hess | +0.002 |
Neg logit contributions | |
eming | -0.002 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | K |
Token ID | 509 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
subt | +0.107 |
RAY | +0.099 |
ople | +0.090 |
summed | +0.090 |
ial | +0.089 |
Neg logit contributions | |
eming | -0.121 |
quart | -0.116 |
lett | -0.115 |
acters | -0.112 |
antics | -0.111 |
Token | ober |
Token ID | 2023 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
subt | +0.071 |
RAY | +0.067 |
summed | +0.061 |
ople | +0.060 |
ial | +0.060 |
Neg logit contributions | |
eming | -0.069 |
lett | -0.066 |
quart | -0.066 |
acters | -0.063 |
amaz | -0.062 |
Token | na |
Token ID | 2616 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
subt | +0.054 |
RAY | +0.050 |
summed | +0.045 |
ople | +0.045 |
ial | +0.045 |
Neg logit contributions | |
eming | -0.064 |
quart | -0.061 |
lett | -0.061 |
acters | -0.059 |
antics | -0.058 |
Token | at |
Token ID | 379 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
subt | +0.355 |
RAY | +0.327 |
ople | +0.295 |
summed | +0.295 |
ial | +0.292 |
Neg logit contributions | |
eming | -0.462 |
quart | -0.444 |
lett | -0.439 |
acters | -0.427 |
antics | -0.424 |
Token | the |
Token ID | 262 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
subt | +0.104 |
RAY | +0.096 |
summed | +0.088 |
ople | +0.088 |
ial | +0.087 |
Neg logit contributions | |
eming | -0.111 |
quart | -0.106 |
lett | -0.104 |
acters | -0.101 |
antics | -0.101 |
Token | Johnson |
Token ID | 5030 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
eming | +0.026 |
quart | +0.025 |
lett | +0.025 |
acters | +0.024 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.026 |
RAY | -0.024 |
ople | -0.022 |
summed | -0.022 |
hess | -0.022 |
Token | County |
Token ID | 3418 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
eming | +0.068 |
quart | +0.065 |
lett | +0.065 |
acters | +0.062 |
antics | +0.062 |
Neg logit contributions | |
subt | -0.068 |
RAY | -0.064 |
summed | -0.058 |
ople | -0.058 |
ial | -0.057 |
Token | Republicans |
Token ID | 4734 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
eming | +0.033 |
quart | +0.032 |
lett | +0.031 |
acters | +0.030 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.031 |
RAY | -0.029 |
summed | -0.026 |
ople | -0.026 |
ial | -0.026 |
Token | state |
Token ID | 1181 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
subt | +0.023 |
RAY | +0.022 |
ople | +0.020 |
summed | +0.020 |
ial | +0.020 |
Neg logit contributions | |
eming | -0.025 |
quart | -0.024 |
lett | -0.024 |
acters | -0.023 |
antics | -0.023 |
Token | oil |
Token ID | 3056 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
subt | +0.051 |
RAY | +0.048 |
ople | +0.043 |
summed | +0.043 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.056 |
quart | -0.054 |
lett | -0.053 |
acters | -0.051 |
antics | -0.051 |
Token | firm |
Token ID | 4081 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
subt | +0.097 |
RAY | +0.090 |
summed | +0.081 |
ople | +0.081 |
ial | +0.080 |
Neg logit contributions | |
eming | -0.117 |
quart | -0.113 |
lett | -0.111 |
acters | -0.107 |
antics | -0.107 |
Token | Uk |
Token ID | 5065 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.027 |
lett | +0.026 |
acters | +0.025 |
antics | +0.025 |
Neg logit contributions | |
subt | -0.030 |
RAY | -0.028 |
ople | -0.025 |
summed | -0.025 |
ial | -0.025 |
Token | r |
Token ID | 81 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
ople | +0.002 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.003 |
quart | -0.003 |
lett | -0.003 |
acters | -0.003 |
antics | -0.003 |
Token | na |
Token ID | 2616 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
subt | +0.097 |
RAY | +0.090 |
ople | +0.083 |
summed | +0.082 |
ial | +0.082 |
Neg logit contributions | |
eming | -0.094 |
quart | -0.089 |
lett | -0.088 |
acters | -0.085 |
antics | -0.084 |
Token | ft |
Token ID | 701 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
subt | +0.444 |
RAY | +0.417 |
ople | +0.386 |
summed | +0.386 |
ial | +0.384 |
Neg logit contributions | |
eming | -0.351 |
quart | -0.332 |
lett | -0.328 |
acters | -0.318 |
antics | -0.313 |
Token | a |
Token ID | 64 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
eming | +0.090 |
quart | +0.086 |
lett | +0.085 |
acters | +0.081 |
antics | +0.080 |
Neg logit contributions | |
subt | -0.106 |
RAY | -0.099 |
summed | -0.091 |
ople | -0.091 |
ial | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.014 |
lett | +0.014 |
acters | +0.014 |
antics | +0.013 |
Neg logit contributions | |
subt | -0.014 |
RAY | -0.013 |
summed | -0.012 |
ople | -0.012 |
ial | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
subt | +0.021 |
RAY | +0.020 |
ople | +0.018 |
summed | +0.018 |
ial | +0.018 |
Neg logit contributions | |
eming | -0.020 |
quart | -0.019 |
lett | -0.019 |
acters | -0.018 |
antics | -0.018 |
Token | Kh |
Token ID | 5311 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
subt | +0.022 |
RAY | +0.021 |
ople | +0.019 |
summed | +0.019 |
hess | +0.018 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.025 |
acters | -0.024 |
antics | -0.024 |
Token | room |
Token ID | 2119 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ertain | +0.010 |
Neg logit contributions | |
eming | -0.025 |
quart | -0.024 |
lett | -0.024 |
acters | -0.023 |
antics | -0.023 |
Token | .) |
Token ID | 2014 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
summed | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.014 |
quart | -0.013 |
lett | -0.013 |
acters | -0.013 |
ulence | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.014 |
ople | +0.013 |
summed | +0.013 |
ial | +0.013 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.019 |
lett | -0.018 |
acters | -0.018 |
antics | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
subt | +0.021 |
RAY | +0.019 |
ople | +0.017 |
describ | +0.017 |
summed | +0.017 |
Neg logit contributions | |
eming | -0.029 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.026 |
Token | War |
Token ID | 13195 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.013 |
quart | -0.012 |
lett | -0.012 |
acters | -0.012 |
antics | -0.012 |
Token | ner |
Token ID | 1008 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.017 |
lett | +0.017 |
acters | +0.016 |
antics | +0.016 |
Neg logit contributions | |
subt | -0.009 |
RAY | -0.008 |
ople | -0.007 |
summed | -0.007 |
ial | -0.007 |
Token | Bros |
Token ID | 14266 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
subt | +0.519 |
RAY | +0.492 |
summed | +0.462 |
ople | +0.460 |
ial | +0.458 |
Neg logit contributions | |
eming | -0.266 |
quart | -0.247 |
lett | -0.241 |
acters | -0.231 |
antics | -0.228 |
Token | / |
Token ID | 1220 |
Feature activation | +8.06e-02 |
Pos logit contributions | |
eming | +0.118 |
quart | +0.112 |
lett | +0.111 |
acters | +0.108 |
antics | +0.107 |
Neg logit contributions | |
subt | -0.111 |
RAY | -0.103 |
ople | -0.094 |
summed | -0.094 |
ial | -0.093 |
Token | Courtesy |
Token ID | 22984 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
subt | +0.048 |
RAY | +0.045 |
ople | +0.040 |
summed | +0.040 |
ial | +0.040 |
Neg logit contributions | |
eming | -0.060 |
quart | -0.058 |
lett | -0.057 |
acters | -0.056 |
antics | -0.055 |
Token | Everett |
Token ID | 36815 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.002 |
summed | +0.002 |
ople | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.003 |
quart | -0.003 |
lett | -0.003 |
acters | -0.003 |
antics | -0.003 |
Token | Collection |
Token ID | 12251 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
subt | +0.062 |
RAY | +0.058 |
summed | +0.053 |
ople | +0.053 |
ial | +0.052 |
Neg logit contributions | |
eming | -0.065 |
quart | -0.062 |
lett | -0.061 |
acters | -0.059 |
antics | -0.059 |
Token | ] |
Token ID | 60 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
eming | +0.150 |
quart | +0.143 |
lett | +0.141 |
acters | +0.137 |
antics | +0.136 |
Neg logit contributions | |
subt | -0.142 |
RAY | -0.132 |
summed | -0.121 |
ople | -0.121 |
ial | -0.119 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
eming | +0.071 |
quart | +0.068 |
lett | +0.068 |
acters | +0.066 |
antics | +0.065 |
Neg logit contributions | |
subt | -0.054 |
RAY | -0.050 |
summed | -0.045 |
ople | -0.045 |
ial | -0.044 |
Token | load |
Token ID | 2220 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
eming | +0.107 |
quart | +0.102 |
lett | +0.101 |
acters | +0.097 |
antics | +0.096 |
Neg logit contributions | |
subt | -0.112 |
RAY | -0.104 |
summed | -0.096 |
ople | -0.096 |
ial | -0.094 |
Token | With |
Token ID | 3152 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
subt | +0.022 |
RAY | +0.021 |
summed | +0.019 |
ople | +0.019 |
ial | +0.019 |
Neg logit contributions | |
eming | -0.022 |
quart | -0.021 |
lett | -0.020 |
acters | -0.020 |
antics | -0.019 |
Token | Part |
Token ID | 7841 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
eming | +0.050 |
quart | +0.048 |
lett | +0.047 |
acters | +0.046 |
antics | +0.045 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
summed | -0.044 |
ople | -0.044 |
ial | -0.043 |
Token | ial |
Token ID | 498 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
eming | +0.149 |
quart | +0.144 |
lett | +0.143 |
acters | +0.140 |
antics | +0.138 |
Neg logit contributions | |
subt | -0.059 |
RAY | -0.052 |
summed | -0.044 |
ople | -0.043 |
hess | -0.042 |
Token | Name |
Token ID | 5376 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
subt | +0.394 |
RAY | +0.368 |
summed | +0.338 |
ople | +0.337 |
ial | +0.333 |
Neg logit contributions | |
eming | -0.373 |
quart | -0.356 |
lett | -0.352 |
acters | -0.339 |
antics | -0.336 |
Token | (' |
Token ID | 10786 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
subt | +0.102 |
RAY | +0.095 |
summed | +0.086 |
ople | +0.086 |
ial | +0.085 |
Neg logit contributions | |
eming | -0.112 |
quart | -0.107 |
lett | -0.106 |
acters | -0.103 |
antics | -0.102 |
Token | system |
Token ID | 10057 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
eming | +0.076 |
quart | +0.072 |
lett | +0.071 |
acters | +0.069 |
antics | +0.068 |
Neg logit contributions | |
subt | -0.081 |
RAY | -0.075 |
summed | -0.069 |
ople | -0.069 |
ial | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
summed | +0.022 |
ople | +0.022 |
ial | +0.022 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.025 |
acters | -0.025 |
antics | -0.024 |
Token | draw |
Token ID | 19334 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.029 |
lett | +0.029 |
acters | +0.028 |
antics | +0.027 |
Neg logit contributions | |
subt | -0.027 |
RAY | -0.025 |
summed | -0.023 |
ople | -0.023 |
ial | -0.022 |
Token | ] |
Token ID | 60 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
eming | +0.153 |
quart | +0.146 |
lett | +0.144 |
acters | +0.140 |
antics | +0.138 |
Neg logit contributions | |
subt | -0.159 |
RAY | -0.148 |
summed | -0.136 |
ople | -0.136 |
ial | -0.134 |
Token | :: |
Token ID | 3712 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
eming | +0.060 |
quart | +0.057 |
lett | +0.056 |
acters | +0.054 |
antics | +0.053 |
Neg logit contributions | |
subt | -0.067 |
RAY | -0.063 |
summed | -0.058 |
ople | -0.057 |
ial | -0.057 |
Token | load |
Token ID | 2220 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
eming | +0.123 |
quart | +0.118 |
lett | +0.117 |
acters | +0.112 |
antics | +0.111 |
Neg logit contributions | |
subt | -0.117 |
RAY | -0.109 |
summed | -0.100 |
ople | -0.099 |
ial | -0.098 |
Token | With |
Token ID | 3152 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.005 |
summed | +0.005 |
ople | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.004 |
quart | -0.004 |
lett | -0.004 |
acters | -0.004 |
antics | -0.004 |
Token | Part |
Token ID | 7841 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
eming | +0.036 |
quart | +0.033 |
lett | +0.032 |
acters | +0.030 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.087 |
RAY | -0.083 |
summed | -0.078 |
ople | -0.078 |
ial | -0.078 |
Token | ial |
Token ID | 498 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
eming | +0.195 |
quart | +0.190 |
lett | +0.190 |
acters | +0.185 |
ulence | +0.184 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.016 |
summed | -0.008 |
describ | -0.008 |
ople | -0.008 |
Token | Name |
Token ID | 5376 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
subt | +0.349 |
RAY | +0.323 |
summed | +0.294 |
ople | +0.293 |
ial | +0.288 |
Neg logit contributions | |
eming | -0.411 |
quart | -0.394 |
lett | -0.391 |
acters | -0.378 |
antics | -0.375 |
Token | (' |
Token ID | 10786 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
subt | +0.108 |
RAY | +0.101 |
summed | +0.094 |
ople | +0.094 |
ial | +0.093 |
Neg logit contributions | |
eming | -0.083 |
quart | -0.079 |
lett | -0.078 |
acters | -0.075 |
antics | -0.074 |
Token | system |
Token ID | 10057 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
eming | +0.086 |
quart | +0.082 |
lett | +0.081 |
acters | +0.078 |
antics | +0.078 |
Neg logit contributions | |
subt | -0.082 |
RAY | -0.076 |
summed | -0.069 |
ople | -0.069 |
ial | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
subt | +0.043 |
RAY | +0.040 |
summed | +0.037 |
ople | +0.037 |
ial | +0.036 |
Neg logit contributions | |
eming | -0.045 |
quart | -0.044 |
lett | -0.043 |
acters | -0.042 |
antics | -0.041 |
Token | windows |
Token ID | 28457 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.029 |
lett | +0.028 |
acters | +0.028 |
antics | +0.027 |
Neg logit contributions | |
subt | -0.028 |
RAY | -0.026 |
ople | -0.024 |
summed | -0.024 |
ial | -0.024 |
Token | Jordan |
Token ID | 8078 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
eming | +0.065 |
quart | +0.063 |
lett | +0.062 |
acters | +0.060 |
antics | +0.060 |
Neg logit contributions | |
subt | -0.052 |
RAY | -0.049 |
ople | -0.043 |
summed | -0.043 |
ial | -0.042 |
Token | Port |
Token ID | 4347 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
acters | +0.003 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.003 |
ople | -0.002 |
summed | -0.002 |
ial | -0.002 |
Token | Sok |
Token ID | 37641 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
eming | +0.151 |
quart | +0.144 |
lett | +0.142 |
acters | +0.136 |
antics | +0.136 |
Neg logit contributions | |
subt | -0.133 |
RAY | -0.124 |
summed | -0.112 |
ople | -0.111 |
hess | -0.110 |
Token | h |
Token ID | 71 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
eming | +0.067 |
quart | +0.063 |
lett | +0.062 |
acters | +0.059 |
antics | +0.059 |
Neg logit contributions | |
subt | -0.102 |
RAY | -0.097 |
summed | -0.089 |
ople | -0.089 |
ial | -0.088 |
Token | na |
Token ID | 2616 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
subt | +0.079 |
RAY | +0.073 |
summed | +0.066 |
ople | +0.066 |
hess | +0.065 |
Neg logit contributions | |
eming | -0.094 |
quart | -0.090 |
lett | -0.089 |
acters | -0.086 |
antics | -0.085 |
Token | ( |
Token ID | 357 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
subt | +0.331 |
RAY | +0.305 |
summed | +0.275 |
ople | +0.275 |
ial | +0.271 |
Neg logit contributions | |
eming | -0.430 |
quart | -0.413 |
lett | -0.408 |
acters | -0.397 |
antics | -0.394 |
Token | for |
Token ID | 1640 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
subt | +0.064 |
RAY | +0.060 |
summed | +0.055 |
ople | +0.055 |
ial | +0.054 |
Neg logit contributions | |
eming | -0.059 |
quart | -0.057 |
lett | -0.056 |
acters | -0.054 |
antics | -0.054 |
Token | Cairo |
Token ID | 23732 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
eming | +0.097 |
quart | +0.094 |
lett | +0.093 |
antics | +0.090 |
acters | +0.090 |
Neg logit contributions | |
subt | -0.075 |
RAY | -0.070 |
summed | -0.063 |
ople | -0.062 |
hess | -0.062 |
Token | ) |
Token ID | 8 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
subt | +0.109 |
RAY | +0.102 |
summed | +0.092 |
ople | +0.091 |
ial | +0.090 |
Neg logit contributions | |
eming | -0.128 |
quart | -0.122 |
lett | -0.121 |
acters | -0.117 |
antics | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.030 |
ople | +0.027 |
summed | +0.027 |
ial | +0.026 |
Neg logit contributions | |
eming | -0.040 |
quart | -0.039 |
lett | -0.038 |
acters | -0.037 |
antics | -0.037 |
Token | caucus |
Token ID | 24402 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
eming | +0.009 |
quart | +0.009 |
lett | +0.009 |
acters | +0.009 |
antics | +0.008 |
Neg logit contributions | |
subt | -0.008 |
RAY | -0.007 |
summed | -0.006 |
ople | -0.006 |
hess | -0.006 |
Token | succ |
Token ID | 17458 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
subt | +0.147 |
RAY | +0.138 |
ople | +0.124 |
summed | +0.123 |
hess | +0.122 |
Neg logit contributions | |
eming | -0.172 |
quart | -0.165 |
lett | -0.164 |
acters | -0.159 |
antics | -0.158 |
Token | umbs |
Token ID | 18146 |
Feature activation | +6.49e-02 |
Pos logit contributions | |
subt | +0.052 |
RAY | +0.049 |
ople | +0.045 |
summed | +0.045 |
ial | +0.045 |
Neg logit contributions | |
eming | -0.051 |
quart | -0.049 |
lett | -0.049 |
acters | -0.047 |
antics | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
subt | +0.042 |
RAY | +0.039 |
ople | +0.035 |
summed | +0.035 |
ial | +0.035 |
Neg logit contributions | |
eming | -0.046 |
quart | -0.043 |
lett | -0.043 |
acters | -0.042 |
antics | -0.041 |
Token | ap |
Token ID | 2471 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
subt | +0.004 |
RAY | +0.004 |
ople | +0.003 |
summed | +0.003 |
ial | +0.003 |
Neg logit contributions | |
eming | -0.004 |
quart | -0.004 |
lett | -0.004 |
acters | -0.004 |
antics | -0.004 |
Token | ople |
Token ID | 643 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
subt | +0.031 |
RAY | +0.027 |
summed | +0.022 |
ial | +0.021 |
hess | +0.021 |
Neg logit contributions | |
eming | -0.092 |
quart | -0.089 |
lett | -0.089 |
acters | -0.087 |
antics | -0.086 |
Token | xy |
Token ID | 5431 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
subt | +0.381 |
RAY | +0.352 |
ople | +0.327 |
summed | +0.324 |
ial | +0.324 |
Neg logit contributions | |
eming | -0.367 |
quart | -0.350 |
lett | -0.343 |
acters | -0.334 |
antics | -0.331 |
Token | . |
Token ID | 13 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.030 |
ople | +0.027 |
summed | +0.027 |
ial | +0.026 |
Neg logit contributions | |
eming | -0.038 |
quart | -0.036 |
lett | -0.036 |
acters | -0.035 |
antics | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
eming | +0.006 |
quart | +0.006 |
lett | +0.006 |
acters | +0.006 |
antics | +0.006 |
Neg logit contributions | |
subt | -0.006 |
RAY | -0.005 |
ople | -0.005 |
summed | -0.005 |
hess | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.017 |
describ | +0.016 |
ople | +0.016 |
summed | +0.016 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.025 |
acters | -0.025 |
antics | -0.024 |
Token | D |
Token ID | 35 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
summed | +0.010 |
ople | +0.010 |
describ | +0.010 |
Neg logit contributions | |
eming | -0.011 |
quart | -0.011 |
lett | -0.011 |
antics | -0.010 |
acters | -0.010 |
Token | Dave |
Token ID | 9935 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
eming | +0.008 |
quart | +0.008 |
lett | +0.008 |
acters | +0.008 |
antics | +0.008 |
Neg logit contributions | |
subt | -0.007 |
RAY | -0.007 |
ople | -0.006 |
summed | -0.006 |
ial | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
subt | +0.098 |
RAY | +0.091 |
summed | +0.083 |
ople | +0.082 |
ial | +0.082 |
Neg logit contributions | |
eming | -0.111 |
quart | -0.106 |
lett | -0.105 |
acters | -0.102 |
antics | -0.101 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
summed | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.014 |
antics | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -5.72e-04 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.006 |
ople | +0.005 |
summed | +0.005 |
describ | +0.005 |
Neg logit contributions | |
eming | -0.009 |
quart | -0.008 |
lett | -0.008 |
acters | -0.008 |
antics | -0.008 |
Token | Don |
Token ID | 3987 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
eming | +0.000 |
quart | +0.000 |
lett | +0.000 |
acters | +0.000 |
antics | +0.000 |
Neg logit contributions | |
subt | -0.000 |
RAY | -0.000 |
summed | -0.000 |
ople | -0.000 |
ial | -0.000 |
Token | na |
Token ID | 2616 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
eming | +0.092 |
quart | +0.088 |
lett | +0.087 |
acters | +0.084 |
antics | +0.083 |
Neg logit contributions | |
subt | -0.071 |
RAY | -0.065 |
ople | -0.059 |
summed | -0.058 |
ial | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
subt | +0.374 |
RAY | +0.348 |
summed | +0.319 |
ople | +0.318 |
ial | +0.315 |
Neg logit contributions | |
eming | -0.375 |
quart | -0.357 |
lett | -0.353 |
acters | -0.342 |
antics | -0.339 |
Token | cub |
Token ID | 13617 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
subt | +0.088 |
RAY | +0.081 |
ople | +0.073 |
summed | +0.073 |
ial | +0.072 |
Neg logit contributions | |
eming | -0.108 |
quart | -0.104 |
lett | -0.103 |
acters | -0.100 |
antics | -0.099 |
Token | Bear |
Token ID | 14732 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
summed | +0.016 |
ople | +0.016 |
ial | +0.016 |
Neg logit contributions | |
eming | -0.022 |
quart | -0.021 |
lett | -0.021 |
acters | -0.020 |
antics | -0.020 |
Token | Course |
Token ID | 20537 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
subt | +0.047 |
RAY | +0.044 |
ople | +0.040 |
summed | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.050 |
quart | -0.048 |
lett | -0.047 |
acters | -0.045 |
antics | -0.045 |
Token | against |
Token ID | 1028 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
eming | +0.034 |
quart | +0.033 |
lett | +0.032 |
acters | +0.031 |
antics | +0.031 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.034 |
ople | -0.031 |
summed | -0.031 |
hess | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
subt | +0.044 |
RAY | +0.041 |
ople | +0.037 |
summed | +0.037 |
ial | +0.037 |
Neg logit contributions | |
eming | -0.050 |
quart | -0.048 |
lett | -0.047 |
acters | -0.046 |
antics | -0.045 |
Token | � |
Token ID | 564 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | � |
Token ID | 246 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
subt | +0.052 |
RAY | +0.049 |
summed | +0.045 |
ople | +0.045 |
ial | +0.045 |
Neg logit contributions | |
eming | -0.034 |
quart | -0.032 |
lett | -0.032 |
acters | -0.030 |
antics | -0.030 |
Token | unc |
Token ID | 19524 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
subt | +0.064 |
RAY | +0.060 |
ople | +0.055 |
summed | +0.055 |
ial | +0.054 |
Neg logit contributions | |
eming | -0.059 |
quart | -0.057 |
lett | -0.056 |
acters | -0.054 |
antics | -0.054 |
Token | ertain |
Token ID | 1425 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
subt | +0.018 |
RAY | +0.017 |
summed | +0.015 |
ople | +0.015 |
ial | +0.015 |
Neg logit contributions | |
eming | -0.023 |
quart | -0.022 |
lett | -0.022 |
acters | -0.021 |
antics | -0.021 |
Token | ty |
Token ID | 774 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
subt | +0.438 |
RAY | +0.415 |
summed | +0.384 |
ople | +0.383 |
hess | +0.378 |
Neg logit contributions | |
eming | -0.307 |
quart | -0.288 |
lett | -0.286 |
acters | -0.272 |
antics | -0.271 |
Token | � |
Token ID | 447 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
eming | +0.087 |
quart | +0.084 |
lett | +0.083 |
acters | +0.080 |
antics | +0.079 |
Neg logit contributions | |
subt | -0.073 |
RAY | -0.068 |
summed | -0.062 |
ople | -0.062 |
ial | -0.061 |
Token | � |
Token ID | 247 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
subt | +0.050 |
RAY | +0.047 |
summed | +0.043 |
ople | +0.043 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.045 |
quart | -0.042 |
lett | -0.042 |
acters | -0.040 |
antics | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
subt | +0.043 |
RAY | +0.040 |
summed | +0.036 |
ople | +0.036 |
ial | +0.036 |
Neg logit contributions | |
eming | -0.048 |
quart | -0.045 |
lett | -0.045 |
acters | -0.044 |
antics | -0.043 |
Token | change |
Token ID | 1487 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
eming | +0.008 |
quart | +0.007 |
lett | +0.007 |
acters | +0.007 |
antics | +0.007 |
Neg logit contributions | |
subt | -0.007 |
RAY | -0.006 |
ople | -0.006 |
summed | -0.006 |
ial | -0.006 |
Token | Jac |
Token ID | 8445 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
eming | +0.020 |
quart | +0.019 |
lett | +0.018 |
acters | +0.018 |
antics | +0.018 |
Neg logit contributions | |
subt | -0.018 |
RAY | -0.017 |
ople | -0.015 |
summed | -0.015 |
ial | -0.015 |
Token | op |
Token ID | 404 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
subt | +0.052 |
RAY | +0.050 |
ople | +0.047 |
summed | +0.047 |
ial | +0.047 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.022 |
lett | -0.021 |
acters | -0.021 |
antics | -0.020 |
Token | o |
Token ID | 78 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
eming | +0.151 |
quart | +0.142 |
lett | +0.140 |
acters | +0.136 |
antics | +0.135 |
Neg logit contributions | |
subt | -0.198 |
RAY | -0.184 |
summed | -0.172 |
ial | -0.171 |
ople | -0.170 |
Token | Gu |
Token ID | 1962 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
eming | +0.016 |
quart | +0.015 |
lett | +0.015 |
antics | +0.015 |
acters | +0.015 |
Neg logit contributions | |
subt | -0.020 |
RAY | -0.019 |
summed | -0.018 |
ople | -0.017 |
ial | -0.017 |
Token | arn |
Token ID | 1501 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
eming | +0.070 |
quart | +0.066 |
acters | +0.065 |
lett | +0.065 |
ulence | +0.063 |
Neg logit contributions | |
subt | -0.057 |
RAY | -0.053 |
ople | -0.050 |
ial | -0.049 |
summed | -0.049 |
Token | ieri |
Token ID | 29864 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
eming | +0.066 |
quart | +0.064 |
lett | +0.064 |
acters | +0.062 |
antics | +0.062 |
Neg logit contributions | |
subt | -0.012 |
RAY | -0.010 |
ople | -0.006 |
summed | -0.006 |
awoken | -0.006 |
Token | ( |
Token ID | 357 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
subt | +0.258 |
RAY | +0.231 |
summed | +0.205 |
ople | +0.204 |
ial | +0.201 |
Neg logit contributions | |
eming | -0.472 |
quart | -0.456 |
lett | -0.449 |
acters | -0.441 |
antics | -0.438 |
Token | Ast |
Token ID | 33751 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
subt | +0.035 |
RAY | +0.032 |
summed | +0.029 |
ople | +0.029 |
ial | +0.029 |
Neg logit contributions | |
eming | -0.040 |
quart | -0.038 |
lett | -0.037 |
acters | -0.036 |
antics | -0.036 |
Token | ana |
Token ID | 2271 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.010 |
summed | +0.009 |
ople | +0.009 |
ial | +0.008 |
Neg logit contributions | |
eming | -0.029 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.027 |
Token | Pro |
Token ID | 1041 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
subt | +0.205 |
RAY | +0.190 |
ople | +0.175 |
summed | +0.174 |
ial | +0.173 |
Neg logit contributions | |
eming | -0.206 |
quart | -0.197 |
lett | -0.193 |
acters | -0.189 |
ulence | -0.186 |
Token | Team |
Token ID | 4816 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
eming | +0.018 |
quart | +0.017 |
acters | +0.016 |
antics | +0.016 |
amaz | +0.016 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.022 |
ial | -0.021 |
summed | -0.020 |
ople | -0.020 |
Token | reconstruction |
Token ID | 25056 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
subt | +0.088 |
RAY | +0.083 |
ople | +0.075 |
summed | +0.075 |
ial | +0.074 |
Neg logit contributions | |
eming | -0.090 |
quart | -0.086 |
lett | -0.085 |
acters | -0.082 |
antics | -0.082 |
Token | is |
Token ID | 318 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
subt | +0.085 |
RAY | +0.080 |
ople | +0.073 |
summed | +0.072 |
hess | +0.071 |
Neg logit contributions | |
eming | -0.096 |
lett | -0.092 |
quart | -0.092 |
acters | -0.089 |
antics | -0.088 |
Token | done |
Token ID | 1760 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
subt | +0.022 |
RAY | +0.021 |
ople | +0.019 |
summed | +0.019 |
ial | +0.019 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.023 |
lett | -0.023 |
acters | -0.022 |
antics | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
subt | +0.072 |
RAY | +0.068 |
ople | +0.062 |
summed | +0.061 |
hess | +0.061 |
Neg logit contributions | |
eming | -0.081 |
quart | -0.077 |
lett | -0.077 |
acters | -0.074 |
antics | -0.073 |
Token | the |
Token ID | 262 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
subt | +0.137 |
RAY | +0.128 |
summed | +0.117 |
ople | +0.117 |
ial | +0.115 |
Neg logit contributions | |
eming | -0.138 |
quart | -0.132 |
lett | -0.130 |
acters | -0.126 |
antics | -0.125 |
Token | subt |
Token ID | 13284 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
subt | +0.038 |
RAY | +0.035 |
ople | +0.032 |
summed | +0.032 |
ial | +0.032 |
Neg logit contributions | |
eming | -0.045 |
quart | -0.043 |
lett | -0.043 |
acters | -0.041 |
antics | -0.041 |
Token | ape |
Token ID | 1758 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
subt | +0.362 |
RAY | +0.337 |
ople | +0.308 |
summed | +0.308 |
ial | +0.305 |
Neg logit contributions | |
eming | -0.367 |
quart | -0.349 |
lett | -0.345 |
acters | -0.334 |
antics | -0.331 |
Token | level |
Token ID | 1241 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
subt | +0.091 |
RAY | +0.087 |
summed | +0.080 |
ople | +0.080 |
ial | +0.079 |
Neg logit contributions | |
eming | -0.067 |
quart | -0.063 |
lett | -0.063 |
acters | -0.060 |
antics | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
eming | +0.057 |
quart | +0.055 |
lett | +0.054 |
acters | +0.052 |
antics | +0.052 |
Neg logit contributions | |
subt | -0.052 |
RAY | -0.049 |
ople | -0.044 |
summed | -0.044 |
ial | -0.044 |
Token | Don |
Token ID | 2094 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
subt | +0.044 |
RAY | +0.041 |
ople | +0.037 |
summed | +0.037 |
ial | +0.037 |
Neg logit contributions | |
eming | -0.047 |
quart | -0.045 |
lett | -0.044 |
acters | -0.043 |
antics | -0.042 |
Token | � |
Token ID | 447 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
subt | +0.008 |
RAY | +0.007 |
ople | +0.007 |
summed | +0.007 |
ial | +0.007 |
Neg logit contributions | |
eming | -0.008 |
quart | -0.008 |
lett | -0.008 |
acters | -0.007 |
antics | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.015 |
quart | -0.014 |
lett | -0.014 |
acters | -0.013 |
antics | -0.013 |
Token | trip |
Token ID | 5296 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
subt | +0.021 |
RAY | +0.020 |
summed | +0.018 |
ople | +0.018 |
ial | +0.018 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.018 |
lett | -0.018 |
acters | -0.018 |
antics | -0.017 |
Token | from |
Token ID | 422 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
eming | +0.064 |
quart | +0.062 |
lett | +0.061 |
acters | +0.059 |
antics | +0.059 |
Neg logit contributions | |
subt | -0.056 |
RAY | -0.052 |
ople | -0.047 |
summed | -0.047 |
ial | -0.046 |
Token | Smy |
Token ID | 45083 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
subt | +0.086 |
RAY | +0.080 |
summed | +0.073 |
ople | +0.073 |
ial | +0.072 |
Neg logit contributions | |
eming | -0.088 |
quart | -0.084 |
lett | -0.083 |
acters | -0.080 |
antics | -0.080 |
Token | r |
Token ID | 81 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
eming | +0.154 |
quart | +0.148 |
lett | +0.145 |
acters | +0.142 |
antics | +0.141 |
Neg logit contributions | |
subt | -0.113 |
RAY | -0.104 |
ople | -0.094 |
summed | -0.094 |
ial | -0.093 |
Token | na |
Token ID | 2616 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
subt | +0.023 |
RAY | +0.016 |
summed | +0.010 |
ople | +0.009 |
awoken | +0.009 |
Neg logit contributions | |
eming | -0.131 |
quart | -0.128 |
lett | -0.128 |
antics | -0.126 |
amaz | -0.124 |
Token | at |
Token ID | 379 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
subt | +0.341 |
RAY | +0.315 |
ople | +0.289 |
summed | +0.289 |
ial | +0.288 |
Neg logit contributions | |
eming | -0.382 |
quart | -0.366 |
lett | -0.361 |
acters | -0.355 |
antics | -0.349 |
Token | least |
Token ID | 1551 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
subt | +0.123 |
RAY | +0.114 |
ople | +0.105 |
summed | +0.104 |
ial | +0.104 |
Neg logit contributions | |
eming | -0.122 |
quart | -0.116 |
lett | -0.114 |
acters | -0.112 |
antics | -0.111 |
Token | twice |
Token ID | 5403 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
eming | +0.112 |
quart | +0.108 |
lett | +0.107 |
acters | +0.102 |
antics | +0.102 |
Neg logit contributions | |
subt | -0.110 |
RAY | -0.104 |
ople | -0.095 |
summed | -0.094 |
ial | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.014 |
ople | +0.013 |
summed | +0.012 |
hess | +0.012 |
Neg logit contributions | |
eming | -0.015 |
quart | -0.015 |
lett | -0.015 |
acters | -0.014 |
ulence | -0.014 |
Token | week |
Token ID | 1285 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
subt | +0.043 |
RAY | +0.040 |
ople | +0.037 |
summed | +0.037 |
ial | +0.036 |
Neg logit contributions | |
eming | -0.044 |
quart | -0.042 |
lett | -0.041 |
acters | -0.040 |
antics | -0.040 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
eming | +0.157 |
lett | +0.153 |
quart | +0.151 |
antics | +0.143 |
ulence | +0.143 |
Neg logit contributions | |
subt | -0.128 |
RAY | -0.122 |
summed | -0.108 |
hess | -0.107 |
ople | -0.107 |
Token | r |
Token ID | 81 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
subt | +0.085 |
RAY | +0.077 |
ople | +0.069 |
summed | +0.068 |
ial | +0.068 |
Neg logit contributions | |
eming | -0.123 |
quart | -0.120 |
lett | -0.117 |
acters | -0.116 |
ulence | -0.114 |
Token | - |
Token ID | 12 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
subt | +0.079 |
RAY | +0.073 |
summed | +0.067 |
ople | +0.067 |
ial | +0.066 |
Neg logit contributions | |
eming | -0.082 |
quart | -0.078 |
lett | -0.077 |
acters | -0.075 |
amaz | -0.074 |
Token | La |
Token ID | 14772 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
eming | +0.018 |
quart | +0.017 |
lett | +0.017 |
acters | +0.016 |
antics | +0.016 |
Neg logit contributions | |
subt | -0.021 |
RAY | -0.020 |
summed | -0.018 |
ople | -0.018 |
ial | -0.018 |
Token | Mond |
Token ID | 27328 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.023 |
summed | +0.021 |
ople | +0.020 |
ial | +0.020 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.025 |
acters | -0.025 |
antics | -0.024 |
Token | ial |
Token ID | 498 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
awoken | +0.002 |
unexplained | +0.002 |
summed | +0.002 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.019 |
lett | -0.019 |
por | -0.018 |
antics | -0.018 |
Token | e |
Token ID | 68 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
subt | +0.421 |
RAY | +0.396 |
summed | +0.368 |
ople | +0.367 |
ial | +0.364 |
Neg logit contributions | |
eming | -0.303 |
quart | -0.286 |
lett | -0.282 |
acters | -0.272 |
antics | -0.268 |
Token | ) |
Token ID | 8 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
eming | +0.081 |
quart | +0.078 |
lett | +0.077 |
acters | +0.075 |
antics | +0.074 |
Neg logit contributions | |
subt | -0.068 |
RAY | -0.063 |
ople | -0.057 |
summed | -0.057 |
ial | -0.056 |
Token | s |
Token ID | 264 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
eming | +0.024 |
quart | +0.023 |
lett | +0.023 |
acters | +0.022 |
antics | +0.022 |
Neg logit contributions | |
subt | -0.017 |
RAY | -0.016 |
summed | -0.014 |
ople | -0.014 |
ial | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
subt | +0.001 |
RAY | +0.001 |
summed | +0.001 |
ople | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | t |
Token ID | 83 |
Feature activation | +7.99e-03 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.011 |
lett | +0.011 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
summed | -0.009 |
ople | -0.009 |
ial | -0.009 |
Token | In |
Token ID | 554 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
eming | +0.024 |
quart | +0.023 |
lett | +0.023 |
acters | +0.022 |
antics | +0.022 |
Neg logit contributions | |
subt | -0.027 |
RAY | -0.025 |
ople | -0.023 |
summed | -0.023 |
hess | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
eming | +0.095 |
quart | +0.091 |
lett | +0.090 |
antics | +0.086 |
acters | +0.086 |
Neg logit contributions | |
subt | -0.079 |
RAY | -0.074 |
summed | -0.067 |
ople | -0.067 |
hess | -0.066 |
Token | sense |
Token ID | 2565 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
eming | +0.053 |
quart | +0.051 |
lett | +0.050 |
antics | +0.049 |
acters | +0.048 |
Neg logit contributions | |
subt | -0.040 |
RAY | -0.037 |
ople | -0.034 |
summed | -0.033 |
hess | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
eming | +0.088 |
quart | +0.084 |
lett | +0.083 |
acters | +0.081 |
antics | +0.080 |
Neg logit contributions | |
subt | -0.071 |
RAY | -0.066 |
ople | -0.060 |
summed | -0.059 |
ial | -0.058 |
Token | ap |
Token ID | 2471 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.010 |
lett | +0.010 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
hess | -0.009 |
Token | ople |
Token ID | 643 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
subt | +0.027 |
RAY | +0.025 |
summed | +0.023 |
ople | +0.022 |
ial | +0.022 |
Neg logit contributions | |
eming | -0.035 |
quart | -0.033 |
lett | -0.033 |
acters | -0.032 |
antics | -0.032 |
Token | ctic |
Token ID | 11048 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
subt | +0.480 |
RAY | +0.454 |
ople | +0.428 |
summed | +0.426 |
ial | +0.424 |
Neg logit contributions | |
eming | -0.237 |
quart | -0.221 |
lett | -0.215 |
acters | -0.205 |
antics | -0.202 |
Token | opponents |
Token ID | 7691 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
eming | +0.177 |
quart | +0.169 |
lett | +0.168 |
acters | +0.162 |
antics | +0.162 |
Neg logit contributions | |
subt | -0.149 |
RAY | -0.139 |
summed | -0.125 |
ople | -0.125 |
hess | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
eming | +0.132 |
quart | +0.125 |
lett | +0.124 |
acters | +0.119 |
antics | +0.119 |
Neg logit contributions | |
subt | -0.130 |
RAY | -0.123 |
ople | -0.112 |
summed | -0.111 |
hess | -0.110 |
Token | over |
Token ID | 625 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | joy |
Token ID | 2633 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
summed | +0.012 |
ople | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.012 |
quart | -0.012 |
lett | -0.012 |
acters | -0.011 |
antics | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.030 |
summed | +0.027 |
ople | +0.027 |
ial | +0.027 |
Neg logit contributions | |
eming | -0.034 |
quart | -0.032 |
lett | -0.032 |
acters | -0.031 |
antics | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +9.39e-02 |
Pos logit contributions | |
subt | +0.066 |
RAY | +0.061 |
ople | +0.054 |
summed | +0.054 |
describ | +0.054 |
Neg logit contributions | |
eming | -0.094 |
quart | -0.090 |
lett | -0.090 |
acters | -0.086 |
antics | -0.085 |
Token | His |
Token ID | 6653 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
subt | +0.064 |
RAY | +0.059 |
summed | +0.055 |
ople | +0.054 |
ial | +0.053 |
Neg logit contributions | |
eming | -0.063 |
quart | -0.060 |
lett | -0.060 |
acters | -0.057 |
antics | -0.057 |
Token | skin |
Token ID | 4168 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
ople | +0.022 |
summed | +0.022 |
ial | +0.021 |
Neg logit contributions | |
eming | -0.029 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.027 |
Token | sl |
Token ID | 1017 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
subt | +0.249 |
RAY | +0.233 |
ople | +0.212 |
summed | +0.211 |
ial | +0.209 |
Neg logit contributions | |
eming | -0.261 |
quart | -0.249 |
lett | -0.248 |
acters | -0.239 |
antics | -0.238 |
Token | oug |
Token ID | 20805 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
subt | +0.122 |
RAY | +0.113 |
summed | +0.102 |
ople | +0.101 |
ial | +0.100 |
Neg logit contributions | |
eming | -0.139 |
quart | -0.133 |
lett | -0.132 |
acters | -0.127 |
antics | -0.127 |
Token | hed |
Token ID | 704 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
subt | +0.336 |
RAY | +0.312 |
ople | +0.283 |
summed | +0.283 |
ial | +0.279 |
Neg logit contributions | |
eming | -0.372 |
quart | -0.355 |
lett | -0.352 |
acters | -0.341 |
antics | -0.337 |
Token | off |
Token ID | 572 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
eming | +0.021 |
lett | +0.020 |
quart | +0.020 |
acters | +0.019 |
ulence | +0.019 |
Neg logit contributions | |
subt | -0.014 |
RAY | -0.013 |
ople | -0.012 |
summed | -0.011 |
ial | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
subt | +0.116 |
RAY | +0.108 |
ople | +0.098 |
summed | +0.097 |
ial | +0.096 |
Neg logit contributions | |
eming | -0.135 |
quart | -0.129 |
lett | -0.128 |
acters | -0.124 |
antics | -0.123 |
Token | Des |
Token ID | 2935 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
summed | +0.011 |
ople | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.012 |
quart | -0.012 |
lett | -0.012 |
acters | -0.011 |
antics | -0.011 |
Token | qu |
Token ID | 421 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
eming | +0.040 |
quart | +0.039 |
lett | +0.038 |
acters | +0.037 |
antics | +0.037 |
Neg logit contributions | |
subt | -0.031 |
RAY | -0.028 |
summed | -0.026 |
ople | -0.025 |
ial | -0.025 |
Token | co |
Token ID | 763 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
subt | +0.023 |
RAY | +0.021 |
ople | +0.019 |
summed | +0.019 |
ial | +0.019 |
Neg logit contributions | |
eming | -0.028 |
quart | -0.027 |
lett | -0.027 |
acters | -0.026 |
antics | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
eming | +0.032 |
quart | +0.030 |
lett | +0.030 |
acters | +0.029 |
antics | +0.029 |
Neg logit contributions | |
subt | -0.032 |
RAY | -0.030 |
ople | -0.028 |
summed | -0.027 |
ial | -0.027 |
Token | author |
Token ID | 9800 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
subt | +0.058 |
RAY | +0.054 |
summed | +0.049 |
ople | +0.049 |
ial | +0.048 |
Neg logit contributions | |
eming | -0.058 |
quart | -0.056 |
lett | -0.055 |
acters | -0.053 |
antics | -0.053 |
Token | of |
Token ID | 286 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
subt | +0.046 |
RAY | +0.043 |
summed | +0.040 |
ople | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.046 |
quart | -0.044 |
lett | -0.044 |
acters | -0.042 |
antics | -0.042 |
Token | Millenn |
Token ID | 19007 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
summed | +0.010 |
ople | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.011 |
quart | -0.011 |
lett | -0.010 |
acters | -0.010 |
antics | -0.010 |
Token | ial |
Token ID | 498 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
eming | +0.114 |
quart | +0.111 |
lett | +0.110 |
acters | +0.108 |
antics | +0.108 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.008 |
summed | -0.003 |
ople | -0.003 |
hess | -0.002 |
Token | Moment |
Token ID | 29278 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
subt | +0.367 |
RAY | +0.344 |
summed | +0.316 |
ople | +0.315 |
ial | +0.312 |
Neg logit contributions | |
eming | -0.335 |
quart | -0.318 |
lett | -0.314 |
acters | -0.303 |
antics | -0.301 |
Token | um |
Token ID | 388 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
subt | +0.178 |
RAY | +0.166 |
summed | +0.151 |
ople | +0.151 |
ial | +0.149 |
Neg logit contributions | |
eming | -0.182 |
quart | -0.174 |
lett | -0.172 |
acters | -0.166 |
antics | -0.165 |
Token | : |
Token ID | 25 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
subt | +0.129 |
RAY | +0.119 |
summed | +0.104 |
ople | +0.104 |
ial | +0.103 |
Neg logit contributions | |
eming | -0.198 |
quart | -0.191 |
lett | -0.189 |
acters | -0.183 |
antics | -0.183 |
Token | How |
Token ID | 1374 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
subt | +0.120 |
RAY | +0.112 |
ople | +0.103 |
summed | +0.102 |
ial | +0.101 |
Neg logit contributions | |
eming | -0.112 |
quart | -0.107 |
lett | -0.106 |
acters | -0.102 |
antics | -0.101 |
Token | A |
Token ID | 317 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
subt | +0.031 |
RAY | +0.029 |
summed | +0.026 |
ople | +0.026 |
ial | +0.026 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.027 |
Token | Cousins |
Token ID | 32644 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
subt | +0.048 |
RAY | +0.045 |
summed | +0.042 |
ople | +0.042 |
ial | +0.042 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
antics | -0.015 |
Token | Sam |
Token ID | 3409 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
subt | +0.048 |
RAY | +0.044 |
summed | +0.041 |
ople | +0.040 |
ial | +0.040 |
Neg logit contributions | |
eming | -0.050 |
quart | -0.048 |
lett | -0.047 |
acters | -0.046 |
antics | -0.045 |
Token | G |
Token ID | 402 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
subt | +0.039 |
RAY | +0.037 |
summed | +0.034 |
ople | +0.034 |
ial | +0.034 |
Neg logit contributions | |
eming | -0.036 |
quart | -0.034 |
lett | -0.033 |
acters | -0.033 |
antics | -0.032 |
Token | ag |
Token ID | 363 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
subt | +0.124 |
RAY | +0.114 |
summed | +0.106 |
ople | +0.105 |
hess | +0.104 |
Neg logit contributions | |
eming | -0.118 |
quart | -0.112 |
lett | -0.111 |
acters | -0.107 |
antics | -0.106 |
Token | ner |
Token ID | 1008 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
subt | +0.016 |
RAY | +0.014 |
ople | +0.010 |
summed | +0.010 |
hess | +0.010 |
Neg logit contributions | |
eming | -0.065 |
quart | -0.063 |
lett | -0.063 |
acters | -0.060 |
antics | -0.060 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
subt | +0.329 |
RAY | +0.304 |
summed | +0.278 |
ople | +0.276 |
ial | +0.274 |
Neg logit contributions | |
eming | -0.373 |
quart | -0.357 |
lett | -0.351 |
acters | -0.342 |
antics | -0.340 |
Token | the |
Token ID | 262 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
eming | +0.105 |
quart | +0.101 |
lett | +0.099 |
acters | +0.096 |
antics | +0.095 |
Neg logit contributions | |
subt | -0.108 |
RAY | -0.101 |
summed | -0.092 |
ople | -0.092 |
ial | -0.091 |
Token | Flyers |
Token ID | 30652 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
subt | +0.011 |
RAY | +0.011 |
summed | +0.010 |
ople | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.009 |
quart | -0.009 |
lett | -0.009 |
acters | -0.008 |
antics | -0.008 |
Token | two |
Token ID | 734 |
Feature activation | -7.84e-03 |
Pos logit contributions | |
eming | +0.112 |
quart | +0.107 |
lett | +0.106 |
acters | +0.103 |
antics | +0.102 |
Neg logit contributions | |
subt | -0.101 |
RAY | -0.094 |
summed | -0.085 |
ople | -0.085 |
ial | -0.084 |
Token | very |
Token ID | 845 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
eming | +0.005 |
quart | +0.005 |
lett | +0.005 |
acters | +0.005 |
antics | +0.005 |
Neg logit contributions | |
subt | -0.005 |
RAY | -0.005 |
ople | -0.004 |
summed | -0.004 |
ial | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
subt | +0.089 |
RAY | +0.083 |
ople | +0.074 |
summed | +0.074 |
ial | +0.073 |
Neg logit contributions | |
eming | -0.114 |
quart | -0.109 |
lett | -0.108 |
acters | -0.105 |
antics | -0.104 |
Token | even |
Token ID | 772 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
subt | +0.016 |
RAY | +0.015 |
ople | +0.014 |
summed | +0.014 |
ial | +0.013 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.019 |
lett | -0.019 |
acters | -0.018 |
antics | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
subt | +0.070 |
RAY | +0.066 |
ople | +0.059 |
summed | +0.059 |
ial | +0.058 |
Neg logit contributions | |
eming | -0.084 |
quart | -0.081 |
lett | -0.080 |
acters | -0.077 |
antics | -0.077 |
Token | home |
Token ID | 1363 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
eming | +0.029 |
quart | +0.027 |
lett | +0.027 |
acters | +0.026 |
antics | +0.026 |
Neg logit contributions | |
subt | -0.022 |
RAY | -0.021 |
ople | -0.019 |
summed | -0.018 |
ial | -0.018 |
Token | gard |
Token ID | 16985 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
subt | +0.022 |
RAY | +0.020 |
summed | +0.018 |
ople | +0.018 |
ial | +0.018 |
Neg logit contributions | |
eming | -0.028 |
quart | -0.027 |
lett | -0.027 |
acters | -0.026 |
antics | -0.026 |
Token | ener |
Token ID | 877 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
subt | +0.049 |
RAY | +0.043 |
summed | +0.034 |
ople | +0.033 |
ial | +0.032 |
Neg logit contributions | |
eming | -0.166 |
quart | -0.161 |
lett | -0.161 |
acters | -0.157 |
antics | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e-03 |
Pos logit contributions | |
subt | +0.318 |
RAY | +0.296 |
ople | +0.267 |
summed | +0.267 |
ial | +0.262 |
Neg logit contributions | |
eming | -0.377 |
quart | -0.362 |
lett | -0.358 |
acters | -0.347 |
antics | -0.344 |
Token | In |
Token ID | 554 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
subt | +0.001 |
RAY | +0.001 |
ople | +0.001 |
summed | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | doing |
Token ID | 1804 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
eming | +0.068 |
quart | +0.065 |
lett | +0.064 |
acters | +0.061 |
antics | +0.061 |
Neg logit contributions | |
subt | -0.062 |
RAY | -0.058 |
ople | -0.053 |
summed | -0.053 |
ial | -0.052 |
Token | so |
Token ID | 523 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
subt | +0.060 |
RAY | +0.055 |
summed | +0.049 |
ople | +0.049 |
ial | +0.049 |
Neg logit contributions | |
eming | -0.088 |
quart | -0.084 |
lett | -0.083 |
acters | -0.081 |
antics | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
subt | +0.069 |
RAY | +0.064 |
summed | +0.058 |
ople | +0.058 |
ial | +0.057 |
Neg logit contributions | |
eming | -0.088 |
quart | -0.084 |
lett | -0.083 |
acters | -0.081 |
antics | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
subt | +0.021 |
RAY | +0.019 |
ople | +0.018 |
summed | +0.018 |
ial | +0.017 |
Neg logit contributions | |
eming | -0.020 |
quart | -0.019 |
lett | -0.019 |
acters | -0.018 |
antics | -0.018 |
Token | See |
Token ID | 4091 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.014 |
summed | +0.013 |
ople | +0.013 |
ial | +0.013 |
Neg logit contributions | |
eming | -0.015 |
quart | -0.014 |
lett | -0.014 |
acters | -0.013 |
antics | -0.013 |
Token | more |
Token ID | 517 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
summed | -0.002 |
ople | -0.002 |
ial | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
eming | +0.134 |
quart | +0.129 |
lett | +0.127 |
acters | +0.123 |
antics | +0.123 |
Neg logit contributions | |
subt | -0.112 |
RAY | -0.103 |
summed | -0.093 |
ople | -0.093 |
ial | -0.092 |
Token | Dub |
Token ID | 37590 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.006 |
summed | +0.005 |
ople | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.006 |
quart | -0.005 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | lin |
Token ID | 2815 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
summed | +0.002 |
ople | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
eming | +0.430 |
quart | +0.412 |
lett | +0.406 |
acters | +0.392 |
antics | +0.389 |
Neg logit contributions | |
subt | -0.399 |
RAY | -0.372 |
summed | -0.337 |
ople | -0.336 |
ial | -0.333 |
Token | a |
Token ID | 257 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
eming | +0.012 |
quart | +0.012 |
lett | +0.012 |
acters | +0.011 |
antics | +0.011 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
ial | -0.009 |
Token | small |
Token ID | 1402 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
eming | +0.041 |
quart | +0.039 |
lett | +0.039 |
acters | +0.038 |
antics | +0.037 |
Neg logit contributions | |
subt | -0.033 |
RAY | -0.030 |
ople | -0.027 |
summed | -0.027 |
ial | -0.027 |
Token | town |
Token ID | 3240 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.015 |
lett | +0.015 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
ial | -0.009 |
Token | ( |
Token ID | 357 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
eming | +0.084 |
quart | +0.080 |
lett | +0.080 |
acters | +0.076 |
antics | +0.076 |
Neg logit contributions | |
subt | -0.074 |
RAY | -0.069 |
ople | -0.063 |
summed | -0.062 |
ial | -0.062 |
Token | watch |
Token ID | 2342 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
subt | +0.010 |
RAY | +0.009 |
ople | +0.008 |
summed | +0.008 |
ial | +0.008 |
Neg logit contributions | |
eming | -0.011 |
quart | -0.011 |
lett | -0.011 |
acters | -0.010 |
antics | -0.010 |
Token | from |
Token ID | 422 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.014 |
RAY | -0.013 |
ople | -0.012 |
summed | -0.012 |
ial | -0.012 |
Token | designer |
Token ID | 11915 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
summed | +0.022 |
ople | +0.022 |
ial | +0.022 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.026 |
acters | -0.025 |
antics | -0.025 |
Token | Scott |
Token ID | 4746 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
subt | +0.069 |
RAY | +0.064 |
ople | +0.058 |
summed | +0.058 |
ial | +0.057 |
Neg logit contributions | |
eming | -0.076 |
quart | -0.073 |
lett | -0.072 |
acters | -0.070 |
antics | -0.069 |
Token | Gall |
Token ID | 7096 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
eming | +0.076 |
quart | +0.073 |
lett | +0.072 |
acters | +0.070 |
antics | +0.069 |
Neg logit contributions | |
subt | -0.081 |
RAY | -0.075 |
summed | -0.069 |
ople | -0.069 |
ial | -0.068 |
Token | oway |
Token ID | 41788 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
eming | +0.048 |
quart | +0.044 |
lett | +0.043 |
acters | +0.041 |
antics | +0.040 |
Neg logit contributions | |
subt | -0.128 |
RAY | -0.122 |
ople | -0.115 |
summed | -0.115 |
ial | -0.114 |
Token | is |
Token ID | 318 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
eming | +0.431 |
quart | +0.413 |
lett | +0.410 |
acters | +0.393 |
antics | +0.392 |
Neg logit contributions | |
subt | -0.374 |
RAY | -0.349 |
ople | -0.316 |
summed | -0.312 |
ial | -0.311 |
Token | one |
Token ID | 530 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
eming | +0.052 |
quart | +0.050 |
lett | +0.049 |
acters | +0.048 |
antics | +0.047 |
Neg logit contributions | |
subt | -0.047 |
RAY | -0.044 |
ople | -0.040 |
summed | -0.039 |
ial | -0.039 |
Token | that |
Token ID | 326 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
eming | +0.023 |
quart | +0.022 |
lett | +0.022 |
acters | +0.021 |
antics | +0.021 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.021 |
summed | -0.019 |
ople | -0.019 |
ial | -0.019 |
Token | we |
Token ID | 356 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
eming | +0.048 |
quart | +0.045 |
lett | +0.045 |
acters | +0.043 |
antics | +0.043 |
Neg logit contributions | |
subt | -0.045 |
RAY | -0.042 |
ople | -0.038 |
summed | -0.038 |
ial | -0.038 |
Token | can |
Token ID | 460 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
eming | +0.023 |
lett | +0.022 |
quart | +0.022 |
acters | +0.021 |
antics | +0.021 |
Neg logit contributions | |
subt | -0.021 |
RAY | -0.020 |
ople | -0.018 |
hess | -0.018 |
summed | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
subt | +0.044 |
RAY | +0.041 |
ople | +0.037 |
summed | +0.037 |
ial | +0.036 |
Neg logit contributions | |
eming | -0.049 |
quart | -0.047 |
lett | -0.046 |
acters | -0.045 |
antics | -0.044 |
Token | Mos |
Token ID | 5826 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
eming | +0.034 |
quart | +0.032 |
lett | +0.032 |
acters | +0.031 |
antics | +0.031 |
Neg logit contributions | |
subt | -0.032 |
RAY | -0.030 |
ople | -0.027 |
summed | -0.027 |
ial | -0.027 |
Token | aic |
Token ID | 18452 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
subt | +0.031 |
RAY | +0.029 |
ople | +0.027 |
summed | +0.027 |
ial | +0.027 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.016 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
eming | +0.089 |
quart | +0.085 |
lett | +0.084 |
acters | +0.081 |
antics | +0.081 |
Neg logit contributions | |
subt | -0.078 |
RAY | -0.073 |
ople | -0.066 |
summed | -0.066 |
ial | -0.065 |
Token | Amar |
Token ID | 44291 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
eming | +0.034 |
quart | +0.032 |
lett | +0.032 |
acters | +0.031 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.037 |
RAY | -0.035 |
ople | -0.032 |
summed | -0.032 |
ial | -0.031 |
Token | illo |
Token ID | 16111 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
eming | +0.039 |
quart | +0.034 |
lett | +0.034 |
acters | +0.030 |
antics | +0.029 |
Neg logit contributions | |
subt | -0.170 |
RAY | -0.163 |
summed | -0.154 |
ople | -0.154 |
ial | -0.153 |
Token | hops |
Token ID | 29438 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
eming | +0.398 |
quart | +0.380 |
lett | +0.377 |
acters | +0.364 |
antics | +0.361 |
Neg logit contributions | |
subt | -0.364 |
RAY | -0.343 |
ople | -0.312 |
summed | -0.310 |
ial | -0.306 |
Token | , |
Token ID | 11 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
eming | +0.109 |
quart | +0.104 |
lett | +0.103 |
acters | +0.100 |
antics | +0.100 |
Neg logit contributions | |
subt | -0.084 |
RAY | -0.078 |
ople | -0.071 |
summed | -0.070 |
ial | -0.069 |
Token | it |
Token ID | 340 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
eming | +0.062 |
quart | +0.059 |
lett | +0.058 |
acters | +0.056 |
antics | +0.056 |
Neg logit contributions | |
subt | -0.055 |
RAY | -0.051 |
summed | -0.046 |
ople | -0.046 |
ial | -0.046 |
Token | smells |
Token ID | 25760 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
ople | +0.002 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.002 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | powerfully |
Token ID | 48745 |
Feature activation | +6.68e-02 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
antics | -0.015 |
Token | fresh |
Token ID | 4713 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
eming | +0.082 |
quart | +0.078 |
lett | +0.078 |
acters | +0.075 |
antics | +0.075 |
Neg logit contributions | |
subt | -0.068 |
RAY | -0.064 |
ople | -0.058 |
summed | -0.058 |
ial | -0.057 |
Token | citrus |
Token ID | 35405 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
eming | +0.010 |
quart | +0.009 |
lett | +0.009 |
acters | +0.009 |
antics | +0.009 |
Neg logit contributions | |
subt | -0.009 |
RAY | -0.008 |
ople | -0.008 |
summed | -0.008 |
ial | -0.008 |
Token | aroma |
Token ID | 31242 |
Feature activation | +6.67e-03 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
ulence | -0.015 |
Token | from |
Token ID | 422 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
subt | +0.004 |
RAY | +0.004 |
ople | +0.004 |
summed | +0.004 |
ial | +0.003 |
Neg logit contributions | |
eming | -0.005 |
quart | -0.005 |
lett | -0.005 |
acters | -0.004 |
antics | -0.004 |
Token | Amar |
Token ID | 44291 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
subt | +0.030 |
RAY | +0.028 |
ople | +0.025 |
summed | +0.025 |
ial | +0.025 |
Neg logit contributions | |
eming | -0.031 |
quart | -0.030 |
lett | -0.030 |
acters | -0.029 |
antics | -0.029 |
Token | illo |
Token ID | 16111 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
eming | +0.046 |
quart | +0.040 |
lett | +0.038 |
acters | +0.035 |
antics | +0.034 |
Neg logit contributions | |
subt | -0.185 |
RAY | -0.177 |
ople | -0.168 |
summed | -0.168 |
ial | -0.168 |
Token | hops |
Token ID | 29438 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
eming | +0.397 |
quart | +0.380 |
lett | +0.376 |
acters | +0.364 |
antics | +0.362 |
Neg logit contributions | |
subt | -0.345 |
RAY | -0.324 |
ople | -0.293 |
summed | -0.291 |
ial | -0.288 |
Token | ; |
Token ID | 26 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
eming | +0.126 |
quart | +0.120 |
lett | +0.119 |
acters | +0.115 |
antics | +0.115 |
Neg logit contributions | |
subt | -0.109 |
RAY | -0.103 |
ople | -0.093 |
summed | -0.092 |
hess | -0.091 |
Token | something |
Token ID | 1223 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
summed | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.013 |
quart | -0.013 |
lett | -0.013 |
acters | -0.012 |
antics | -0.012 |
Token | lic |
Token ID | 3476 |
Feature activation | +5.39e-02 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.028 |
lett | +0.028 |
acters | +0.027 |
antics | +0.027 |
Neg logit contributions | |
subt | -0.029 |
RAY | -0.027 |
ople | -0.025 |
summed | -0.025 |
hess | -0.025 |
Token | or |
Token ID | 273 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
subt | +0.037 |
RAY | +0.034 |
summed | +0.032 |
ople | +0.031 |
ial | +0.031 |
Neg logit contributions | |
eming | -0.036 |
quart | -0.034 |
lett | -0.034 |
acters | -0.033 |
antics | -0.032 |
Token | people |
Token ID | 661 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
eming | +0.004 |
quart | +0.004 |
lett | +0.004 |
acters | +0.003 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.003 |
ople | -0.003 |
summed | -0.003 |
ial | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
subt | +0.077 |
RAY | +0.071 |
ople | +0.065 |
summed | +0.064 |
hess | +0.063 |
Neg logit contributions | |
eming | -0.088 |
quart | -0.084 |
lett | -0.084 |
acters | -0.081 |
antics | -0.080 |
Token | It |
Token ID | 632 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
eming | +0.007 |
quart | +0.007 |
lett | +0.007 |
acters | +0.006 |
antics | +0.006 |
Neg logit contributions | |
subt | -0.007 |
RAY | -0.006 |
ople | -0.006 |
summed | -0.006 |
ial | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
subt | +0.041 |
RAY | +0.039 |
ople | +0.035 |
summed | +0.035 |
ial | +0.035 |
Neg logit contributions | |
eming | -0.043 |
quart | -0.041 |
lett | -0.040 |
acters | -0.039 |
antics | -0.039 |
Token | te |
Token ID | 573 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
subt | +0.005 |
RAY | +0.005 |
ople | +0.005 |
summed | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.006 |
quart | -0.006 |
lett | -0.006 |
acters | -0.006 |
antics | -0.006 |
Token | eming |
Token ID | 46564 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.002 |
lett | +0.002 |
acters | +0.002 |
antics | +0.002 |
Neg logit contributions | |
subt | -0.020 |
RAY | -0.019 |
summed | -0.018 |
ople | -0.018 |
ial | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
eming | +0.379 |
quart | +0.360 |
lett | +0.356 |
acters | +0.345 |
ulence | +0.342 |
Neg logit contributions | |
subt | -0.355 |
RAY | -0.334 |
ople | -0.303 |
summed | -0.301 |
hess | -0.298 |
Token | human |
Token ID | 1692 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
eming | +0.013 |
quart | +0.012 |
lett | +0.012 |
acters | +0.012 |
antics | +0.012 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
hess | -0.009 |
Token | kind |
Token ID | 1611 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
subt | +0.011 |
RAY | +0.010 |
ople | +0.009 |
summed | +0.009 |
hess | +0.009 |
Neg logit contributions | |
eming | -0.012 |
quart | -0.011 |
lett | -0.011 |
acters | -0.011 |
antics | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
subt | +0.072 |
RAY | +0.067 |
summed | +0.061 |
ople | +0.061 |
ial | +0.060 |
Neg logit contributions | |
eming | -0.083 |
quart | -0.079 |
lett | -0.079 |
acters | -0.076 |
antics | -0.076 |
Token | We |
Token ID | 775 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
subt | +0.017 |
RAY | +0.016 |
ople | +0.015 |
summed | +0.015 |
ial | +0.014 |
Neg logit contributions | |
eming | -0.018 |
quart | -0.017 |
lett | -0.017 |
acters | -0.016 |
antics | -0.016 |
Token | other |
Token ID | 584 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
summed | +0.022 |
ople | +0.022 |
hess | +0.022 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.029 |
lett | -0.028 |
acters | -0.027 |
amaz | -0.027 |
Token | signs |
Token ID | 5895 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
subt | +0.086 |
RAY | +0.080 |
summed | +0.073 |
ople | +0.073 |
hess | +0.072 |
Neg logit contributions | |
eming | -0.089 |
quart | -0.085 |
lett | -0.084 |
acters | -0.082 |
antics | -0.081 |
Token | of |
Token ID | 286 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
eming | +0.073 |
quart | +0.070 |
lett | +0.069 |
acters | +0.066 |
antics | +0.066 |
Neg logit contributions | |
subt | -0.064 |
RAY | -0.059 |
ople | -0.054 |
summed | -0.053 |
ial | -0.053 |
Token | security |
Token ID | 2324 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
acters | +0.003 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
summed | -0.002 |
ople | -0.002 |
ial | -0.002 |
Token | pre |
Token ID | 662 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
subt | +0.052 |
RAY | +0.049 |
summed | +0.044 |
ople | +0.044 |
ial | +0.044 |
Neg logit contributions | |
eming | -0.058 |
quart | -0.056 |
lett | -0.055 |
acters | -0.053 |
antics | -0.053 |
Token | ps |
Token ID | 862 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
subt | +0.060 |
RAY | +0.056 |
summed | +0.051 |
ople | +0.051 |
ial | +0.050 |
Neg logit contributions | |
eming | -0.058 |
quart | -0.055 |
lett | -0.054 |
acters | -0.052 |
antics | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
eming | +0.385 |
quart | +0.367 |
lett | +0.364 |
acters | +0.351 |
antics | +0.348 |
Neg logit contributions | |
subt | -0.338 |
RAY | -0.314 |
summed | -0.284 |
ople | -0.282 |
ial | -0.278 |
Token | Police |
Token ID | 4287 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
subt | +0.008 |
RAY | +0.008 |
summed | +0.007 |
ople | +0.007 |
ial | +0.007 |
Neg logit contributions | |
eming | -0.008 |
quart | -0.008 |
lett | -0.008 |
acters | -0.008 |
antics | -0.008 |
Token | chief |
Token ID | 4039 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
eming | +0.062 |
quart | +0.060 |
lett | +0.059 |
acters | +0.057 |
antics | +0.057 |
Neg logit contributions | |
subt | -0.054 |
RAY | -0.051 |
ople | -0.046 |
summed | -0.046 |
hess | -0.045 |
Token | BS |
Token ID | 24218 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
subt | +0.049 |
RAY | +0.046 |
ople | +0.042 |
summed | +0.042 |
hess | +0.041 |
Neg logit contributions | |
eming | -0.049 |
quart | -0.047 |
lett | -0.046 |
acters | -0.045 |
antics | -0.044 |
Token | Bass |
Token ID | 19829 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
eming | +0.076 |
quart | +0.072 |
lett | +0.072 |
acters | +0.069 |
antics | +0.069 |
Neg logit contributions | |
subt | -0.079 |
RAY | -0.074 |
ople | -0.067 |
summed | -0.067 |
ial | -0.067 |
Token | mayor |
Token ID | 9591 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
eming | +0.004 |
quart | +0.004 |
lett | +0.004 |
acters | +0.004 |
antics | +0.004 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.003 |
ople | -0.003 |
summed | -0.003 |
ial | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
subt | +0.030 |
RAY | +0.028 |
ople | +0.026 |
summed | +0.025 |
hess | +0.025 |
Neg logit contributions | |
eming | -0.033 |
quart | -0.032 |
lett | -0.032 |
acters | -0.031 |
antics | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.015 |
lett | +0.015 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.014 |
RAY | -0.013 |
ople | -0.012 |
summed | -0.012 |
hess | -0.012 |
Token | drawing |
Token ID | 8263 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.014 |
lett | +0.014 |
acters | +0.013 |
antics | +0.013 |
Neg logit contributions | |
subt | -0.014 |
RAY | -0.013 |
ople | -0.012 |
summed | -0.012 |
ial | -0.012 |
Token | gas |
Token ID | 3623 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
eming | +0.017 |
lett | +0.016 |
quart | +0.016 |
acters | +0.015 |
amaz | +0.015 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.012 |
ople | -0.011 |
summed | -0.011 |
hess | -0.011 |
Token | ps |
Token ID | 862 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
subt | +0.133 |
RAY | +0.128 |
ople | +0.122 |
summed | +0.122 |
ial | +0.121 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.019 |
lett | -0.018 |
acters | -0.016 |
antics | -0.015 |
Token | from |
Token ID | 422 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
eming | +0.429 |
quart | +0.412 |
lett | +0.409 |
acters | +0.396 |
antics | +0.393 |
Neg logit contributions | |
subt | -0.288 |
RAY | -0.266 |
ople | -0.236 |
summed | -0.234 |
hess | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
subt | +0.075 |
RAY | +0.070 |
summed | +0.063 |
ople | +0.063 |
ial | +0.063 |
Neg logit contributions | |
eming | -0.078 |
quart | -0.075 |
lett | -0.074 |
acters | -0.071 |
antics | -0.071 |
Token | press |
Token ID | 1803 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
eming | +0.019 |
quart | +0.018 |
lett | +0.018 |
acters | +0.017 |
antics | +0.017 |
Neg logit contributions | |
subt | -0.012 |
RAY | -0.012 |
summed | -0.010 |
ople | -0.010 |
ial | -0.010 |
Token | corps |
Token ID | 16812 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
subt | +0.096 |
RAY | +0.090 |
ople | +0.081 |
summed | +0.081 |
ial | +0.080 |
Neg logit contributions | |
eming | -0.112 |
quart | -0.107 |
lett | -0.106 |
acters | -0.102 |
antics | -0.102 |
Token | at |
Token ID | 379 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
subt | +0.040 |
RAY | +0.037 |
ople | +0.034 |
summed | +0.034 |
ial | +0.033 |
Neg logit contributions | |
eming | -0.047 |
quart | -0.045 |
lett | -0.044 |
acters | -0.043 |
antics | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
subt | +0.011 |
RAY | +0.010 |
ople | +0.009 |
summed | +0.009 |
ial | +0.009 |
Neg logit contributions | |
eming | -0.014 |
quart | -0.013 |
lett | -0.013 |
acters | -0.012 |
antics | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
eming | +0.051 |
quart | +0.049 |
lett | +0.048 |
acters | +0.046 |
antics | +0.046 |
Neg logit contributions | |
subt | -0.053 |
RAY | -0.049 |
summed | -0.045 |
ople | -0.045 |
ial | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
eming | +0.043 |
quart | +0.041 |
lett | +0.041 |
acters | +0.040 |
antics | +0.039 |
Neg logit contributions | |
subt | -0.030 |
RAY | -0.028 |
ople | -0.025 |
describ | -0.025 |
summed | -0.025 |
Token | Facebook |
Token ID | 12025 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
eming | +0.045 |
quart | +0.043 |
lett | +0.043 |
acters | +0.041 |
antics | +0.041 |
Neg logit contributions | |
subt | -0.052 |
RAY | -0.048 |
summed | -0.045 |
ople | -0.044 |
ial | -0.044 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
subt | +0.094 |
RAY | +0.087 |
summed | +0.081 |
ople | +0.080 |
ial | +0.080 |
Neg logit contributions | |
eming | -0.087 |
quart | -0.083 |
lett | -0.081 |
acters | -0.078 |
antics | -0.078 |
Token | Pinterest |
Token ID | 17334 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
eming | +0.054 |
quart | +0.048 |
lett | +0.046 |
acters | +0.042 |
antics | +0.041 |
Neg logit contributions | |
subt | -0.221 |
RAY | -0.212 |
ople | -0.201 |
summed | -0.201 |
ial | -0.199 |
Token | Lake |
Token ID | 6233 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
eming | +0.345 |
quart | +0.329 |
lett | +0.325 |
acters | +0.314 |
antics | +0.311 |
Neg logit contributions | |
subt | -0.366 |
RAY | -0.342 |
summed | -0.314 |
ople | -0.313 |
ial | -0.310 |
Token | Ur |
Token ID | 8799 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
eming | +0.110 |
quart | +0.105 |
lett | +0.103 |
acters | +0.100 |
antics | +0.099 |
Neg logit contributions | |
subt | -0.138 |
RAY | -0.129 |
ople | -0.119 |
summed | -0.119 |
ial | -0.118 |
Token | mia |
Token ID | 20730 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
eming | +0.091 |
quart | +0.084 |
lett | +0.083 |
acters | +0.078 |
antics | +0.077 |
Neg logit contributions | |
subt | -0.196 |
RAY | -0.186 |
summed | -0.175 |
ople | -0.175 |
ial | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
eming | +0.148 |
quart | +0.142 |
lett | +0.140 |
acters | +0.136 |
antics | +0.135 |
Neg logit contributions | |
subt | -0.125 |
RAY | -0.116 |
ople | -0.105 |
summed | -0.105 |
ial | -0.103 |
Token | Iran |
Token ID | 4068 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
eming | +0.035 |
quart | +0.034 |
lett | +0.033 |
acters | +0.032 |
ulence | +0.032 |
Neg logit contributions | |
subt | -0.031 |
RAY | -0.029 |
ople | -0.026 |
summed | -0.026 |
ial | -0.026 |
Token | expelled |
Token ID | 27307 |
Feature activation | -8.69e-02 |
Pos logit contributions | |
eming | +0.026 |
quart | +0.025 |
lett | +0.024 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.023 |
ople | -0.021 |
summed | -0.021 |
ial | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
eming | +0.068 |
quart | +0.065 |
lett | +0.064 |
acters | +0.062 |
antics | +0.062 |
Neg logit contributions | |
subt | -0.049 |
RAY | -0.046 |
ople | -0.041 |
summed | -0.041 |
ertain | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.027 |
lett | +0.027 |
acters | +0.026 |
antics | +0.026 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.021 |
summed | -0.019 |
ople | -0.019 |
ial | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
describ | +0.010 |
summed | +0.010 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.017 |
lett | -0.017 |
acters | -0.016 |
antics | -0.016 |
Token | S |
Token ID | 50 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
summed | +0.002 |
ople | +0.002 |
hess | +0.002 |
Neg logit contributions | |
eming | -0.002 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | por |
Token ID | 1819 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
eming | +0.026 |
quart | +0.025 |
lett | +0.024 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.034 |
summed | -0.032 |
ople | -0.032 |
hess | -0.031 |
Token | adic |
Token ID | 23876 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
eming | +0.251 |
quart | +0.235 |
lett | +0.231 |
acters | +0.220 |
antics | +0.217 |
Neg logit contributions | |
subt | -0.460 |
RAY | -0.436 |
summed | -0.408 |
ople | -0.408 |
ial | -0.404 |
Token | gunfire |
Token ID | 29276 |
Feature activation | -8.55e-03 |
Pos logit contributions | |
eming | +0.148 |
quart | +0.143 |
lett | +0.142 |
acters | +0.137 |
ulence | +0.136 |
Neg logit contributions | |
subt | -0.104 |
RAY | -0.096 |
ople | -0.086 |
summed | -0.085 |
hess | -0.084 |
Token | rocked |
Token ID | 36872 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
eming | +0.006 |
quart | +0.005 |
lett | +0.005 |
acters | +0.005 |
antics | +0.005 |
Neg logit contributions | |
subt | -0.006 |
RAY | -0.006 |
ople | -0.005 |
summed | -0.005 |
hess | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
eming | +0.109 |
quart | +0.104 |
lett | +0.103 |
acters | +0.100 |
antics | +0.099 |
Neg logit contributions | |
subt | -0.107 |
RAY | -0.100 |
summed | -0.091 |
ople | -0.091 |
ial | -0.090 |
Token | new |
Token ID | 649 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
subt | +0.013 |
RAY | +0.012 |
ople | +0.010 |
summed | +0.010 |
hess | +0.010 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
antics | -0.015 |
Token | find |
Token ID | 1064 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
subt | +0.059 |
RAY | +0.055 |
ople | +0.049 |
summed | +0.049 |
hess | +0.049 |
Neg logit contributions | |
eming | -0.078 |
quart | -0.074 |
lett | -0.074 |
acters | -0.072 |
antics | -0.071 |
Token | all |
Token ID | 477 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
subt | +0.027 |
RAY | +0.025 |
ople | +0.023 |
summed | +0.023 |
hess | +0.023 |
Neg logit contributions | |
eming | -0.029 |
lett | -0.027 |
quart | -0.027 |
acters | -0.026 |
antics | -0.026 |
Token | kinds |
Token ID | 6982 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
eming | +0.096 |
quart | +0.092 |
lett | +0.091 |
acters | +0.088 |
antics | +0.087 |
Neg logit contributions | |
subt | -0.099 |
RAY | -0.092 |
summed | -0.085 |
ople | -0.084 |
ial | -0.084 |
Token | of |
Token ID | 286 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
eming | +0.079 |
quart | +0.075 |
lett | +0.074 |
acters | +0.071 |
antics | +0.071 |
Neg logit contributions | |
subt | -0.087 |
RAY | -0.083 |
ople | -0.076 |
summed | -0.075 |
hess | -0.074 |
Token | crack |
Token ID | 8469 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
eming | +0.022 |
lett | +0.021 |
quart | +0.021 |
acters | +0.020 |
antics | +0.020 |
Neg logit contributions | |
subt | -0.017 |
RAY | -0.016 |
ople | -0.015 |
summed | -0.014 |
hess | -0.014 |
Token | pots |
Token ID | 40793 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
subt | +0.071 |
RAY | +0.068 |
ople | +0.064 |
summed | +0.064 |
ial | +0.064 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.021 |
lett | -0.021 |
acters | -0.020 |
antics | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
eming | +0.390 |
quart | +0.372 |
lett | +0.370 |
acters | +0.358 |
antics | +0.356 |
Neg logit contributions | |
subt | -0.317 |
RAY | -0.298 |
ople | -0.268 |
summed | -0.265 |
hess | -0.264 |
Token | social |
Token ID | 1919 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
eming | +0.016 |
quart | +0.015 |
lett | +0.015 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.017 |
RAY | -0.016 |
summed | -0.014 |
ople | -0.014 |
ial | -0.014 |
Token | media |
Token ID | 2056 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
eming | +0.126 |
quart | +0.122 |
lett | +0.121 |
acters | +0.118 |
antics | +0.117 |
Neg logit contributions | |
subt | -0.056 |
RAY | -0.050 |
summed | -0.043 |
ople | -0.043 |
ial | -0.042 |
Token | making |
Token ID | 1642 |
Feature activation | -8.66e-02 |
Pos logit contributions | |
subt | +0.108 |
RAY | +0.101 |
ople | +0.092 |
summed | +0.091 |
hess | +0.090 |
Neg logit contributions | |
eming | -0.127 |
quart | -0.121 |
lett | -0.121 |
acters | -0.117 |
antics | -0.116 |
Token | insane |
Token ID | 13251 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
eming | +0.060 |
quart | +0.057 |
lett | +0.057 |
acters | +0.055 |
antics | +0.054 |
Neg logit contributions | |
subt | -0.056 |
RAY | -0.053 |
ople | -0.048 |
summed | -0.048 |
ial | -0.048 |
Token | ews |
Token ID | 15515 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
eming | +0.136 |
quart | +0.131 |
lett | +0.130 |
acters | +0.125 |
antics | +0.125 |
Neg logit contributions | |
subt | -0.109 |
RAY | -0.100 |
summed | -0.090 |
ople | -0.090 |
hess | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
subt | +0.245 |
RAY | +0.227 |
ople | +0.206 |
summed | +0.205 |
ial | +0.203 |
Neg logit contributions | |
eming | -0.289 |
quart | -0.276 |
lett | -0.274 |
acters | -0.265 |
antics | -0.263 |
Token | grains |
Token ID | 21824 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
eming | +0.002 |
quart | +0.002 |
lett | +0.002 |
acters | +0.002 |
antics | +0.002 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.001 |
summed | -0.001 |
ople | -0.001 |
ial | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
eming | +0.146 |
quart | +0.140 |
lett | +0.138 |
acters | +0.135 |
antics | +0.134 |
Neg logit contributions | |
subt | -0.110 |
RAY | -0.101 |
summed | -0.091 |
ople | -0.091 |
ial | -0.090 |
Token | sou |
Token ID | 24049 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
eming | +0.014 |
quart | +0.013 |
lett | +0.013 |
acters | +0.012 |
antics | +0.012 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
ial | -0.009 |
Token | ps |
Token ID | 862 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.009 |
lett | +0.009 |
antics | +0.007 |
acters | +0.007 |
Neg logit contributions | |
subt | -0.067 |
RAY | -0.064 |
ople | -0.062 |
hess | -0.061 |
ial | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
eming | +0.398 |
quart | +0.382 |
lett | +0.379 |
acters | +0.367 |
antics | +0.364 |
Neg logit contributions | |
subt | -0.306 |
RAY | -0.284 |
ople | -0.255 |
summed | -0.254 |
ial | -0.250 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
eming | +0.004 |
quart | +0.004 |
lett | +0.004 |
acters | +0.004 |
antics | +0.004 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.003 |
summed | -0.003 |
ople | -0.003 |
ial | -0.003 |
Token | beans |
Token ID | 16567 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
summed | +0.012 |
ople | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-03 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
summed | +0.012 |
ople | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | The |
Token ID | 383 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
subt | +0.001 |
RAY | +0.001 |
ople | +0.001 |
summed | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | est |
Token ID | 395 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
eming | +0.209 |
quart | +0.203 |
lett | +0.199 |
acters | +0.196 |
antics | +0.196 |
Neg logit contributions | |
subt | -0.119 |
RAY | -0.107 |
ial | -0.096 |
ople | -0.095 |
summed | -0.094 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
subt | +0.249 |
RAY | +0.237 |
ople | +0.224 |
summed | +0.223 |
ial | +0.223 |
Neg logit contributions | |
eming | -0.102 |
quart | -0.095 |
lett | -0.092 |
acters | -0.086 |
antics | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
eming | +0.112 |
quart | +0.108 |
lett | +0.106 |
acters | +0.103 |
antics | +0.103 |
Neg logit contributions | |
subt | -0.087 |
RAY | -0.080 |
summed | -0.072 |
ople | -0.072 |
ial | -0.071 |
Token | digital |
Token ID | 4875 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
summed | +0.010 |
ople | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.014 |
quart | -0.014 |
lett | -0.014 |
acters | -0.013 |
antics | -0.013 |
Token | hots |
Token ID | 33915 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
eming | +0.007 |
quart | +0.007 |
lett | +0.006 |
acters | +0.006 |
antics | +0.006 |
Neg logit contributions | |
subt | -0.006 |
RAY | -0.006 |
summed | -0.005 |
ople | -0.005 |
ial | -0.005 |
Token | pots |
Token ID | 40793 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
ulence | +0.002 |
acters | +0.002 |
Neg logit contributions | |
subt | -0.027 |
RAY | -0.026 |
ople | -0.025 |
summed | -0.025 |
ial | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
eming | +0.377 |
quart | +0.361 |
lett | +0.357 |
acters | +0.346 |
antics | +0.344 |
Neg logit contributions | |
subt | -0.326 |
RAY | -0.302 |
summed | -0.274 |
ople | -0.273 |
ial | -0.270 |
Token | players |
Token ID | 1938 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
eming | +0.012 |
quart | +0.012 |
lett | +0.012 |
acters | +0.011 |
antics | +0.011 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
summed | -0.009 |
ople | -0.009 |
ial | -0.009 |
Token | must |
Token ID | 1276 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
eming | +0.032 |
quart | +0.031 |
lett | +0.031 |
acters | +0.030 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.021 |
RAY | -0.019 |
ople | -0.017 |
summed | -0.017 |
ial | -0.017 |
Token | visit |
Token ID | 3187 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
subt | +0.046 |
RAY | +0.043 |
summed | +0.039 |
ople | +0.039 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.051 |
quart | -0.049 |
lett | -0.049 |
acters | -0.047 |
antics | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
eming | +0.107 |
quart | +0.102 |
lett | +0.102 |
acters | +0.098 |
ulence | +0.097 |
Neg logit contributions | |
subt | -0.098 |
RAY | -0.092 |
ople | -0.084 |
summed | -0.083 |
ial | -0.082 |
Token | new |
Token ID | 649 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
eming | +0.027 |
quart | +0.026 |
lett | +0.026 |
acters | +0.025 |
antics | +0.025 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.022 |
ople | -0.020 |
summed | -0.020 |
ial | -0.020 |
Token | rule |
Token ID | 3896 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
eming | +0.026 |
quart | +0.025 |
lett | +0.024 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.023 |
ople | -0.020 |
summed | -0.020 |
ial | -0.020 |
Token | book |
Token ID | 2070 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
eming | +0.038 |
quart | +0.036 |
lett | +0.035 |
acters | +0.034 |
antics | +0.034 |
Neg logit contributions | |
subt | -0.032 |
RAY | -0.030 |
ople | -0.027 |
summed | -0.027 |
ial | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
subt | +0.061 |
RAY | +0.057 |
ople | +0.052 |
summed | +0.051 |
ial | +0.051 |
Neg logit contributions | |
eming | -0.073 |
quart | -0.070 |
lett | -0.069 |
acters | -0.067 |
antics | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
eming | +0.031 |
quart | +0.030 |
lett | +0.030 |
acters | +0.029 |
antics | +0.029 |
Neg logit contributions | |
subt | -0.025 |
RAY | -0.024 |
ople | -0.021 |
summed | -0.021 |
ial | -0.021 |
Token | Lisbon |
Token ID | 41898 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
eming | +0.013 |
quart | +0.012 |
lett | +0.012 |
acters | +0.011 |
antics | +0.011 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.011 |
ople | -0.010 |
summed | -0.010 |
ial | -0.010 |
Token | treaty |
Token ID | 15775 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
eming | +0.280 |
quart | +0.264 |
lett | +0.261 |
acters | +0.247 |
antics | +0.247 |
Neg logit contributions | |
subt | -0.420 |
RAY | -0.398 |
ople | -0.369 |
summed | -0.368 |
ial | -0.365 |
Token | , |
Token ID | 11 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
eming | +0.141 |
quart | +0.135 |
lett | +0.134 |
acters | +0.129 |
antics | +0.129 |
Neg logit contributions | |
subt | -0.116 |
RAY | -0.108 |
ople | -0.097 |
summed | -0.097 |
ial | -0.096 |
Token | which |
Token ID | 543 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
eming | +0.055 |
quart | +0.052 |
lett | +0.052 |
acters | +0.050 |
antics | +0.050 |
Neg logit contributions | |
subt | -0.041 |
RAY | -0.039 |
ople | -0.035 |
summed | -0.034 |
ial | -0.034 |
Token | entered |
Token ID | 5982 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
subt | +0.074 |
RAY | +0.070 |
ople | +0.063 |
summed | +0.062 |
ial | +0.062 |
Neg logit contributions | |
eming | -0.085 |
quart | -0.081 |
lett | -0.080 |
acters | -0.077 |
antics | -0.077 |
Token | into |
Token ID | 656 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
eming | +0.088 |
quart | +0.084 |
lett | +0.083 |
acters | +0.079 |
antics | +0.078 |
Neg logit contributions | |
subt | -0.106 |
RAY | -0.100 |
ople | -0.092 |
summed | -0.092 |
ial | -0.090 |
Token | Oklahoma |
Token ID | 10433 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
eming | +0.057 |
quart | +0.054 |
lett | +0.054 |
acters | +0.052 |
antics | +0.052 |
Neg logit contributions | |
subt | -0.052 |
RAY | -0.048 |
ople | -0.044 |
summed | -0.044 |
hess | -0.043 |
Token | residents |
Token ID | 5085 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
eming | +0.156 |
quart | +0.150 |
lett | +0.148 |
acters | +0.143 |
antics | +0.142 |
Neg logit contributions | |
subt | -0.139 |
RAY | -0.129 |
ople | -0.117 |
summed | -0.117 |
ial | -0.115 |
Token | impacted |
Token ID | 20755 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
eming | +0.019 |
quart | +0.019 |
lett | +0.018 |
acters | +0.018 |
antics | +0.018 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.012 |
ople | -0.011 |
summed | -0.011 |
hess | -0.010 |
Token | by |
Token ID | 416 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.014 |
summed | +0.013 |
ial | +0.013 |
ople | +0.013 |
Neg logit contributions | |
eming | -0.013 |
quart | -0.012 |
lett | -0.012 |
acters | -0.012 |
antics | -0.012 |
Token | sw |
Token ID | 1509 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
eming | +0.051 |
quart | +0.049 |
lett | +0.048 |
acters | +0.047 |
antics | +0.046 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
ople | -0.043 |
summed | -0.043 |
ial | -0.043 |
Token | arms |
Token ID | 8357 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
eming | +0.009 |
quart | +0.008 |
lett | +0.008 |
acters | +0.008 |
ulence | +0.008 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ial | -0.009 |
ople | -0.009 |
summed | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +7.09e-03 |
Pos logit contributions | |
eming | +0.348 |
quart | +0.333 |
lett | +0.329 |
acters | +0.319 |
antics | +0.318 |
Neg logit contributions | |
subt | -0.341 |
RAY | -0.314 |
summed | -0.290 |
ial | -0.288 |
ople | -0.288 |
Token | fracking |
Token ID | 25441 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
subt | +0.004 |
RAY | +0.004 |
ople | +0.004 |
summed | +0.004 |
ial | +0.004 |
Neg logit contributions | |
eming | -0.005 |
quart | -0.005 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
eming | +0.154 |
quart | +0.147 |
lett | +0.146 |
acters | +0.141 |
antics | +0.140 |
Neg logit contributions | |
subt | -0.136 |
RAY | -0.126 |
summed | -0.114 |
ople | -0.114 |
ial | -0.113 |
Token | induced |
Token ID | 17223 |
Feature activation | +4.31e-04 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.010 |
lett | +0.010 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
ial | -0.009 |
Token | earthquakes |
Token ID | 29781 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
subt | +0.000 |
RAY | +0.000 |
summed | +0.000 |
ople | +0.000 |
ial | +0.000 |
Neg logit contributions | |
eming | -0.000 |
quart | -0.000 |
lett | -0.000 |
acters | -0.000 |
antics | -0.000 |
Token | ised |
Token ID | 1417 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.029 |
summed | +0.025 |
ople | +0.025 |
hess | +0.024 |
Neg logit contributions | |
eming | -0.061 |
lett | -0.058 |
quart | -0.058 |
acters | -0.056 |
antics | -0.056 |
Token | Wi |
Token ID | 11759 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
subt | +0.118 |
RAY | +0.110 |
ople | +0.100 |
summed | +0.099 |
ial | +0.098 |
Neg logit contributions | |
eming | -0.139 |
quart | -0.132 |
lett | -0.131 |
acters | -0.127 |
antics | -0.126 |
Token | - |
Token ID | 12 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
eming | +0.047 |
quart | +0.045 |
lett | +0.044 |
acters | +0.043 |
antics | +0.042 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.047 |
summed | -0.043 |
ople | -0.043 |
ial | -0.042 |
Token | Fi |
Token ID | 10547 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
eming | +0.004 |
quart | +0.004 |
lett | +0.004 |
acters | +0.004 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.003 |
summed | -0.003 |
ople | -0.003 |
ial | -0.002 |
Token | hots |
Token ID | 33915 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
subt | +0.005 |
RAY | +0.005 |
ople | +0.004 |
summed | +0.004 |
ial | +0.004 |
Neg logit contributions | |
eming | -0.006 |
quart | -0.005 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | pots |
Token ID | 40793 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
eming | +0.360 |
quart | +0.344 |
lett | +0.341 |
acters | +0.330 |
antics | +0.326 |
Neg logit contributions | |
subt | -0.317 |
RAY | -0.299 |
ople | -0.270 |
summed | -0.267 |
ial | -0.264 |
Token | big |
Token ID | 1263 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.028 |
lett | +0.028 |
acters | +0.027 |
ulence | +0.027 |
Neg logit contributions | |
subt | -0.027 |
RAY | -0.025 |
ople | -0.023 |
summed | -0.023 |
hess | -0.022 |
Token | red |
Token ID | 2266 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
eming | +0.041 |
quart | +0.039 |
lett | +0.039 |
acters | +0.037 |
antics | +0.037 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.034 |
ople | -0.031 |
summed | -0.031 |
ial | -0.030 |
Token | detectors |
Token ID | 40471 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
eming | +0.111 |
quart | +0.106 |
lett | +0.105 |
acters | +0.102 |
antics | +0.101 |
Neg logit contributions | |
subt | -0.116 |
RAY | -0.109 |
summed | -0.100 |
ople | -0.100 |
ial | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -8.00e-02 |
Pos logit contributions | |
subt | +0.110 |
RAY | +0.103 |
ople | +0.093 |
summed | +0.093 |
ial | +0.092 |
Neg logit contributions | |
eming | -0.130 |
quart | -0.124 |
lett | -0.123 |
acters | -0.119 |
antics | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
eming | +0.022 |
quart | +0.021 |
lett | +0.021 |
acters | +0.021 |
antics | +0.020 |
Neg logit contributions | |
subt | -0.016 |
RAY | -0.014 |
ople | -0.013 |
summed | -0.013 |
describ | -0.013 |
Token | K |
Token ID | 42 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.027 |
lett | +0.027 |
acters | +0.026 |
antics | +0.025 |
Neg logit contributions | |
subt | -0.032 |
RAY | -0.030 |
summed | -0.028 |
ople | -0.028 |
ial | -0.028 |
Token | irk |
Token ID | 14232 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
eming | +0.045 |
quart | +0.043 |
lett | +0.043 |
acters | +0.041 |
antics | +0.041 |
Neg logit contributions | |
subt | -0.049 |
RAY | -0.046 |
ople | -0.042 |
summed | -0.042 |
ial | -0.042 |
Token | Cousins |
Token ID | 32644 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
eming | +0.053 |
quart | +0.050 |
lett | +0.049 |
acters | +0.047 |
antics | +0.047 |
Neg logit contributions | |
subt | -0.061 |
RAY | -0.057 |
summed | -0.053 |
ople | -0.052 |
ial | -0.052 |
Token | ( |
Token ID | 357 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
eming | +0.066 |
quart | +0.063 |
lett | +0.062 |
acters | +0.061 |
antics | +0.061 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.033 |
summed | -0.029 |
ople | -0.029 |
ial | -0.028 |
Token | vs |
Token ID | 14259 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
subt | +0.043 |
RAY | +0.042 |
ople | +0.039 |
summed | +0.039 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.015 |
lett | -0.015 |
acters | -0.014 |
ulence | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-04 |
Pos logit contributions | |
eming | +0.351 |
quart | +0.335 |
lett | +0.331 |
acters | +0.321 |
antics | +0.319 |
Neg logit contributions | |
subt | -0.329 |
RAY | -0.307 |
summed | -0.279 |
ople | -0.278 |
ial | -0.276 |
Token | BU |
Token ID | 20571 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
eming | +0.000 |
quart | +0.000 |
lett | +0.000 |
acters | +0.000 |
antics | +0.000 |
Neg logit contributions | |
subt | -0.000 |
RAY | -0.000 |
summed | -0.000 |
ople | -0.000 |
ial | -0.000 |
Token | F |
Token ID | 37 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
eming | +0.014 |
lett | +0.014 |
quart | +0.014 |
acters | +0.013 |
antics | +0.013 |
Neg logit contributions | |
subt | -0.015 |
RAY | -0.014 |
ople | -0.013 |
summed | -0.013 |
hess | -0.013 |
Token | ): |
Token ID | 2599 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
subt | +0.051 |
RAY | +0.047 |
summed | +0.042 |
ople | +0.042 |
ial | +0.041 |
Neg logit contributions | |
eming | -0.070 |
quart | -0.067 |
lett | -0.067 |
acters | -0.065 |
antics | -0.064 |
Token | He |
Token ID | 679 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
subt | +0.055 |
RAY | +0.052 |
summed | +0.048 |
ople | +0.047 |
ial | +0.047 |
Neg logit contributions | |
eming | -0.050 |
quart | -0.047 |
lett | -0.047 |
acters | -0.045 |
antics | -0.045 |
Token | it |
Token ID | 340 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
subt | +0.058 |
RAY | +0.054 |
summed | +0.049 |
ople | +0.049 |
ial | +0.049 |
Neg logit contributions | |
eming | -0.067 |
quart | -0.064 |
lett | -0.063 |
acters | -0.061 |
antics | -0.061 |
Token | through |
Token ID | 832 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.022 |
ople | +0.020 |
summed | +0.020 |
ial | +0.020 |
Neg logit contributions | |
eming | -0.026 |
quart | -0.025 |
lett | -0.024 |
acters | -0.024 |
antics | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
eming | +0.054 |
quart | +0.051 |
lett | +0.051 |
acters | +0.049 |
antics | +0.049 |
Neg logit contributions | |
subt | -0.049 |
RAY | -0.046 |
ople | -0.042 |
summed | -0.042 |
ial | -0.041 |
Token | w |
Token ID | 266 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
eming | +0.031 |
quart | +0.030 |
lett | +0.030 |
acters | +0.029 |
antics | +0.029 |
Neg logit contributions | |
subt | -0.025 |
RAY | -0.024 |
ople | -0.021 |
summed | -0.021 |
ial | -0.021 |
Token | is |
Token ID | 271 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
subt | +0.054 |
RAY | +0.051 |
summed | +0.047 |
ople | +0.047 |
ial | +0.046 |
Neg logit contributions | |
eming | -0.041 |
quart | -0.039 |
lett | -0.039 |
acters | -0.037 |
antics | -0.037 |
Token | ps |
Token ID | 862 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
ople | +0.017 |
ial | +0.017 |
summed | +0.017 |
Neg logit contributions | |
eming | -0.003 |
quart | -0.003 |
lett | -0.003 |
acters | -0.002 |
antics | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
eming | +0.365 |
quart | +0.349 |
lett | +0.346 |
acters | +0.335 |
antics | +0.332 |
Neg logit contributions | |
subt | -0.312 |
RAY | -0.290 |
summed | -0.262 |
ople | -0.262 |
ial | -0.259 |
Token | air |
Token ID | 1633 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.029 |
lett | +0.029 |
acters | +0.027 |
antics | +0.027 |
Neg logit contributions | |
subt | -0.025 |
RAY | -0.023 |
ople | -0.021 |
summed | -0.021 |
ial | -0.021 |
Token | just |
Token ID | 655 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
subt | +0.028 |
RAY | +0.026 |
ople | +0.023 |
summed | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.037 |
quart | -0.035 |
lett | -0.035 |
acters | -0.034 |
antics | -0.034 |
Token | 224 |
Token ID | 26063 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
eming | +0.067 |
lett | +0.064 |
quart | +0.064 |
acters | +0.061 |
ulence | +0.061 |
Neg logit contributions | |
subt | -0.058 |
RAY | -0.055 |
ople | -0.049 |
summed | -0.049 |
ertain | -0.048 |
Token | km |
Token ID | 13276 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
subt | +0.062 |
RAY | +0.058 |
ople | +0.054 |
summed | +0.054 |
ial | +0.053 |
Neg logit contributions | |
eming | -0.046 |
quart | -0.044 |
lett | -0.043 |
acters | -0.042 |
antics | -0.041 |
Token | that |
Token ID | 326 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.011 |
lett | +0.010 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.012 |
RAY | -0.011 |
ople | -0.010 |
summed | -0.010 |
ial | -0.010 |
Token | most |
Token ID | 749 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
eming | +0.020 |
quart | +0.019 |
lett | +0.019 |
acters | +0.018 |
antics | +0.018 |
Neg logit contributions | |
subt | -0.020 |
RAY | -0.018 |
ople | -0.017 |
summed | -0.017 |
ial | -0.017 |
Token | celebrities |
Token ID | 21305 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
eming | +0.137 |
quart | +0.131 |
lett | +0.131 |
acters | +0.126 |
antics | +0.125 |
Neg logit contributions | |
subt | -0.122 |
RAY | -0.115 |
ople | -0.104 |
summed | -0.104 |
hess | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
eming | +0.148 |
quart | +0.142 |
lett | +0.141 |
acters | +0.136 |
antics | +0.135 |
Neg logit contributions | |
subt | -0.127 |
RAY | -0.119 |
ople | -0.108 |
summed | -0.107 |
hess | -0.106 |
Token | public |
Token ID | 1171 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.014 |
ople | +0.013 |
summed | +0.013 |
ial | +0.013 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.018 |
lett | -0.018 |
acters | -0.017 |
antics | -0.017 |
Token | figures |
Token ID | 5538 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
eming | +0.036 |
quart | +0.033 |
lett | +0.033 |
acters | +0.031 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.093 |
RAY | -0.089 |
summed | -0.084 |
ople | -0.083 |
ial | -0.083 |
Token | have |
Token ID | 423 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
eming | +0.349 |
quart | +0.333 |
lett | +0.333 |
acters | +0.319 |
antics | +0.317 |
Neg logit contributions | |
subt | -0.316 |
RAY | -0.297 |
ople | -0.269 |
hess | -0.266 |
summed | -0.265 |
Token | social |
Token ID | 1919 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
eming | +0.047 |
lett | +0.045 |
quart | +0.045 |
acters | +0.044 |
antics | +0.043 |
Neg logit contributions | |
subt | -0.042 |
RAY | -0.039 |
ople | -0.036 |
summed | -0.035 |
hess | -0.035 |
Token | media |
Token ID | 2056 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
eming | +0.144 |
quart | +0.139 |
lett | +0.138 |
acters | +0.135 |
antics | +0.134 |
Neg logit contributions | |
subt | -0.068 |
RAY | -0.061 |
ople | -0.053 |
summed | -0.053 |
ial | -0.052 |
Token | managers |
Token ID | 11663 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
subt | +0.122 |
RAY | +0.114 |
ople | +0.104 |
summed | +0.103 |
ial | +0.102 |
Neg logit contributions | |
eming | -0.132 |
quart | -0.126 |
lett | -0.124 |
acters | -0.121 |
antics | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
ople | +0.016 |
summed | +0.016 |
hess | +0.016 |
Neg logit contributions | |
eming | -0.022 |
quart | -0.021 |
lett | -0.021 |
acters | -0.020 |
antics | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
eming | +0.022 |
quart | +0.021 |
lett | +0.021 |
acters | +0.020 |
antics | +0.020 |
Neg logit contributions | |
subt | -0.018 |
RAY | -0.016 |
ople | -0.015 |
summed | -0.015 |
ial | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
eming | +0.012 |
quart | +0.011 |
lett | +0.011 |
acters | +0.011 |
antics | +0.011 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.009 |
ople | -0.009 |
summed | -0.008 |
ial | -0.008 |
Token | number |
Token ID | 1271 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.012 |
ial | +0.011 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.015 |
antics | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
subt | +0.017 |
RAY | +0.016 |
ople | +0.015 |
summed | +0.015 |
ial | +0.015 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.016 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | conservative |
Token ID | 5940 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
eming | +0.009 |
quart | +0.008 |
lett | +0.008 |
acters | +0.008 |
antics | +0.008 |
Neg logit contributions | |
subt | -0.007 |
RAY | -0.006 |
summed | -0.006 |
ople | -0.006 |
hess | -0.006 |
Token | figures |
Token ID | 5538 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
eming | +0.054 |
quart | +0.051 |
lett | +0.051 |
acters | +0.049 |
antics | +0.049 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
summed | -0.044 |
ople | -0.043 |
ial | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
eming | +0.363 |
quart | +0.348 |
lett | +0.344 |
acters | +0.333 |
antics | +0.331 |
Neg logit contributions | |
subt | -0.305 |
RAY | -0.283 |
ople | -0.256 |
summed | -0.255 |
ial | -0.252 |
Token | including |
Token ID | 1390 |
Feature activation | +9.72e-02 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.010 |
ople | -0.008 |
summed | -0.008 |
ial | -0.008 |
Token | Iran |
Token ID | 4068 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
subt | +0.063 |
RAY | +0.059 |
ople | +0.054 |
summed | +0.054 |
ial | +0.053 |
Neg logit contributions | |
eming | -0.067 |
quart | -0.064 |
lett | -0.064 |
acters | -0.062 |
antics | -0.061 |
Token | � |
Token ID | 447 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
eming | +0.065 |
quart | +0.062 |
lett | +0.061 |
acters | +0.059 |
antics | +0.059 |
Neg logit contributions | |
subt | -0.067 |
RAY | -0.063 |
summed | -0.057 |
ople | -0.057 |
ial | -0.057 |
Token | � |
Token ID | 247 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
eming | +0.039 |
quart | +0.037 |
lett | +0.036 |
acters | +0.035 |
antics | +0.034 |
Neg logit contributions | |
subt | -0.067 |
RAY | -0.064 |
ople | -0.060 |
summed | -0.060 |
hess | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
eming | +0.033 |
quart | +0.032 |
lett | +0.032 |
acters | +0.031 |
antics | +0.030 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.021 |
ople | -0.019 |
summed | -0.019 |
describ | -0.019 |
Token | 15 |
Token ID | 1314 |
Feature activation | -7.96e-02 |
Pos logit contributions | |
eming | +0.041 |
quart | +0.038 |
lett | +0.038 |
acters | +0.037 |
ulence | +0.037 |
Neg logit contributions | |
subt | -0.044 |
RAY | -0.042 |
summed | -0.038 |
hess | -0.038 |
ople | -0.038 |
Token | ) |
Token ID | 8 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
eming | +0.056 |
quart | +0.053 |
lett | +0.053 |
acters | +0.051 |
antics | +0.050 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
summed | -0.044 |
ople | -0.044 |
ial | -0.043 |
Token | Accept |
Token ID | 21699 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
eming | +0.077 |
quart | +0.073 |
lett | +0.072 |
acters | +0.070 |
antics | +0.069 |
Neg logit contributions | |
subt | -0.080 |
RAY | -0.075 |
summed | -0.069 |
ople | -0.069 |
ial | -0.068 |
Token | Re |
Token ID | 797 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
eming | +0.025 |
quart | +0.024 |
lett | +0.024 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.025 |
RAY | -0.024 |
summed | -0.022 |
ople | -0.022 |
ial | -0.021 |
Token | jection |
Token ID | 29192 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
eming | +0.021 |
quart | +0.020 |
lett | +0.019 |
acters | +0.018 |
antics | +0.018 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.034 |
ople | -0.032 |
summed | -0.032 |
ial | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
eming | +0.353 |
quart | +0.336 |
lett | +0.334 |
acters | +0.322 |
antics | +0.320 |
Neg logit contributions | |
subt | -0.312 |
RAY | -0.292 |
summed | -0.264 |
ople | -0.264 |
ial | -0.258 |
Token | Good |
Token ID | 4599 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
eming | +0.024 |
quart | +0.023 |
lett | +0.023 |
acters | +0.022 |
antics | +0.022 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.022 |
summed | -0.020 |
ople | -0.020 |
ial | -0.020 |
Token | Grace |
Token ID | 16156 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
eming | +0.073 |
quart | +0.070 |
lett | +0.069 |
acters | +0.067 |
antics | +0.066 |
Neg logit contributions | |
subt | -0.081 |
RAY | -0.076 |
summed | -0.070 |
ople | -0.069 |
ial | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
subt | +0.152 |
RAY | +0.141 |
summed | +0.128 |
ople | +0.128 |
ial | +0.126 |
Neg logit contributions | |
eming | -0.172 |
quart | -0.164 |
lett | -0.163 |
acters | -0.157 |
antics | -0.156 |
Token |
|
Token ID | 198 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
eming | +0.043 |
quart | +0.041 |
lett | +0.041 |
acters | +0.040 |
antics | +0.039 |
Neg logit contributions | |
subt | -0.027 |
RAY | -0.025 |
summed | -0.022 |
ople | -0.022 |
ial | -0.022 |
Token | parse |
Token ID | 29572 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
subt | +0.023 |
RAY | +0.021 |
summed | +0.019 |
ople | +0.019 |
ial | +0.019 |
Neg logit contributions | |
eming | -0.028 |
quart | -0.026 |
lett | -0.026 |
acters | -0.025 |
antics | -0.025 |
Token | _ |
Token ID | 62 |
Feature activation | -9.85e-02 |
Pos logit contributions | |
subt | +0.107 |
RAY | +0.100 |
ople | +0.092 |
summed | +0.092 |
ial | +0.092 |
Neg logit contributions | |
eming | -0.089 |
quart | -0.084 |
lett | -0.083 |
acters | -0.080 |
antics | -0.079 |
Token | args |
Token ID | 22046 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
eming | +0.053 |
quart | +0.050 |
lett | +0.049 |
acters | +0.047 |
antics | +0.047 |
Neg logit contributions | |
subt | -0.080 |
RAY | -0.075 |
summed | -0.070 |
ople | -0.070 |
ial | -0.069 |
Token | ()) |
Token ID | 28955 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
eming | +0.056 |
quart | +0.053 |
lett | +0.053 |
acters | +0.051 |
antics | +0.050 |
Neg logit contributions | |
subt | -0.071 |
RAY | -0.066 |
summed | -0.061 |
ople | -0.061 |
ial | -0.061 |
Token | # |
Token ID | 1303 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
ople | +0.002 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.004 |
quart | -0.004 |
lett | -0.004 |
acters | -0.003 |
antics | -0.003 |
Token | initialize |
Token ID | 41216 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
subt | +0.025 |
RAY | +0.023 |
ople | +0.021 |
summed | +0.021 |
ial | +0.021 |
Neg logit contributions | |
eming | -0.034 |
quart | -0.033 |
lett | -0.033 |
acters | -0.032 |
antics | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
subt | +0.237 |
RAY | +0.221 |
summed | +0.201 |
ople | +0.201 |
ial | +0.199 |
Neg logit contributions | |
eming | -0.252 |
quart | -0.240 |
lett | -0.238 |
acters | -0.230 |
antics | -0.228 |
Token | rectangular |
Token ID | 36954 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
subt | +0.053 |
RAY | +0.049 |
ople | +0.044 |
summed | +0.044 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.072 |
quart | -0.069 |
lett | -0.069 |
acters | -0.067 |
antics | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
subt | +0.035 |
RAY | +0.033 |
ople | +0.030 |
summed | +0.029 |
hess | +0.029 |
Neg logit contributions | |
eming | -0.052 |
quart | -0.050 |
lett | -0.050 |
acters | -0.048 |
ulence | -0.048 |
Token | square |
Token ID | 6616 |
Feature activation | +8.20e-02 |
Pos logit contributions | |
subt | +0.054 |
RAY | +0.050 |
ople | +0.045 |
summed | +0.045 |
ial | +0.044 |
Neg logit contributions | |
eming | -0.064 |
quart | -0.062 |
lett | -0.061 |
acters | -0.059 |
antics | -0.059 |
Token | struct |
Token ID | 2878 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
subt | +0.043 |
RAY | +0.039 |
ople | +0.035 |
summed | +0.035 |
ial | +0.034 |
Neg logit contributions | |
eming | -0.067 |
quart | -0.064 |
lett | -0.064 |
acters | -0.062 |
ulence | -0.062 |
Token | well |
Token ID | 880 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
subt | +0.029 |
RAY | +0.028 |
ople | +0.025 |
summed | +0.025 |
ial | +0.025 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.023 |
lett | -0.022 |
acters | -0.022 |
antics | -0.021 |
Token | as |
Token ID | 355 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
eming | +0.041 |
quart | +0.039 |
lett | +0.038 |
acters | +0.037 |
antics | +0.037 |
Neg logit contributions | |
subt | -0.036 |
RAY | -0.033 |
summed | -0.030 |
ople | -0.030 |
ial | -0.030 |
Token | more |
Token ID | 517 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
subt | +0.016 |
RAY | +0.015 |
ople | +0.014 |
summed | +0.014 |
ial | +0.013 |
Neg logit contributions | |
eming | -0.018 |
quart | -0.017 |
lett | -0.017 |
acters | -0.016 |
antics | -0.016 |
Token | relaxed |
Token ID | 18397 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
eming | +0.125 |
lett | +0.120 |
quart | +0.119 |
acters | +0.115 |
amaz | +0.114 |
Neg logit contributions | |
subt | -0.091 |
RAY | -0.086 |
ople | -0.077 |
summed | -0.076 |
ertain | -0.075 |
Token | AMD |
Token ID | 10324 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
acters | +0.003 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
ople | -0.002 |
summed | -0.002 |
ial | -0.002 |
Token | Catalyst |
Token ID | 48238 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
subt | +0.077 |
RAY | +0.072 |
ople | +0.065 |
summed | +0.065 |
ial | +0.064 |
Neg logit contributions | |
eming | -0.091 |
quart | -0.086 |
lett | -0.086 |
acters | -0.083 |
antics | -0.082 |
Token | Control |
Token ID | 6779 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
subt | +0.260 |
RAY | +0.244 |
ople | +0.222 |
summed | +0.220 |
ial | +0.217 |
Neg logit contributions | |
eming | -0.278 |
lett | -0.264 |
quart | -0.264 |
acters | -0.253 |
antics | -0.253 |
Token | Center |
Token ID | 3337 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
ople | +0.016 |
summed | +0.016 |
ial | +0.016 |
Neg logit contributions | |
eming | -0.020 |
quart | -0.019 |
lett | -0.019 |
acters | -0.019 |
antics | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +9.56e-02 |
Pos logit contributions | |
subt | +0.110 |
RAY | +0.103 |
ople | +0.092 |
summed | +0.092 |
ial | +0.090 |
Neg logit contributions | |
eming | -0.145 |
quart | -0.138 |
lett | -0.138 |
acters | -0.133 |
antics | -0.133 |
Token | Over |
Token ID | 3827 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
subt | +0.060 |
RAY | +0.056 |
ople | +0.051 |
summed | +0.050 |
ial | +0.050 |
Neg logit contributions | |
eming | -0.069 |
quart | -0.065 |
lett | -0.065 |
acters | -0.063 |
antics | -0.062 |
Token | Current |
Token ID | 11297 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
subt | +0.106 |
RAY | +0.099 |
ople | +0.092 |
summed | +0.091 |
ial | +0.090 |
Neg logit contributions | |
eming | -0.088 |
quart | -0.084 |
lett | -0.083 |
acters | -0.079 |
amaz | -0.078 |
Token | inaugural |
Token ID | 26851 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
eming | +0.045 |
quart | +0.043 |
lett | +0.043 |
acters | +0.041 |
antics | +0.041 |
Neg logit contributions | |
subt | -0.037 |
RAY | -0.034 |
ople | -0.031 |
summed | -0.031 |
ial | -0.031 |
Token | episode |
Token ID | 4471 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
subt | +0.234 |
RAY | +0.216 |
ople | +0.194 |
summed | +0.194 |
ial | +0.191 |
Neg logit contributions | |
eming | -0.308 |
quart | -0.296 |
lett | -0.293 |
acters | -0.284 |
antics | -0.282 |
Token | of |
Token ID | 286 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
subt | +0.007 |
RAY | +0.007 |
summed | +0.006 |
ople | +0.006 |
ial | +0.006 |
Neg logit contributions | |
eming | -0.007 |
quart | -0.007 |
lett | -0.007 |
acters | -0.007 |
antics | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.015 |
lett | +0.014 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.016 |
RAY | -0.015 |
summed | -0.013 |
ople | -0.013 |
ial | -0.013 |
Token | Nov |
Token ID | 5267 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
summed | +0.003 |
ople | +0.003 |
ial | +0.003 |
Neg logit contributions | |
eming | -0.003 |
quart | -0.003 |
lett | -0.003 |
acters | -0.003 |
antics | -0.003 |
Token | ice |
Token ID | 501 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
eming | +0.181 |
quart | +0.173 |
lett | +0.171 |
acters | +0.166 |
antics | +0.164 |
Neg logit contributions | |
subt | -0.176 |
RAY | -0.163 |
ople | -0.149 |
summed | -0.149 |
ial | -0.148 |
Token | No |
Token ID | 1400 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
subt | +0.258 |
RAY | +0.241 |
summed | +0.221 |
ople | +0.220 |
ial | +0.218 |
Neg logit contributions | |
eming | -0.247 |
quart | -0.235 |
lett | -0.232 |
acters | -0.225 |
antics | -0.222 |
Token | Long |
Token ID | 5882 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
eming | +0.034 |
quart | +0.033 |
lett | +0.032 |
acters | +0.031 |
amaz | +0.031 |
Neg logit contributions | |
subt | -0.040 |
RAY | -0.037 |
summed | -0.034 |
ople | -0.034 |
ial | -0.034 |
Token | er |
Token ID | 263 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
subt | +0.059 |
RAY | +0.052 |
ople | +0.045 |
summed | +0.045 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.127 |
quart | -0.122 |
lett | -0.122 |
acters | -0.119 |
antics | -0.118 |
Token | Podcast |
Token ID | 16036 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
subt | +0.137 |
RAY | +0.128 |
summed | +0.117 |
ople | +0.117 |
ial | +0.115 |
Neg logit contributions | |
eming | -0.133 |
quart | -0.126 |
lett | -0.125 |
acters | -0.121 |
antics | -0.119 |
Token | , |
Token ID | 11 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
subt | +0.025 |
RAY | +0.023 |
summed | +0.021 |
ople | +0.021 |
ial | +0.021 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.029 |
lett | -0.029 |
acters | -0.028 |
antics | -0.028 |
Token | symbols |
Token ID | 14354 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.000 |
summed | -0.000 |
hess | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
eming | +0.132 |
quart | +0.126 |
lett | +0.125 |
acters | +0.121 |
antics | +0.120 |
Neg logit contributions | |
subt | -0.115 |
RAY | -0.110 |
ople | -0.100 |
ertain | -0.097 |
summed | -0.097 |
Token | dist |
Token ID | 1233 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.015 |
lett | +0.014 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.013 |
ople | -0.011 |
hess | -0.011 |
ial | -0.011 |
Token | ill |
Token ID | 359 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
subt | +0.070 |
RAY | +0.067 |
summed | +0.063 |
ople | +0.063 |
hess | +0.062 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.014 |
lett | -0.014 |
antics | -0.013 |
acters | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
eming | +0.341 |
lett | +0.326 |
quart | +0.323 |
acters | +0.313 |
antics | +0.311 |
Neg logit contributions | |
subt | -0.312 |
RAY | -0.295 |
ople | -0.271 |
summed | -0.264 |
ertain | -0.263 |
Token | weight |
Token ID | 3463 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
subt | +0.009 |
RAY | +0.008 |
ople | +0.007 |
summed | +0.007 |
ial | +0.007 |
Neg logit contributions | |
eming | -0.010 |
quart | -0.010 |
lett | -0.010 |
acters | -0.010 |
antics | -0.009 |
Token | y |
Token ID | 88 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
subt | +0.259 |
RAY | +0.242 |
ople | +0.222 |
summed | +0.222 |
ial | +0.219 |
Neg logit contributions | |
eming | -0.252 |
quart | -0.240 |
lett | -0.237 |
acters | -0.229 |
antics | -0.227 |
Token | concept |
Token ID | 3721 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.023 |
ople | +0.021 |
summed | +0.020 |
hess | +0.020 |
Neg logit contributions | |
eming | -0.028 |
quart | -0.027 |
lett | -0.027 |
acters | -0.026 |
antics | -0.026 |
Token | into |
Token ID | 656 |
Feature activation | -8.01e-02 |
Pos logit contributions | |
eming | +0.055 |
quart | +0.052 |
lett | +0.051 |
ulence | +0.049 |
acters | +0.049 |
Neg logit contributions | |
subt | -0.055 |
RAY | -0.052 |
ople | -0.047 |
summed | -0.046 |
hess | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +5.09e-03 |
Pos logit contributions | |
eming | +0.056 |
lett | +0.054 |
quart | +0.054 |
acters | +0.052 |
antics | +0.051 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.048 |
ople | -0.044 |
summed | -0.043 |
hess | -0.043 |
Token | profoundly |
Token ID | 27377 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
ople | +0.003 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.004 |
quart | -0.004 |
lett | -0.004 |
acters | -0.004 |
antics | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
subt | +0.050 |
RAY | +0.046 |
summed | +0.041 |
ople | +0.041 |
ial | +0.041 |
Neg logit contributions | |
eming | -0.064 |
quart | -0.061 |
lett | -0.060 |
acters | -0.059 |
antics | -0.058 |
Token | once |
Token ID | 1752 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
subt | +0.020 |
RAY | +0.018 |
summed | +0.017 |
ople | +0.017 |
ial | +0.017 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.018 |
lett | -0.018 |
acters | -0.017 |
antics | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
eming | +0.022 |
quart | +0.021 |
lett | +0.021 |
acters | +0.020 |
antics | +0.020 |
Neg logit contributions | |
subt | -0.021 |
RAY | -0.020 |
summed | -0.018 |
ople | -0.018 |
ial | -0.018 |
Token | D |
Token ID | 360 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
ople | +0.022 |
summed | +0.022 |
ial | +0.022 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.022 |
lett | -0.022 |
acters | -0.021 |
antics | -0.021 |
Token | DoS |
Token ID | 46498 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
eming | +0.032 |
quart | +0.030 |
lett | +0.030 |
acters | +0.028 |
amaz | +0.028 |
Neg logit contributions | |
subt | -0.060 |
RAY | -0.057 |
summed | -0.053 |
ople | -0.053 |
describ | -0.052 |
Token | mitigation |
Token ID | 33585 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
eming | +0.059 |
quart | +0.057 |
lett | +0.056 |
acters | +0.054 |
antics | +0.054 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.047 |
ople | -0.042 |
summed | -0.042 |
ial | -0.042 |
Token | posture |
Token ID | 24521 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
subt | +0.214 |
RAY | +0.200 |
ople | +0.181 |
summed | +0.180 |
ial | +0.177 |
Neg logit contributions | |
eming | -0.254 |
quart | -0.243 |
lett | -0.241 |
acters | -0.233 |
antics | -0.231 |
Token | has |
Token ID | 468 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
eming | +0.099 |
quart | +0.095 |
lett | +0.094 |
acters | +0.091 |
antics | +0.090 |
Neg logit contributions | |
subt | -0.088 |
RAY | -0.082 |
ople | -0.074 |
summed | -0.074 |
ial | -0.073 |
Token | been |
Token ID | 587 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
eming | +0.035 |
quart | +0.033 |
lett | +0.033 |
acters | +0.032 |
antics | +0.032 |
Neg logit contributions | |
subt | -0.026 |
RAY | -0.024 |
ople | -0.022 |
summed | -0.021 |
ial | -0.021 |
Token | deployed |
Token ID | 12380 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
subt | +0.017 |
RAY | +0.016 |
ople | +0.014 |
summed | +0.014 |
ial | +0.014 |
Neg logit contributions | |
eming | -0.026 |
quart | -0.025 |
lett | -0.024 |
acters | -0.024 |
antics | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
subt | +0.020 |
RAY | +0.019 |
ople | +0.017 |
summed | +0.017 |
ial | +0.017 |
Neg logit contributions | |
eming | -0.026 |
quart | -0.024 |
lett | -0.024 |
acters | -0.024 |
antics | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
eming | +0.000 |
quart | +0.000 |
lett | +0.000 |
acters | +0.000 |
antics | +0.000 |
Neg logit contributions | |
subt | -0.000 |
RAY | -0.000 |
ople | -0.000 |
summed | -0.000 |
hess | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
subt | +0.042 |
RAY | +0.038 |
ople | +0.035 |
summed | +0.035 |
describ | +0.034 |
Neg logit contributions | |
eming | -0.061 |
quart | -0.058 |
lett | -0.058 |
acters | -0.056 |
antics | -0.055 |
Token | Neg |
Token ID | 32863 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
subt | +0.038 |
RAY | +0.035 |
ople | +0.033 |
summed | +0.033 |
hess | +0.032 |
Neg logit contributions | |
eming | -0.034 |
quart | -0.033 |
lett | -0.032 |
acters | -0.031 |
antics | -0.031 |
Token | ative |
Token ID | 876 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
eming | +0.032 |
quart | +0.030 |
lett | +0.030 |
acters | +0.029 |
antics | +0.029 |
Neg logit contributions | |
subt | -0.032 |
RAY | -0.030 |
summed | -0.027 |
ople | -0.027 |
ial | -0.027 |
Token | gearing |
Token ID | 40592 |
Feature activation | +8.03e-03 |
Pos logit contributions | |
eming | +0.052 |
quart | +0.049 |
lett | +0.048 |
acters | +0.047 |
antics | +0.046 |
Neg logit contributions | |
subt | -0.059 |
RAY | -0.055 |
summed | -0.051 |
ial | -0.051 |
ople | -0.051 |
Token | : |
Token ID | 25 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
subt | +0.005 |
RAY | +0.005 |
ople | +0.004 |
summed | +0.004 |
hess | +0.004 |
Neg logit contributions | |
eming | -0.006 |
quart | -0.006 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | parents |
Token ID | 3397 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
subt | +0.072 |
RAY | +0.068 |
ople | +0.062 |
summed | +0.061 |
hess | +0.060 |
Neg logit contributions | |
eming | -0.074 |
quart | -0.071 |
lett | -0.070 |
acters | -0.068 |
antics | -0.068 |
Token | may |
Token ID | 743 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
subt | +0.060 |
RAY | +0.056 |
ople | +0.051 |
summed | +0.050 |
hess | +0.050 |
Neg logit contributions | |
eming | -0.070 |
quart | -0.067 |
lett | -0.066 |
acters | -0.064 |
antics | -0.063 |
Token | have |
Token ID | 423 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.016 |
antics | +0.016 |
Neg logit contributions | |
subt | -0.016 |
RAY | -0.015 |
ople | -0.014 |
summed | -0.014 |
ial | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
eming | +0.025 |
lett | +0.024 |
quart | +0.024 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.022 |
ople | -0.020 |
ial | -0.020 |
ertain | -0.020 |
Token | choose |
Token ID | 3853 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
eming | +0.037 |
quart | +0.036 |
lett | +0.035 |
acters | +0.034 |
antics | +0.034 |
Neg logit contributions | |
subt | -0.029 |
RAY | -0.027 |
ople | -0.024 |
summed | -0.024 |
ial | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.27e-03 |
Pos logit contributions | |
subt | +0.144 |
RAY | +0.135 |
ople | +0.123 |
summed | +0.121 |
ertain | +0.120 |
Neg logit contributions | |
eming | -0.167 |
quart | -0.160 |
lett | -0.159 |
acters | -0.154 |
antics | -0.154 |
Token | At |
Token ID | 1629 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
ople | +0.001 |
summed | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | $ |
Token ID | 720 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
subt | +0.031 |
RAY | +0.029 |
ople | +0.025 |
summed | +0.025 |
ial | +0.025 |
Neg logit contributions | |
eming | -0.052 |
quart | -0.050 |
lett | -0.049 |
acters | -0.048 |
antics | -0.047 |
Token | 35 |
Token ID | 2327 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
subt | +0.142 |
RAY | +0.132 |
summed | +0.122 |
ople | +0.121 |
ial | +0.120 |
Neg logit contributions | |
eming | -0.134 |
quart | -0.128 |
lett | -0.126 |
acters | -0.121 |
antics | -0.120 |
Token | USD |
Token ID | 11403 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
eming | +0.048 |
quart | +0.046 |
lett | +0.045 |
acters | +0.044 |
antics | +0.044 |
Neg logit contributions | |
subt | -0.042 |
RAY | -0.039 |
ople | -0.036 |
summed | -0.035 |
ial | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
subt | +0.105 |
RAY | +0.098 |
ople | +0.089 |
summed | +0.089 |
ial | +0.087 |
Neg logit contributions | |
eming | -0.125 |
quart | -0.120 |
lett | -0.119 |
acters | -0.115 |
antics | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
subt | +0.029 |
RAY | +0.027 |
ople | +0.025 |
summed | +0.024 |
ial | +0.024 |
Neg logit contributions | |
eming | -0.029 |
quart | -0.028 |
lett | -0.027 |
acters | -0.026 |
antics | -0.026 |
Token | Big |
Token ID | 4403 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
subt | +0.014 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.012 |
ial | +0.012 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.014 |
antics | -0.014 |
Token | Di |
Token ID | 6031 |
Feature activation | -7.36e-02 |
Pos logit contributions | |
eming | +0.063 |
quart | +0.060 |
lett | +0.059 |
acters | +0.057 |
antics | +0.056 |
Neg logit contributions | |
subt | -0.072 |
RAY | -0.068 |
summed | -0.062 |
ople | -0.062 |
ial | -0.062 |
Token | pper |
Token ID | 2848 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.025 |
lett | +0.025 |
acters | +0.023 |
antics | +0.023 |
Neg logit contributions | |
subt | -0.071 |
RAY | -0.068 |
ople | -0.064 |
summed | -0.064 |
ial | -0.064 |
Token | ties |
Token ID | 8470 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
eming | +0.111 |
quart | +0.106 |
lett | +0.105 |
acters | +0.102 |
antics | +0.101 |
Neg logit contributions | |
subt | -0.098 |
RAY | -0.091 |
ople | -0.083 |
summed | -0.083 |
ial | -0.082 |
Token | wrong |
Token ID | 2642 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.014 |
lett | +0.014 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.012 |
ople | -0.011 |
summed | -0.010 |
ial | -0.010 |
Token | stack |
Token ID | 8931 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
subt | +0.077 |
RAY | +0.072 |
ople | +0.065 |
summed | +0.065 |
ial | +0.064 |
Neg logit contributions | |
eming | -0.089 |
quart | -0.086 |
lett | -0.085 |
acters | -0.082 |
antics | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -2.78e-03 |
Pos logit contributions | |
subt | +0.005 |
RAY | +0.004 |
ople | +0.004 |
summed | +0.004 |
ial | +0.004 |
Neg logit contributions | |
eming | -0.005 |
quart | -0.005 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | � |
Token ID | 447 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
eming | +0.002 |
quart | +0.002 |
lett | +0.002 |
acters | +0.002 |
antics | +0.002 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | � |
Token ID | 251 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.023 |
ople | +0.021 |
summed | +0.021 |
ial | +0.021 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
antics | -0.015 |
Token | Ryan |
Token ID | 6047 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
subt | +0.005 |
RAY | +0.005 |
ople | +0.004 |
summed | +0.004 |
ial | +0.004 |
Neg logit contributions | |
eming | -0.006 |
quart | -0.005 |
lett | -0.005 |
acters | -0.005 |
antics | -0.005 |
Token | explained |
Token ID | 4893 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
subt | +0.054 |
RAY | +0.050 |
ople | +0.045 |
summed | +0.044 |
ial | +0.044 |
Neg logit contributions | |
eming | -0.069 |
quart | -0.066 |
lett | -0.065 |
acters | -0.063 |
antics | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
subt | +0.079 |
RAY | +0.073 |
ople | +0.067 |
summed | +0.067 |
ial | +0.066 |
Neg logit contributions | |
eming | -0.087 |
quart | -0.083 |
lett | -0.083 |
acters | -0.080 |
antics | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.006 |
describ | +0.005 |
ople | +0.005 |
summed | +0.005 |
Neg logit contributions | |
eming | -0.009 |
quart | -0.009 |
lett | -0.009 |
acters | -0.008 |
antics | -0.008 |
Token | Beat |
Token ID | 34979 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
eming | +0.005 |
quart | +0.005 |
lett | +0.005 |
acters | +0.004 |
antics | +0.004 |
Neg logit contributions | |
subt | -0.005 |
RAY | -0.005 |
summed | -0.004 |
ople | -0.004 |
ial | -0.004 |
Token | community |
Token ID | 2055 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
eming | +0.051 |
quart | +0.049 |
lett | +0.049 |
acters | +0.047 |
antics | +0.047 |
Neg logit contributions | |
subt | -0.037 |
RAY | -0.035 |
summed | -0.031 |
ople | -0.031 |
ial | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | � |
Token ID | 447 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
eming | +0.013 |
quart | +0.012 |
lett | +0.012 |
acters | +0.012 |
antics | +0.012 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
hess | -0.008 |
Token | � |
Token ID | 251 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
subt | +0.016 |
RAY | +0.015 |
ople | +0.014 |
summed | +0.014 |
ial | +0.014 |
Neg logit contributions | |
eming | -0.012 |
quart | -0.011 |
lett | -0.011 |
acters | -0.010 |
antics | -0.010 |
Token | leaving |
Token ID | 4305 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.005 |
ople | +0.005 |
summed | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.007 |
quart | -0.006 |
lett | -0.006 |
acters | -0.006 |
antics | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +8.16e-02 |
Pos logit contributions | |
eming | +0.084 |
lett | +0.080 |
quart | +0.080 |
acters | +0.077 |
antics | +0.076 |
Neg logit contributions | |
subt | -0.076 |
RAY | -0.071 |
ople | -0.065 |
summed | -0.065 |
ial | -0.064 |
Token | largely |
Token ID | 5688 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
subt | +0.051 |
RAY | +0.048 |
ople | +0.043 |
summed | +0.043 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.059 |
quart | -0.056 |
lett | -0.055 |
acters | -0.054 |
antics | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
eming | +0.044 |
quart | +0.042 |
lett | +0.041 |
acters | +0.040 |
antics | +0.040 |
Neg logit contributions | |
subt | -0.035 |
RAY | -0.033 |
ople | -0.029 |
summed | -0.029 |
hess | -0.029 |
Token | embedded |
Token ID | 14553 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.012 |
ople | +0.011 |
summed | +0.011 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.014 |
quart | -0.013 |
lett | -0.013 |
acters | -0.013 |
antics | -0.013 |
Token | tweets |
Token ID | 12665 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
subt | +0.047 |
RAY | +0.044 |
summed | +0.040 |
ople | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.056 |
quart | -0.054 |
lett | -0.053 |
acters | -0.052 |
antics | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
eming | +0.066 |
quart | +0.063 |
lett | +0.063 |
acters | +0.061 |
antics | +0.060 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
ople | -0.043 |
summed | -0.043 |
ial | -0.042 |
Token | it |
Token ID | 340 |
Feature activation | +6.46e-02 |
Pos logit contributions | |
subt | +0.090 |
RAY | +0.084 |
summed | +0.076 |
ople | +0.076 |
ial | +0.075 |
Neg logit contributions | |
eming | -0.097 |
quart | -0.092 |
lett | -0.091 |
acters | -0.088 |
antics | -0.088 |
Token | incredibly |
Token ID | 8131 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
subt | +0.041 |
RAY | +0.038 |
summed | +0.035 |
ople | +0.035 |
ial | +0.034 |
Neg logit contributions | |
eming | -0.046 |
quart | -0.044 |
lett | -0.044 |
acters | -0.042 |
antics | -0.042 |
Token | easy |
Token ID | 2562 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
subt | +0.042 |
RAY | +0.039 |
ople | +0.035 |
summed | +0.035 |
ial | +0.035 |
Neg logit contributions | |
eming | -0.048 |
quart | -0.046 |
lett | -0.046 |
acters | -0.044 |
antics | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
acters | +0.003 |
antics | +0.003 |
Neg logit contributions | |
subt | -0.003 |
RAY | -0.002 |
ople | -0.002 |
summed | -0.002 |
ial | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
subt | +0.029 |
RAY | +0.028 |
ople | +0.025 |
summed | +0.025 |
ial | +0.025 |
Neg logit contributions | |
eming | -0.032 |
quart | -0.031 |
lett | -0.031 |
acters | -0.029 |
antics | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
eming | +0.006 |
quart | +0.005 |
lett | +0.005 |
acters | +0.005 |
antics | +0.005 |
Neg logit contributions | |
subt | -0.005 |
RAY | -0.005 |
ople | -0.005 |
summed | -0.005 |
ial | -0.004 |
Token | again |
Token ID | 757 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
subt | +0.017 |
RAY | +0.016 |
summed | +0.015 |
ople | +0.015 |
ial | +0.014 |
Neg logit contributions | |
eming | -0.019 |
quart | -0.018 |
lett | -0.018 |
acters | -0.018 |
antics | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
eming | +0.003 |
quart | +0.003 |
lett | +0.003 |
acters | +0.003 |
antics | +0.002 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
ople | -0.002 |
summed | -0.002 |
ial | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
subt | +0.026 |
RAY | +0.024 |
summed | +0.022 |
ople | +0.022 |
ial | +0.022 |
Neg logit contributions | |
eming | -0.030 |
quart | -0.029 |
lett | -0.028 |
acters | -0.028 |
antics | -0.027 |
Token | again |
Token ID | 757 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
subt | +0.034 |
RAY | +0.032 |
summed | +0.029 |
ople | +0.029 |
ial | +0.028 |
Neg logit contributions | |
eming | -0.037 |
quart | -0.035 |
lett | -0.035 |
acters | -0.034 |
antics | -0.033 |
Token | …… |
Token ID | 7398 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
eming | +0.016 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.013 |
RAY | -0.012 |
ople | -0.011 |
summed | -0.011 |
ial | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
eming | +0.100 |
quart | +0.096 |
lett | +0.095 |
acters | +0.092 |
antics | +0.091 |
Neg logit contributions | |
subt | -0.085 |
RAY | -0.080 |
summed | -0.072 |
ople | -0.072 |
ial | -0.071 |
Token | registered |
Token ID | 6823 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.030 |
ople | +0.027 |
summed | +0.027 |
hess | +0.027 |
Neg logit contributions | |
eming | -0.038 |
quart | -0.036 |
lett | -0.036 |
acters | -0.035 |
antics | -0.034 |
Token | voters |
Token ID | 4446 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
subt | +0.029 |
RAY | +0.027 |
ople | +0.024 |
summed | +0.024 |
ial | +0.024 |
Neg logit contributions | |
eming | -0.038 |
quart | -0.037 |
lett | -0.036 |
acters | -0.035 |
antics | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
subt | +0.146 |
RAY | +0.137 |
ople | +0.124 |
summed | +0.123 |
hess | +0.122 |
Neg logit contributions | |
eming | -0.168 |
quart | -0.160 |
lett | -0.158 |
acters | -0.153 |
antics | -0.152 |
Token | i |
Token ID | 1312 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
eming | +0.001 |
quart | +0.001 |
lett | +0.001 |
acters | +0.001 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.001 |
RAY | -0.001 |
ople | -0.001 |
summed | -0.001 |
ial | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
eming | +0.056 |
quart | +0.054 |
lett | +0.053 |
acters | +0.052 |
antics | +0.051 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.046 |
summed | -0.042 |
ople | -0.042 |
ial | -0.041 |
Token | e |
Token ID | 68 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.025 |
RAY | -0.024 |
summed | -0.022 |
ople | -0.022 |
ial | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
eming | +0.077 |
quart | +0.073 |
lett | +0.072 |
acters | +0.070 |
amaz | +0.069 |
Neg logit contributions | |
subt | -0.089 |
RAY | -0.084 |
summed | -0.077 |
ople | -0.077 |
ial | -0.076 |
Token | those |
Token ID | 883 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
eming | +0.027 |
quart | +0.026 |
lett | +0.026 |
acters | +0.025 |
antics | +0.025 |
Neg logit contributions | |
subt | -0.023 |
RAY | -0.021 |
ople | -0.019 |
summed | -0.019 |
ial | -0.019 |
Token | who |
Token ID | 508 |
Feature activation | +3.53e-03 |
Pos logit contributions | |
subt | +0.047 |
RAY | +0.044 |
ople | +0.040 |
summed | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.053 |
quart | -0.051 |
lett | -0.050 |
acters | -0.048 |
antics | -0.048 |
Token | voted |
Token ID | 7052 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
ople | +0.002 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.003 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | creation |
Token ID | 6282 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
eming | +0.110 |
quart | +0.105 |
lett | +0.105 |
acters | +0.102 |
antics | +0.101 |
Neg logit contributions | |
subt | -0.078 |
RAY | -0.073 |
ople | -0.065 |
summed | -0.064 |
hess | -0.064 |
Token | system |
Token ID | 1080 |
Feature activation | -8.18e-02 |
Pos logit contributions | |
eming | +0.096 |
quart | +0.092 |
lett | +0.092 |
acters | +0.089 |
ulence | +0.088 |
Neg logit contributions | |
subt | -0.075 |
RAY | -0.071 |
ople | -0.064 |
summed | -0.063 |
hess | -0.063 |
Token | for |
Token ID | 329 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
eming | +0.059 |
quart | +0.056 |
lett | +0.056 |
acters | +0.054 |
antics | +0.053 |
Neg logit contributions | |
subt | -0.051 |
RAY | -0.048 |
ople | -0.043 |
summed | -0.043 |
ial | -0.042 |
Token | making |
Token ID | 1642 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
eming | +0.038 |
quart | +0.036 |
lett | +0.036 |
acters | +0.035 |
antics | +0.034 |
Neg logit contributions | |
subt | -0.035 |
RAY | -0.033 |
ople | -0.030 |
summed | -0.030 |
ial | -0.029 |
Token | custom |
Token ID | 2183 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
eming | +0.013 |
quart | +0.012 |
lett | +0.012 |
acters | +0.012 |
antics | +0.011 |
Neg logit contributions | |
subt | -0.012 |
RAY | -0.011 |
ople | -0.010 |
summed | -0.010 |
ial | -0.010 |
Token | characters |
Token ID | 3435 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
eming | +0.029 |
quart | +0.028 |
lett | +0.027 |
acters | +0.027 |
antics | +0.026 |
Neg logit contributions | |
subt | -0.029 |
RAY | -0.027 |
ople | -0.025 |
summed | -0.025 |
ial | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
eming | +0.157 |
quart | +0.150 |
lett | +0.149 |
acters | +0.145 |
antics | +0.143 |
Neg logit contributions | |
subt | -0.136 |
RAY | -0.128 |
ople | -0.116 |
summed | -0.115 |
hess | -0.113 |
Token |
|
Token ID | 198 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
eming | +0.009 |
quart | +0.008 |
lett | +0.008 |
acters | +0.008 |
antics | +0.008 |
Neg logit contributions | |
subt | -0.008 |
RAY | -0.007 |
ople | -0.006 |
summed | -0.006 |
ial | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e-03 |
Pos logit contributions | |
subt | +0.015 |
RAY | +0.013 |
ople | +0.012 |
summed | +0.012 |
describ | +0.012 |
Neg logit contributions | |
eming | -0.021 |
quart | -0.020 |
lett | -0.020 |
acters | -0.019 |
antics | -0.019 |
Token | Gameplay |
Token ID | 43241 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
subt | +0.001 |
RAY | +0.001 |
summed | +0.001 |
ople | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.001 |
quart | -0.001 |
lett | -0.001 |
acters | -0.001 |
antics | -0.001 |
Token | consists |
Token ID | 10874 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
subt | +0.098 |
RAY | +0.091 |
ople | +0.082 |
summed | +0.082 |
ial | +0.081 |
Neg logit contributions | |
eming | -0.127 |
quart | -0.122 |
lett | -0.121 |
acters | -0.117 |
antics | -0.116 |
Token | project |
Token ID | 1628 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
subt | +0.003 |
RAY | +0.003 |
summed | +0.003 |
ople | +0.003 |
ial | +0.003 |
Neg logit contributions | |
eming | -0.004 |
quart | -0.004 |
lett | -0.004 |
acters | -0.004 |
antics | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
subt | +0.023 |
RAY | +0.021 |
ople | +0.019 |
summed | +0.019 |
hess | +0.019 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.026 |
acters | -0.025 |
antics | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -7.39e-02 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.002 |
ople | +0.002 |
summed | +0.002 |
ial | +0.002 |
Neg logit contributions | |
eming | -0.002 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | say |
Token ID | 910 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
eming | +0.051 |
quart | +0.048 |
lett | +0.048 |
acters | +0.046 |
antics | +0.046 |
Neg logit contributions | |
subt | -0.048 |
RAY | -0.046 |
ople | -0.041 |
hess | -0.041 |
ial | -0.041 |
Token | that |
Token ID | 326 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.010 |
lett | +0.010 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.012 |
RAY | -0.011 |
ople | -0.010 |
summed | -0.010 |
ertain | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
subt | +0.016 |
RAY | +0.015 |
ople | +0.014 |
summed | +0.014 |
ertain | +0.013 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.015 |
antics | -0.015 |
Token | only |
Token ID | 691 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
summed | +0.010 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.013 |
quart | -0.013 |
lett | -0.013 |
acters | -0.012 |
antics | -0.012 |
Token | possible |
Token ID | 1744 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
subt | +0.042 |
RAY | +0.039 |
ople | +0.035 |
summed | +0.035 |
hess | +0.034 |
Neg logit contributions | |
eming | -0.056 |
quart | -0.053 |
lett | -0.053 |
acters | -0.052 |
antics | -0.051 |
Token | objection |
Token ID | 19630 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
subt | +0.049 |
RAY | +0.046 |
ople | +0.042 |
summed | +0.041 |
hess | +0.041 |
Neg logit contributions | |
eming | -0.057 |
quart | -0.054 |
lett | -0.054 |
acters | -0.052 |
antics | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
eming | +0.062 |
quart | +0.058 |
lett | +0.058 |
acters | +0.056 |
antics | +0.056 |
Neg logit contributions | |
subt | -0.059 |
RAY | -0.056 |
ople | -0.050 |
ertain | -0.050 |
summed | -0.050 |
Token | how |
Token ID | 703 |
Feature activation | -9.30e-02 |
Pos logit contributions | |
subt | +0.009 |
RAY | +0.009 |
ople | +0.008 |
summed | +0.008 |
hess | +0.008 |
Neg logit contributions | |
eming | -0.009 |
quart | -0.009 |
lett | -0.009 |
acters | -0.008 |
antics | -0.008 |
Token | version |
Token ID | 2196 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
subt | +0.106 |
RAY | +0.098 |
ople | +0.088 |
summed | +0.088 |
ial | +0.086 |
Neg logit contributions | |
eming | -0.146 |
quart | -0.140 |
lett | -0.139 |
acters | -0.135 |
antics | -0.134 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
subt | +0.093 |
RAY | +0.087 |
summed | +0.079 |
ople | +0.079 |
ial | +0.078 |
Neg logit contributions | |
eming | -0.092 |
quart | -0.088 |
lett | -0.087 |
acters | -0.084 |
antics | -0.084 |
Token | Wii |
Token ID | 16591 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
subt | +0.018 |
RAY | +0.017 |
summed | +0.015 |
ople | +0.015 |
ial | +0.015 |
Neg logit contributions | |
eming | -0.018 |
quart | -0.018 |
lett | -0.017 |
acters | -0.017 |
antics | -0.017 |
Token | Sports |
Token ID | 7092 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
subt | +0.006 |
RAY | +0.006 |
summed | +0.005 |
ople | +0.005 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.005 |
quart | -0.004 |
lett | -0.004 |
acters | -0.004 |
antics | -0.004 |
Token | Club |
Token ID | 6289 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
subt | +0.052 |
RAY | +0.048 |
ople | +0.044 |
summed | +0.044 |
ial | +0.044 |
Neg logit contributions | |
eming | -0.054 |
quart | -0.051 |
lett | -0.051 |
acters | -0.049 |
antics | -0.049 |
Token | hits |
Token ID | 7127 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
subt | +0.092 |
RAY | +0.086 |
ople | +0.079 |
summed | +0.078 |
ial | +0.078 |
Neg logit contributions | |
eming | -0.096 |
quart | -0.092 |
lett | -0.092 |
acters | -0.088 |
antics | -0.088 |
Token | stores |
Token ID | 7000 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
eming | +0.019 |
quart | +0.018 |
lett | +0.018 |
acters | +0.018 |
antics | +0.018 |
Neg logit contributions | |
subt | -0.016 |
RAY | -0.015 |
summed | -0.013 |
ople | -0.013 |
ial | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
subt | +0.066 |
RAY | +0.061 |
summed | +0.056 |
ople | +0.056 |
ial | +0.055 |
Neg logit contributions | |
eming | -0.076 |
quart | -0.072 |
lett | -0.071 |
acters | -0.069 |
antics | -0.069 |
Token | July |
Token ID | 2901 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.023 |
ople | +0.021 |
summed | +0.020 |
ial | +0.020 |
Neg logit contributions | |
eming | -0.026 |
quart | -0.024 |
lett | -0.024 |
acters | -0.023 |
antics | -0.023 |
Token | 25 |
Token ID | 1679 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
eming | +0.012 |
quart | +0.011 |
lett | +0.011 |
acters | +0.011 |
amaz | +0.010 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
hess | -0.009 |
Token | at |
Token ID | 379 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
subt | +0.028 |
RAY | +0.026 |
summed | +0.023 |
ople | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.029 |
quart | -0.028 |
lett | -0.028 |
acters | -0.027 |
antics | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
eming | +0.078 |
quart | +0.075 |
lett | +0.074 |
acters | +0.071 |
ulence | +0.071 |
Neg logit contributions | |
subt | -0.063 |
RAY | -0.059 |
ople | -0.053 |
summed | -0.052 |
hess | -0.052 |
Token | aged |
Token ID | 9722 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
eming | +0.031 |
quart | +0.030 |
lett | +0.029 |
acters | +0.028 |
ulence | +0.028 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.023 |
ople | -0.021 |
summed | -0.020 |
hess | -0.020 |
Token | 27 |
Token ID | 2681 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
subt | +0.143 |
RAY | +0.134 |
ople | +0.121 |
summed | +0.119 |
hess | +0.118 |
Neg logit contributions | |
eming | -0.173 |
quart | -0.167 |
lett | -0.166 |
acters | -0.159 |
amaz | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
subt | +0.048 |
RAY | +0.045 |
ople | +0.040 |
summed | +0.040 |
ial | +0.039 |
Neg logit contributions | |
eming | -0.061 |
quart | -0.058 |
lett | -0.058 |
acters | -0.056 |
antics | -0.056 |
Token | Butt |
Token ID | 36041 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
subt | +0.018 |
RAY | +0.017 |
summed | +0.015 |
ople | +0.015 |
ial | +0.015 |
Neg logit contributions | |
eming | -0.018 |
quart | -0.017 |
lett | -0.017 |
acters | -0.017 |
antics | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
eming | +0.058 |
quart | +0.055 |
lett | +0.055 |
acters | +0.053 |
antics | +0.052 |
Neg logit contributions | |
subt | -0.054 |
RAY | -0.050 |
ople | -0.046 |
summed | -0.045 |
hess | -0.045 |
Token | previously |
Token ID | 4271 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
eming | +0.039 |
quart | +0.038 |
lett | +0.038 |
acters | +0.036 |
amaz | +0.036 |
Neg logit contributions | |
subt | -0.033 |
RAY | -0.031 |
ople | -0.028 |
summed | -0.028 |
hess | -0.028 |
Token | known |
Token ID | 1900 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
eming | +0.175 |
quart | +0.170 |
lett | +0.169 |
acters | +0.162 |
amaz | +0.161 |
Neg logit contributions | |
subt | -0.106 |
RAY | -0.097 |
ople | -0.086 |
summed | -0.085 |
hess | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
subt | +0.053 |
RAY | +0.049 |
summed | +0.044 |
ial | +0.044 |
ople | +0.044 |
Neg logit contributions | |
eming | -0.064 |
quart | -0.061 |
lett | -0.060 |
acters | -0.059 |
antics | -0.059 |
Token | police |
Token ID | 1644 |
Feature activation | +2.42e-03 |
Pos logit contributions | |
eming | +0.021 |
quart | +0.020 |
lett | +0.020 |
acters | +0.019 |
antics | +0.019 |
Neg logit contributions | |
subt | -0.020 |
RAY | -0.019 |
summed | -0.017 |
ople | -0.017 |
ial | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -8.24e-03 |
Pos logit contributions | |
subt | +0.002 |
RAY | +0.001 |
summed | +0.001 |
ople | +0.001 |
ial | +0.001 |
Neg logit contributions | |
eming | -0.002 |
quart | -0.002 |
lett | -0.002 |
acters | -0.002 |
antics | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
subt | +0.061 |
RAY | +0.057 |
ople | +0.052 |
summed | +0.052 |
ial | +0.051 |
Neg logit contributions | |
eming | -0.069 |
quart | -0.066 |
lett | -0.065 |
acters | -0.063 |
antics | -0.063 |
Token | cities |
Token ID | 4736 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.016 |
antics | +0.016 |
Neg logit contributions | |
subt | -0.016 |
RAY | -0.015 |
ople | -0.014 |
summed | -0.014 |
ial | -0.013 |
Token | like |
Token ID | 588 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
eming | +0.034 |
quart | +0.032 |
lett | +0.032 |
acters | +0.031 |
antics | +0.031 |
Neg logit contributions | |
subt | -0.030 |
RAY | -0.028 |
summed | -0.026 |
ople | -0.026 |
ial | -0.025 |
Token | N |
Token ID | 399 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
subt | +0.024 |
RAY | +0.023 |
summed | +0.021 |
ople | +0.021 |
ial | +0.021 |
Neg logit contributions | |
eming | -0.024 |
quart | -0.023 |
lett | -0.022 |
acters | -0.022 |
antics | -0.021 |
Token | airo |
Token ID | 18131 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
eming | +0.077 |
quart | +0.074 |
lett | +0.073 |
acters | +0.071 |
antics | +0.071 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.046 |
summed | -0.041 |
ople | -0.041 |
ial | -0.040 |
Token | bi |
Token ID | 8482 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
subt | +0.192 |
RAY | +0.183 |
summed | +0.173 |
ople | +0.172 |
ial | +0.171 |
Neg logit contributions | |
eming | -0.066 |
quart | -0.060 |
lett | -0.058 |
acters | -0.055 |
antics | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
eming | +0.243 |
quart | +0.233 |
lett | +0.230 |
acters | +0.223 |
antics | +0.221 |
Neg logit contributions | |
subt | -0.197 |
RAY | -0.183 |
ople | -0.165 |
summed | -0.165 |
ial | -0.162 |
Token | M |
Token ID | 337 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
subt | +0.027 |
RAY | +0.026 |
ople | +0.024 |
summed | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.027 |
quart | -0.026 |
lett | -0.025 |
acters | -0.024 |
antics | -0.024 |
Token | omb |
Token ID | 2381 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
subt | +0.036 |
RAY | +0.034 |
summed | +0.031 |
ople | +0.031 |
ial | +0.030 |
Neg logit contributions | |
eming | -0.040 |
quart | -0.038 |
lett | -0.037 |
acters | -0.036 |
antics | -0.036 |
Token | asa |
Token ID | 15462 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
subt | +0.080 |
RAY | +0.076 |
ople | +0.071 |
summed | +0.071 |
ial | +0.071 |
Neg logit contributions | |
eming | -0.049 |
quart | -0.047 |
lett | -0.046 |
acters | -0.044 |
antics | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
eming | +0.097 |
quart | +0.093 |
lett | +0.092 |
acters | +0.090 |
antics | +0.089 |
Neg logit contributions | |
subt | -0.081 |
RAY | -0.075 |
summed | -0.067 |
ople | -0.067 |
ial | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
eming | +0.163 |
quart | +0.157 |
lett | +0.155 |
acters | +0.150 |
antics | +0.149 |
Neg logit contributions | |
subt | -0.126 |
RAY | -0.116 |
summed | -0.104 |
ople | -0.104 |
ial | -0.103 |
Token | 1988 |
Token ID | 12122 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
eming | +0.031 |
quart | +0.030 |
lett | +0.029 |
acters | +0.028 |
antics | +0.028 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.023 |
ople | -0.020 |
summed | -0.020 |
ial | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.015 |
RAY | -0.014 |
summed | -0.013 |
ople | -0.013 |
ial | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.027 |
lett | +0.027 |
acters | +0.026 |
antics | +0.026 |
Neg logit contributions | |
subt | -0.019 |
RAY | -0.018 |
summed | -0.016 |
ople | -0.016 |
ial | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
eming | +0.015 |
quart | +0.014 |
lett | +0.014 |
acters | +0.014 |
antics | +0.014 |
Neg logit contributions | |
subt | -0.010 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
describ | -0.009 |
Token | Ye |
Token ID | 35543 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
eming | +0.017 |
quart | +0.016 |
lett | +0.016 |
acters | +0.015 |
antics | +0.015 |
Neg logit contributions | |
subt | -0.020 |
RAY | -0.019 |
summed | -0.018 |
ople | -0.018 |
ial | -0.018 |
Token | ager |
Token ID | 3536 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
eming | +0.236 |
quart | +0.226 |
lett | +0.224 |
acters | +0.216 |
antics | +0.215 |
Neg logit contributions | |
subt | -0.180 |
RAY | -0.166 |
summed | -0.150 |
ople | -0.149 |
ial | -0.146 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
subt | +0.019 |
RAY | +0.018 |
ople | +0.016 |
summed | +0.016 |
ial | +0.016 |
Neg logit contributions | |
eming | -0.025 |
quart | -0.024 |
lett | -0.023 |
acters | -0.023 |
antics | -0.023 |
Token | Chuck |
Token ID | 14663 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
eming | +0.028 |
quart | +0.027 |
lett | +0.027 |
acters | +0.026 |
antics | +0.026 |
Neg logit contributions | |
subt | -0.024 |
RAY | -0.022 |
ople | -0.020 |
summed | -0.020 |
ial | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
subt | +0.050 |
RAY | +0.047 |
ople | +0.043 |
summed | +0.043 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.050 |
quart | -0.047 |
lett | -0.047 |
acters | -0.045 |
antics | -0.045 |
Token | et |
Token ID | 2123 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
eming | +0.026 |
quart | +0.025 |
lett | +0.025 |
acters | +0.024 |
antics | +0.024 |
Neg logit contributions | |
subt | -0.022 |
RAY | -0.020 |
ople | -0.019 |
summed | -0.018 |
ial | -0.018 |
Token | incorporated |
Token ID | 16560 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
eming | +0.013 |
quart | +0.012 |
lett | +0.012 |
acters | +0.012 |
ulence | +0.012 |
Neg logit contributions | |
subt | -0.011 |
RAY | -0.010 |
ople | -0.009 |
summed | -0.009 |
ial | -0.009 |
Token | small |
Token ID | 1402 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
subt | +0.059 |
RAY | +0.055 |
ople | +0.050 |
summed | +0.050 |
ial | +0.050 |
Neg logit contributions | |
eming | -0.062 |
quart | -0.059 |
lett | -0.059 |
acters | -0.057 |
antics | -0.056 |
Token | business |
Token ID | 1597 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
eming | +0.002 |
quart | +0.002 |
lett | +0.002 |
acters | +0.002 |
antics | +0.001 |
Neg logit contributions | |
subt | -0.002 |
RAY | -0.002 |
summed | -0.001 |
ople | -0.001 |
ial | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
eming | +0.093 |
quart | +0.089 |
lett | +0.088 |
acters | +0.085 |
antics | +0.085 |
Neg logit contributions | |
subt | -0.084 |
RAY | -0.078 |
summed | -0.071 |
ople | -0.070 |
ial | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -2.07e-04 |
Pos logit contributions | |
eming | +0.035 |
quart | +0.033 |
lett | +0.033 |
acters | +0.032 |
antics | +0.032 |
Neg logit contributions | |
subt | -0.031 |
RAY | -0.028 |
ople | -0.026 |
summed | -0.026 |
ial | -0.025 |
Token | vehicle |
Token ID | 4038 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
eming | +0.000 |
quart | +0.000 |
lett | +0.000 |
acters | +0.000 |
antics | +0.000 |
Neg logit contributions | |
subt | -0.000 |
RAY | -0.000 |
ople | -0.000 |
summed | -0.000 |
ial | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
eming | +0.217 |
quart | +0.207 |
lett | +0.204 |
acters | +0.198 |
antics | +0.196 |
Neg logit contributions | |
subt | -0.223 |
RAY | -0.208 |
summed | -0.191 |
ople | -0.190 |
ial | -0.189 |
Token | making |
Token ID | 1642 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
eming | +0.056 |
quart | +0.053 |
lett | +0.053 |
acters | +0.051 |
antics | +0.051 |
Neg logit contributions | |
subt | -0.050 |
RAY | -0.046 |
ople | -0.042 |
summed | -0.042 |
ial | -0.042 |
Token | passive |
Token ID | 14513 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
eming | +0.011 |
quart | +0.010 |
lett | +0.010 |
acters | +0.010 |
antics | +0.010 |
Neg logit contributions | |
subt | -0.009 |
RAY | -0.009 |
ople | -0.008 |
summed | -0.008 |
ial | -0.008 |
Token | investments |
Token ID | 11115 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
subt | +0.063 |
RAY | +0.058 |
summed | +0.053 |
ople | +0.053 |
ial | +0.052 |
Neg logit contributions | |
eming | -0.072 |
quart | -0.068 |
lett | -0.067 |
acters | -0.065 |
antics | -0.065 |
Token | unrelated |
Token ID | 19938 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
subt | +0.032 |
RAY | +0.030 |
ople | +0.027 |
summed | +0.027 |
ial | +0.027 |
Neg logit contributions | |
eming | -0.036 |
quart | -0.034 |
lett | -0.034 |
acters | -0.033 |
antics | -0.032 |
Token | which |
Token ID | 543 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
eming | +0.024 |
quart | +0.023 |
lett | +0.022 |
acters | +0.022 |
antics | +0.021 |
Neg logit contributions | |
subt | -0.019 |
RAY | -0.018 |
ople | -0.016 |
summed | -0.016 |
ial | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
subt | +0.070 |
RAY | +0.065 |
ople | +0.059 |
summed | +0.059 |
ial | +0.058 |
Neg logit contributions | |
eming | -0.079 |
quart | -0.076 |
lett | -0.075 |
acters | -0.073 |
antics | -0.072 |
Token | also |
Token ID | 635 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
eming | +0.030 |
quart | +0.029 |
lett | +0.029 |
acters | +0.028 |
antics | +0.027 |
Neg logit contributions | |
subt | -0.022 |
RAY | -0.020 |
ople | -0.018 |
summed | -0.018 |
ial | -0.018 |
Token | controlled |
Token ID | 6856 |
Feature activation | -5.38e-04 |
Pos logit contributions | |
subt | +0.007 |
RAY | +0.006 |
ople | +0.006 |
summed | +0.006 |
ial | +0.005 |
Neg logit contributions | |
eming | -0.009 |
quart | -0.009 |
lett | -0.009 |
acters | -0.009 |
antics | -0.009 |
Token | by |
Token ID | 416 |
Feature activation | -9.05e-02 |
Pos logit contributions | |
eming | +0.000 |
quart | +0.000 |
lett | +0.000 |
acters | +0.000 |
antics | +0.000 |
Neg logit contributions | |
subt | -0.000 |
RAY | -0.000 |
summed | -0.000 |
ial | -0.000 |
ople | -0.000 |
Token | Kol |
Token ID | 25910 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
eming | +0.046 |
quart | +0.043 |
lett | +0.043 |
acters | +0.041 |
antics | +0.040 |
Neg logit contributions | |
subt | -0.076 |
RAY | -0.072 |
summed | -0.067 |
ople | -0.067 |
ial | -0.066 |
Token | omo |
Token ID | 17902 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
eming | +0.219 |
quart | +0.209 |
lett | +0.206 |
acters | +0.200 |
antics | +0.198 |
Neg logit contributions | |
subt | -0.212 |
RAY | -0.197 |
ople | -0.180 |
summed | -0.180 |
ial | -0.178 |
Token | isky |
Token ID | 34041 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
subt | +0.027 |
RAY | +0.025 |
ople | +0.023 |
summed | +0.023 |
ial | +0.023 |
Neg logit contributions | |
eming | -0.016 |
quart | -0.015 |
lett | -0.015 |
acters | -0.014 |
antics | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
eming | +0.024 |
quart | +0.023 |
lett | +0.022 |
acters | +0.022 |
antics | +0.021 |
Neg logit contributions | |
subt | -0.021 |
RAY | -0.019 |
ople | -0.018 |
summed | -0.018 |
ial | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
subt | +0.044 |
RAY | +0.041 |
ople | +0.038 |
summed | +0.038 |
ial | +0.037 |
Neg logit contributions | |
eming | -0.044 |
quart | -0.042 |
lett | -0.041 |
acters | -0.040 |
antics | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.011 |
ople | +0.010 |
summed | +0.010 |
describ | +0.010 |
Neg logit contributions | |
eming | -0.017 |
quart | -0.016 |
lett | -0.016 |
acters | -0.015 |
antics | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
eming | +0.075 |
quart | +0.072 |
lett | +0.071 |
acters | +0.069 |
antics | +0.069 |
Neg logit contributions | |
subt | -0.055 |
RAY | -0.051 |
summed | -0.046 |
ople | -0.046 |
ial | -0.045 |
Token | Leg |
Token ID | 3564 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
subt | +0.018 |
RAY | +0.017 |
summed | +0.016 |
ople | +0.016 |
ial | +0.016 |
Neg logit contributions | |
eming | -0.014 |
quart | -0.013 |
lett | -0.013 |
acters | -0.012 |
antics | -0.012 |
Token | olas |
Token ID | 12456 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
eming | +0.058 |
quart | +0.055 |
lett | +0.055 |
acters | +0.053 |
antics | +0.053 |
Neg logit contributions | |
subt | -0.062 |
RAY | -0.058 |
summed | -0.053 |
ople | -0.053 |
ial | -0.052 |
Token | track |
Token ID | 2610 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
subt | +0.069 |
RAY | +0.065 |
ople | +0.058 |
summed | +0.058 |
ial | +0.057 |
Neg logit contributions | |
eming | -0.074 |
quart | -0.071 |
lett | -0.071 |
acters | -0.068 |
antics | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
subt | +0.246 |
RAY | +0.231 |
summed | +0.212 |
ople | +0.211 |
ial | +0.210 |
Neg logit contributions | |
eming | -0.219 |
quart | -0.209 |
lett | -0.205 |
acters | -0.198 |
antics | -0.197 |
Token | hob |
Token ID | 32724 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
subt | +0.012 |
RAY | +0.012 |
summed | +0.011 |
ople | +0.011 |
ial | +0.010 |
Neg logit contributions | |
eming | -0.011 |
quart | -0.010 |
lett | -0.010 |
acters | -0.010 |
antics | -0.010 |
Token | bits |
Token ID | 9895 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
eming | +0.198 |
quart | +0.185 |
lett | +0.183 |
acters | +0.175 |
antics | +0.172 |
Neg logit contributions | |
subt | -0.346 |
RAY | -0.328 |
summed | -0.305 |
ople | -0.304 |
ial | -0.302 |
Token | to |
Token ID | 284 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
eming | +0.119 |
quart | +0.113 |
lett | +0.112 |
acters | +0.108 |
antics | +0.107 |
Neg logit contributions | |
subt | -0.116 |
RAY | -0.108 |
ople | -0.099 |
summed | -0.098 |
ial | -0.097 |
Token | Fang |
Token ID | 24468 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
eming | +0.032 |
quart | +0.030 |
lett | +0.030 |
acters | +0.029 |
antics | +0.028 |
Neg logit contributions | |
subt | -0.031 |
RAY | -0.029 |
ople | -0.026 |
summed | -0.026 |
ial | -0.026 |
Token | orn |
Token ID | 1211 |
Feature activation | +9.41e-02 |
Pos logit contributions | |
subt | +0.211 |
RAY | +0.198 |
summed | +0.182 |
ople | +0.180 |
ial | +0.178 |
Neg logit contributions | |
eming | -0.193 |
quart | -0.184 |
lett | -0.183 |
acters | -0.174 |
antics | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
subt | +0.053 |
RAY | +0.048 |
summed | +0.043 |
ople | +0.043 |
ial | +0.043 |
Neg logit contributions | |
eming | -0.074 |
quart | -0.071 |
lett | -0.071 |
acters | -0.068 |
antics | -0.068 |