Token | dubious |
Token ID | 25292 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
blasphemy | +0.120 |
Goat | +0.116 |
ドラ | +0.108 |
arge | +0.105 |
hift | +0.104 |
Neg logit contributions | |
]. | -0.098 |
�� | -0.095 |
Nikol | -0.083 |
Rub | -0.082 |
chest | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
blasphemy | +0.034 |
Goat | +0.032 |
ドラ | +0.030 |
arge | +0.029 |
hift | +0.028 |
Neg logit contributions | |
]. | -0.035 |
�� | -0.035 |
Nikol | -0.030 |
Rub | -0.030 |
chest | -0.029 |
Token | Obama |
Token ID | 2486 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
blasphemy | +0.099 |
Goat | +0.095 |
ドラ | +0.089 |
arge | +0.087 |
hift | +0.085 |
Neg logit contributions | |
]. | -0.083 |
�� | -0.079 |
Nikol | -0.071 |
Rub | -0.070 |
chest | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
blasphemy | +0.198 |
Goat | +0.192 |
ドラ | +0.177 |
arge | +0.172 |
hift | +0.170 |
Neg logit contributions | |
]. | -0.178 |
�� | -0.174 |
Nikol | -0.153 |
Rub | -0.152 |
chest | -0.145 |
Token | con |
Token ID | 369 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
blasphemy | +0.268 |
Goat | +0.259 |
ドラ | +0.241 |
arge | +0.234 |
hift | +0.231 |
Neg logit contributions | |
]. | -0.232 |
�� | -0.227 |
Nikol | -0.200 |
Rub | -0.197 |
chest | -0.188 |
Token | versely |
Token ID | 21243 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
]. | +0.324 |
�� | +0.313 |
Nikol | +0.279 |
Rub | +0.275 |
chest | +0.267 |
Neg logit contributions | |
blasphemy | -0.356 |
Goat | -0.344 |
ドラ | -0.320 |
arge | -0.309 |
yrinth | -0.305 |
Token | , |
Token ID | 11 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
blasphemy | +1.754 |
Goat | +1.685 |
ドラ | +1.534 |
arge | +1.477 |
hift | +1.451 |
Neg logit contributions | |
]. | -2.261 |
�� | -2.215 |
Nikol | -1.995 |
Rub | -1.974 |
chest | -1.912 |
Token | has |
Token ID | 468 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
blasphemy | +0.337 |
Goat | +0.327 |
ドラ | +0.305 |
arge | +0.297 |
hift | +0.293 |
Neg logit contributions | |
]. | -0.250 |
�� | -0.245 |
Nikol | -0.211 |
Rub | -0.208 |
chest | -0.198 |
Token | played |
Token ID | 2826 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
blasphemy | +0.106 |
Goat | +0.103 |
ドラ | +0.096 |
arge | +0.094 |
hift | +0.092 |
Neg logit contributions | |
]. | -0.083 |
�� | -0.081 |
Nikol | -0.071 |
Rub | -0.070 |
chest | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
blasphemy | +0.210 |
Goat | +0.203 |
ドラ | +0.189 |
arge | +0.184 |
hift | +0.181 |
Neg logit contributions | |
]. | -0.186 |
�� | -0.182 |
Nikol | -0.160 |
Rub | -0.158 |
chest | -0.151 |
Token | role |
Token ID | 2597 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
blasphemy | +0.045 |
Goat | +0.044 |
ドラ | +0.040 |
arge | +0.039 |
hift | +0.038 |
Neg logit contributions | |
]. | -0.055 |
�� | -0.054 |
Nikol | -0.049 |
Rub | -0.048 |
chest | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
blasphemy | +0.442 |
Goat | +0.425 |
ドラ | +0.393 |
arge | +0.380 |
hift | +0.374 |
Neg logit contributions | |
]. | -0.452 |
�� | -0.440 |
Nikol | -0.389 |
Rub | -0.387 |
chest | -0.371 |
Token | � |
Token ID | 564 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
blasphemy | +0.013 |
Goat | +0.013 |
ドラ | +0.012 |
arge | +0.012 |
hift | +0.012 |
Neg logit contributions | |
]. | -0.011 |
�� | -0.010 |
Nikol | -0.009 |
Rub | -0.009 |
addle | -0.008 |
Token | � |
Token ID | 250 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
blasphemy | +0.082 |
Goat | +0.079 |
ドラ | +0.074 |
arge | +0.073 |
hift | +0.072 |
Neg logit contributions | |
]. | -0.054 |
�� | -0.053 |
Nikol | -0.045 |
Rub | -0.044 |
chest | -0.042 |
Token | Pl |
Token ID | 3646 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
]. | +0.053 |
�� | +0.051 |
Rub | +0.046 |
Nikol | +0.045 |
chest | +0.043 |
Neg logit contributions | |
blasphemy | -0.063 |
Goat | -0.061 |
ドラ | -0.057 |
arge | -0.055 |
hift | -0.055 |
Token | anned |
Token ID | 3577 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
blasphemy | +0.146 |
Goat | +0.143 |
ドラ | +0.135 |
arge | +0.129 |
hift | +0.129 |
Neg logit contributions | |
]. | -0.069 |
�� | -0.064 |
Rub | -0.053 |
Nikol | -0.053 |
addle | -0.050 |
Token | Parenthood |
Token ID | 18461 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
blasphemy | +0.253 |
Goat | +0.244 |
ドラ | +0.228 |
hift | +0.218 |
yrinth | +0.218 |
Neg logit contributions | |
]. | -0.262 |
�� | -0.254 |
Nikol | -0.228 |
Rub | -0.227 |
addle | -0.217 |
Token | is |
Token ID | 318 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
blasphemy | +1.873 |
Goat | +1.812 |
ドラ | +1.682 |
arge | +1.637 |
hift | +1.613 |
Neg logit contributions | |
]. | -1.553 |
�� | -1.533 |
Nikol | -1.323 |
Rub | -1.309 |
chest | -1.255 |
Token | answering |
Token ID | 18877 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
blasphemy | +0.125 |
Goat | +0.122 |
ドラ | +0.115 |
arge | +0.111 |
hift | +0.110 |
Neg logit contributions | |
]. | -0.095 |
�� | -0.090 |
Nikol | -0.080 |
Rub | -0.079 |
chest | -0.075 |
Token | questions |
Token ID | 2683 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
]. | +0.410 |
�� | +0.394 |
Nikol | +0.354 |
Rub | +0.349 |
chest | +0.335 |
Neg logit contributions | |
blasphemy | -0.436 |
Goat | -0.424 |
ドラ | -0.400 |
arge | -0.386 |
yrinth | -0.379 |
Token | and |
Token ID | 290 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
]. | +0.151 |
�� | +0.145 |
Nikol | +0.128 |
Rub | +0.126 |
addle | +0.119 |
Neg logit contributions | |
blasphemy | -0.202 |
Goat | -0.195 |
ドラ | -0.185 |
arge | -0.177 |
yrinth | -0.176 |
Token | will |
Token ID | 481 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
blasphemy | +0.032 |
Goat | +0.031 |
ドラ | +0.029 |
arge | +0.028 |
hift | +0.028 |
Neg logit contributions | |
]. | -0.021 |
�� | -0.020 |
Nikol | -0.017 |
Rub | -0.017 |
chest | -0.016 |
Token | iff |
Token ID | 733 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
]. | +0.089 |
�� | +0.080 |
Rub | +0.069 |
Nikol | +0.068 |
addle | +0.065 |
Neg logit contributions | |
blasphemy | -0.221 |
Goat | -0.218 |
ドラ | -0.210 |
hift | -0.198 |
yrinth | -0.198 |
Token | Tra |
Token ID | 15721 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
]. | +0.107 |
�� | +0.099 |
Rub | +0.097 |
Nikol | +0.093 |
chest | +0.093 |
Neg logit contributions | |
blasphemy | -0.060 |
Goat | -0.056 |
ドラ | -0.051 |
yrinth | -0.048 |
arge | -0.047 |
Token | x |
Token ID | 87 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
blasphemy | +0.698 |
Goat | +0.678 |
ドラ | +0.635 |
yrinth | +0.612 |
arge | +0.605 |
Neg logit contributions | |
]. | -0.454 |
�� | -0.410 |
Rub | -0.376 |
Nikol | -0.365 |
xff | -0.361 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
]. | +0.148 |
�� | +0.144 |
Nikol | +0.122 |
Rub | +0.120 |
chest | +0.113 |
Neg logit contributions | |
blasphemy | -0.244 |
Goat | -0.237 |
ドラ | -0.223 |
arge | -0.217 |
hift | -0.214 |
Token |
|
Token ID | 198 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
blasphemy | +0.257 |
Goat | +0.248 |
ドラ | +0.237 |
yrinth | +0.231 |
arge | +0.229 |
Neg logit contributions | |
]. | -0.133 |
�� | -0.119 |
Nikol | -0.105 |
Rub | -0.105 |
chest | -0.098 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
blasphemy | +0.207 |
Goat | +0.200 |
ドラ | +0.185 |
arge | +0.178 |
yrinth | +0.176 |
Neg logit contributions | |
]. | -0.183 |
�� | -0.175 |
Rub | -0.157 |
Nikol | -0.154 |
chest | -0.150 |
Token | : |
Token ID | 25 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
blasphemy | +1.801 |
Goat | +1.724 |
ドラ | +1.620 |
yrinth | +1.559 |
arge | +1.543 |
Neg logit contributions | |
]. | -1.636 |
�� | -1.543 |
Nikol | -1.395 |
Rub | -1.391 |
chest | -1.332 |
Token | V |
Token ID | 569 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
blasphemy | +0.230 |
Goat | +0.223 |
ドラ | +0.207 |
arge | +0.201 |
hift | +0.198 |
Neg logit contributions | |
]. | -0.200 |
�� | -0.197 |
Nikol | -0.171 |
Rub | -0.170 |
chest | -0.162 |
Token | the |
Token ID | 1169 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
]. | +0.017 |
�� | +0.017 |
Nikol | +0.015 |
Rub | +0.015 |
addle | +0.014 |
Neg logit contributions | |
blasphemy | -0.018 |
Goat | -0.018 |
ドラ | -0.016 |
arge | -0.016 |
hift | -0.016 |
Token | Happy |
Token ID | 25082 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
blasphemy | +0.122 |
Goat | +0.118 |
ドラ | +0.109 |
arge | +0.105 |
hift | +0.104 |
Neg logit contributions | |
]. | -0.120 |
�� | -0.118 |
Nikol | -0.104 |
Rub | -0.104 |
chest | -0.100 |
Token | L |
Token ID | 43 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
blasphemy | +0.357 |
Goat | +0.341 |
ドラ | +0.317 |
arge | +0.306 |
hift | +0.301 |
Neg logit contributions | |
]. | -0.371 |
�� | -0.363 |
Nikol | -0.321 |
Rub | -0.321 |
chest | -0.308 |
Token | dividing |
Token ID | 27241 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
blasphemy | +0.173 |
Goat | +0.168 |
ドラ | +0.157 |
arge | +0.153 |
hift | +0.151 |
Neg logit contributions | |
]. | -0.128 |
�� | -0.125 |
Nikol | -0.108 |
Rub | -0.106 |
addle | -0.101 |
Token | that |
Token ID | 326 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
blasphemy | +0.216 |
Goat | +0.209 |
ドラ | +0.192 |
arge | +0.186 |
hift | +0.184 |
Neg logit contributions | |
]. | -0.215 |
�� | -0.212 |
Nikol | -0.186 |
Rub | -0.184 |
chest | -0.177 |
Token | result |
Token ID | 1255 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
]. | +0.107 |
�� | +0.105 |
Nikol | +0.093 |
Rub | +0.092 |
addle | +0.089 |
Neg logit contributions | |
blasphemy | -0.099 |
Goat | -0.096 |
ドラ | -0.089 |
arge | -0.086 |
hift | -0.084 |
Token | by |
Token ID | 416 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
]. | +0.156 |
�� | +0.153 |
Nikol | +0.136 |
Rub | +0.134 |
addle | +0.129 |
Neg logit contributions | |
blasphemy | -0.146 |
Goat | -0.141 |
ドラ | -0.130 |
arge | -0.125 |
hift | -0.123 |
Token | 24 |
Token ID | 1987 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
blasphemy | +0.075 |
Goat | +0.072 |
ドラ | +0.068 |
arge | +0.066 |
hift | +0.065 |
Neg logit contributions | |
]. | -0.061 |
�� | -0.059 |
Nikol | -0.052 |
Rub | -0.051 |
addle | -0.049 |
Token | hours |
Token ID | 2250 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
blasphemy | +0.454 |
Goat | +0.438 |
ドラ | +0.401 |
arge | +0.389 |
hift | +0.383 |
Neg logit contributions | |
]. | -0.497 |
�� | -0.490 |
Nikol | -0.433 |
Rub | -0.429 |
chest | -0.414 |
Token | to |
Token ID | 284 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
blasphemy | +1.619 |
Goat | +1.558 |
ドラ | +1.418 |
arge | +1.386 |
hift | +1.382 |
Neg logit contributions | |
�� | -1.625 |
]. | -1.624 |
Nikol | -1.414 |
Rub | -1.408 |
chest | -1.353 |
Token | get |
Token ID | 651 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
blasphemy | +0.385 |
Goat | +0.372 |
ドラ | +0.350 |
arge | +0.338 |
yrinth | +0.333 |
Neg logit contributions | |
]. | -0.280 |
�� | -0.270 |
Nikol | -0.233 |
Rub | -0.231 |
addle | -0.221 |
Token | miles |
Token ID | 4608 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
blasphemy | +0.280 |
Goat | +0.271 |
ドラ | +0.252 |
arge | +0.245 |
hift | +0.242 |
Neg logit contributions | |
]. | -0.238 |
�� | -0.233 |
Nikol | -0.203 |
Rub | -0.200 |
addle | -0.192 |
Token | per |
Token ID | 583 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
blasphemy | +0.456 |
Goat | +0.441 |
ドラ | +0.409 |
arge | +0.398 |
hift | +0.394 |
Neg logit contributions | |
]. | -0.372 |
�� | -0.367 |
Nikol | -0.317 |
Rub | -0.314 |
chest | -0.300 |
Token | hour |
Token ID | 1711 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
]. | +0.030 |
�� | +0.029 |
Nikol | +0.026 |
Rub | +0.026 |
addle | +0.025 |
Neg logit contributions | |
blasphemy | -0.026 |
Goat | -0.025 |
ドラ | -0.023 |
arge | -0.022 |
hift | -0.022 |
Token | first |
Token ID | 717 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
blasphemy | +0.079 |
Goat | +0.075 |
ドラ | +0.071 |
yrinth | +0.068 |
arge | +0.068 |
Neg logit contributions | |
]. | -0.086 |
�� | -0.082 |
Nikol | -0.074 |
Rub | -0.073 |
chest | -0.071 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
blasphemy | +0.048 |
Goat | +0.047 |
ドラ | +0.044 |
yrinth | +0.043 |
arge | +0.043 |
Neg logit contributions | |
]. | -0.033 |
�� | -0.031 |
Nikol | -0.027 |
Rub | -0.027 |
chest | -0.026 |
Token | hear |
Token ID | 3285 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
blasphemy | +0.155 |
Goat | +0.151 |
ドラ | +0.143 |
arge | +0.140 |
hift | +0.139 |
Neg logit contributions | |
]. | -0.051 |
�� | -0.049 |
Nikol | -0.037 |
Rub | -0.036 |
chest | -0.033 |
Token | about |
Token ID | 546 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
]. | +0.177 |
�� | +0.159 |
Nikol | +0.142 |
Rub | +0.139 |
chest | +0.130 |
Neg logit contributions | |
blasphemy | -0.337 |
Goat | -0.326 |
ドラ | -0.310 |
yrinth | -0.302 |
arge | -0.299 |
Token | Nation |
Token ID | 8741 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
blasphemy | +0.109 |
Goat | +0.103 |
ドラ | +0.100 |
arge | +0.094 |
hift | +0.094 |
Neg logit contributions | |
]. | -0.109 |
�� | -0.099 |
Nikol | -0.094 |
Rub | -0.092 |
addle | -0.088 |
Token | Travels |
Token ID | 48899 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
]. | +0.309 |
�� | +0.286 |
Nikol | +0.257 |
Rub | +0.251 |
addle | +0.244 |
Neg logit contributions | |
blasphemy | -0.466 |
Goat | -0.451 |
ドラ | -0.424 |
arge | -0.414 |
hift | -0.413 |
Token | destinations |
Token ID | 23982 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
blasphemy | +0.846 |
Goat | +0.789 |
ドラ | +0.667 |
arge | +0.624 |
hift | +0.605 |
Neg logit contributions | |
]. | -2.381 |
�� | -2.351 |
Nikol | -2.163 |
Rub | -2.148 |
addle | -2.097 |
Token | , |
Token ID | 11 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
blasphemy | +0.609 |
Goat | +0.577 |
ドラ | +0.537 |
yrinth | +0.530 |
arge | +0.513 |
Neg logit contributions | |
]. | -0.658 |
�� | -0.599 |
Rub | -0.569 |
Nikol | -0.567 |
chest | -0.547 |
Token | and |
Token ID | 290 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
blasphemy | +0.078 |
Goat | +0.075 |
ドラ | +0.070 |
yrinth | +0.068 |
arge | +0.067 |
Neg logit contributions | |
]. | -0.073 |
�� | -0.067 |
Nikol | -0.062 |
Rub | -0.061 |
chest | -0.059 |
Token | explore |
Token ID | 7301 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
blasphemy | +0.046 |
Goat | +0.045 |
ドラ | +0.042 |
arge | +0.041 |
hift | +0.041 |
Neg logit contributions | |
]. | -0.026 |
�� | -0.025 |
Nikol | -0.021 |
Rub | -0.020 |
chest | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
blasphemy | +0.338 |
Goat | +0.324 |
ドラ | +0.306 |
yrinth | +0.300 |
arge | +0.295 |
Neg logit contributions | |
]. | -0.270 |
�� | -0.242 |
Nikol | -0.229 |
Rub | -0.222 |
chest | -0.213 |
Token | For |
Token ID | 1114 |
Feature activation | -6.59e-02 |
Pos logit contributions | |
blasphemy | +0.011 |
Goat | +0.010 |
ドラ | +0.010 |
arge | +0.009 |
hift | +0.009 |
Neg logit contributions | |
]. | -0.009 |
�� | -0.009 |
Nikol | -0.008 |
Rub | -0.008 |
chest | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
]. | +0.045 |
�� | +0.044 |
Nikol | +0.039 |
Rub | +0.038 |
chest | +0.037 |
Neg logit contributions | |
blasphemy | -0.050 |
Goat | -0.048 |
ドラ | -0.046 |
arge | -0.044 |
hift | -0.043 |
Token | sake |
Token ID | 11060 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
blasphemy | +0.113 |
Goat | +0.109 |
ドラ | +0.102 |
arge | +0.098 |
hift | +0.097 |
Neg logit contributions | |
]. | -0.125 |
�� | -0.121 |
Nikol | -0.109 |
Rub | -0.108 |
chest | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
blasphemy | +0.003 |
Goat | +0.003 |
ドラ | +0.003 |
yrinth | +0.003 |
arge | +0.003 |
Neg logit contributions | |
]. | -0.003 |
�� | -0.003 |
Nikol | -0.002 |
Rub | -0.002 |
chest | -0.002 |
Token | comple |
Token ID | 1224 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
blasphemy | +0.286 |
Goat | +0.276 |
ドラ | +0.257 |
arge | +0.248 |
hift | +0.244 |
Neg logit contributions | |
]. | -0.290 |
�� | -0.284 |
Nikol | -0.251 |
Rub | -0.249 |
chest | -0.239 |
Token | teness |
Token ID | 43205 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
blasphemy | +0.017 |
Goat | +0.015 |
ドラ | +0.012 |
arge | +0.010 |
hift | +0.010 |
Neg logit contributions | |
]. | -0.070 |
�� | -0.069 |
Nikol | -0.064 |
Rub | -0.063 |
chest | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
blasphemy | +1.435 |
Goat | +1.376 |
ドラ | +1.232 |
arge | +1.213 |
hift | +1.188 |
Neg logit contributions | |
]. | -1.749 |
�� | -1.736 |
Rub | -1.529 |
Nikol | -1.524 |
chest | -1.476 |
Token | here |
Token ID | 994 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
blasphemy | +0.096 |
Goat | +0.093 |
ドラ | +0.087 |
arge | +0.084 |
hift | +0.083 |
Neg logit contributions | |
]. | -0.074 |
�� | -0.072 |
Nikol | -0.063 |
Rub | -0.062 |
chest | -0.059 |
Token | is |
Token ID | 318 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
]. | +0.456 |
�� | +0.446 |
Nikol | +0.378 |
Rub | +0.373 |
chest | +0.354 |
Neg logit contributions | |
blasphemy | -0.713 |
Goat | -0.692 |
ドラ | -0.650 |
arge | -0.633 |
hift | -0.626 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
blasphemy | +0.265 |
Goat | +0.257 |
ドラ | +0.239 |
arge | +0.232 |
hift | +0.229 |
Neg logit contributions | |
]. | -0.219 |
�� | -0.215 |
Nikol | -0.187 |
Rub | -0.185 |
chest | -0.177 |
Token | real |
Token ID | 1103 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
blasphemy | +0.166 |
Goat | +0.160 |
ドラ | +0.151 |
arge | +0.146 |
hift | +0.144 |
Neg logit contributions | |
]. | -0.150 |
�� | -0.146 |
Nikol | -0.130 |
Rub | -0.127 |
chest | -0.122 |
Token | first |
Token ID | 717 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
blasphemy | +0.208 |
Goat | +0.197 |
ドラ | +0.187 |
arge | +0.180 |
hift | +0.180 |
Neg logit contributions | |
]. | -0.221 |
�� | -0.213 |
Nikol | -0.190 |
Rub | -0.188 |
chest | -0.183 |
Token | to |
Token ID | 284 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
blasphemy | +0.131 |
Goat | +0.127 |
ドラ | +0.120 |
arge | +0.115 |
hift | +0.115 |
Neg logit contributions | |
]. | -0.091 |
�� | -0.087 |
Nikol | -0.076 |
Rub | -0.075 |
addle | -0.072 |
Token | hear |
Token ID | 3285 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
blasphemy | +0.382 |
Goat | +0.370 |
ドラ | +0.349 |
arge | +0.348 |
hift | +0.340 |
Neg logit contributions | |
�� | -0.153 |
]. | -0.152 |
Nikol | -0.117 |
Rub | -0.114 |
ItemTracker | -0.105 |
Token | about |
Token ID | 546 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
blasphemy | +0.026 |
Goat | +0.025 |
ドラ | +0.024 |
arge | +0.023 |
yrinth | +0.023 |
Neg logit contributions | |
]. | -0.015 |
�� | -0.014 |
Nikol | -0.012 |
Rub | -0.012 |
addle | -0.011 |
Token | Nation |
Token ID | 8741 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
blasphemy | +0.272 |
Goat | +0.263 |
ドラ | +0.244 |
arge | +0.234 |
eeks | +0.230 |
Neg logit contributions | |
]. | -0.311 |
�� | -0.302 |
Nikol | -0.271 |
Rub | -0.267 |
addle | -0.260 |
Token | Travels |
Token ID | 48899 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
]. | +0.014 |
�� | +0.014 |
Nikol | +0.012 |
Rub | +0.012 |
chest | +0.011 |
Neg logit contributions | |
blasphemy | -0.018 |
Goat | -0.017 |
ドラ | -0.016 |
arge | -0.016 |
hift | -0.015 |
Token | destinations |
Token ID | 23982 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
blasphemy | +0.783 |
Goat | +0.730 |
ドラ | +0.613 |
arge | +0.571 |
hift | +0.545 |
Neg logit contributions | |
]. | -2.333 |
�� | -2.321 |
Nikol | -2.125 |
Rub | -2.118 |
chest | -2.066 |
Token | , |
Token ID | 11 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
blasphemy | +0.612 |
Goat | +0.586 |
ドラ | +0.540 |
arge | +0.521 |
yrinth | +0.518 |
Neg logit contributions | |
]. | -0.727 |
�� | -0.700 |
Nikol | -0.639 |
Rub | -0.631 |
addle | -0.614 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
blasphemy | +0.201 |
Goat | +0.196 |
ドラ | +0.180 |
arge | +0.174 |
yrinth | +0.173 |
Neg logit contributions | |
]. | -0.198 |
�� | -0.185 |
Nikol | -0.169 |
Rub | -0.164 |
addle | -0.161 |
Token | explore |
Token ID | 7301 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
blasphemy | +0.210 |
Goat | +0.204 |
ドラ | +0.191 |
arge | +0.187 |
hift | +0.185 |
Neg logit contributions | |
]. | -0.123 |
�� | -0.119 |
Nikol | -0.100 |
Rub | -0.098 |
addle | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
blasphemy | +0.387 |
Goat | +0.371 |
ドラ | +0.347 |
arge | +0.339 |
hift | +0.333 |
Neg logit contributions | |
]. | -0.338 |
�� | -0.322 |
Nikol | -0.289 |
Rub | -0.283 |
chest | -0.273 |
Token | Cabinet |
Token ID | 20384 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
blasphemy | +0.146 |
Goat | +0.140 |
ドラ | +0.131 |
arge | +0.126 |
hift | +0.125 |
Neg logit contributions | |
]. | -0.140 |
�� | -0.136 |
Nikol | -0.120 |
Rub | -0.119 |
chest | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
]. | +0.251 |
�� | +0.242 |
Nikol | +0.219 |
Rub | +0.215 |
chest | +0.207 |
Neg logit contributions | |
blasphemy | -0.241 |
Goat | -0.232 |
ドラ | -0.216 |
arge | -0.207 |
hift | -0.205 |
Token | Today |
Token ID | 6288 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
blasphemy | +0.012 |
Goat | +0.012 |
ドラ | +0.011 |
arge | +0.011 |
hift | +0.011 |
Neg logit contributions | |
]. | -0.009 |
�� | -0.008 |
Nikol | -0.007 |
Rub | -0.007 |
chest | -0.007 |
Token | Cabinet |
Token ID | 20384 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
blasphemy | +0.301 |
Goat | +0.288 |
ドラ | +0.267 |
arge | +0.256 |
hift | +0.252 |
Neg logit contributions | |
]. | -0.354 |
�� | -0.345 |
Nikol | -0.310 |
Rub | -0.306 |
addle | -0.295 |
Token | Ch |
Token ID | 609 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
]. | +0.163 |
�� | +0.157 |
Nikol | +0.138 |
Rub | +0.136 |
addle | +0.128 |
Neg logit contributions | |
blasphemy | -0.216 |
Goat | -0.209 |
ドラ | -0.196 |
arge | -0.190 |
hift | -0.188 |
Token | aired |
Token ID | 9820 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
blasphemy | +0.475 |
Goat | +0.459 |
ドラ | +0.426 |
arge | +0.412 |
hift | +0.408 |
Neg logit contributions | |
]. | -0.420 |
�� | -0.412 |
Nikol | -0.360 |
Rub | -0.356 |
chest | -0.341 |
Token | by |
Token ID | 416 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
blasphemy | +1.448 |
Goat | +1.402 |
ドラ | +1.275 |
arge | +1.242 |
hift | +1.220 |
Neg logit contributions | |
]. | -1.647 |
�� | -1.633 |
Nikol | -1.433 |
Rub | -1.428 |
chest | -1.375 |
Token | Hon |
Token ID | 8835 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
blasphemy | +0.132 |
Goat | +0.127 |
ドラ | +0.119 |
arge | +0.115 |
hift | +0.113 |
Neg logit contributions | |
]. | -0.124 |
�� | -0.120 |
Nikol | -0.107 |
Rub | -0.105 |
chest | -0.101 |
Token | � |
Token ID | 447 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
]. | +0.116 |
�� | +0.115 |
Nikol | +0.101 |
Rub | +0.100 |
addle | +0.097 |
Neg logit contributions | |
blasphemy | -0.104 |
Goat | -0.100 |
ドラ | -0.090 |
arge | -0.089 |
dot | -0.087 |
Token | � |
Token ID | 247 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
blasphemy | +0.052 |
Goat | +0.050 |
ドラ | +0.047 |
arge | +0.045 |
hift | +0.045 |
Neg logit contributions | |
]. | -0.044 |
�� | -0.044 |
Nikol | -0.038 |
Rub | -0.037 |
chest | -0.036 |
Token | ble |
Token ID | 903 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
blasphemy | +0.053 |
Goat | +0.051 |
ドラ | +0.047 |
arge | +0.046 |
hift | +0.045 |
Neg logit contributions | |
]. | -0.054 |
�� | -0.052 |
Nikol | -0.047 |
Rub | -0.046 |
chest | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
blasphemy | +0.461 |
Goat | +0.444 |
ドラ | +0.411 |
arge | +0.398 |
hift | +0.392 |
Neg logit contributions | |
]. | -0.446 |
�� | -0.438 |
Nikol | -0.386 |
Rub | -0.381 |
chest | -0.366 |
Token | including |
Token ID | 1390 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
blasphemy | +0.165 |
Goat | +0.160 |
ドラ | +0.150 |
arge | +0.145 |
hift | +0.144 |
Neg logit contributions | |
]. | -0.119 |
�� | -0.114 |
Nikol | -0.099 |
Rub | -0.098 |
chest | -0.093 |
Token | � |
Token ID | 564 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
blasphemy | +0.032 |
Goat | +0.031 |
ドラ | +0.029 |
arge | +0.028 |
hift | +0.028 |
Neg logit contributions | |
]. | -0.032 |
�� | -0.031 |
Nikol | -0.027 |
Rub | -0.027 |
chest | -0.026 |
Token | � |
Token ID | 250 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
]. | +0.074 |
�� | +0.072 |
Rub | +0.060 |
Nikol | +0.059 |
chest | +0.056 |
Neg logit contributions | |
blasphemy | -0.126 |
Goat | -0.123 |
ドラ | -0.115 |
arge | -0.112 |
hift | -0.111 |
Token | ex |
Token ID | 1069 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
]. | +0.123 |
�� | +0.118 |
Rub | +0.105 |
Nikol | +0.104 |
chest | +0.102 |
Neg logit contributions | |
blasphemy | -0.135 |
Goat | -0.131 |
ドラ | -0.121 |
arge | -0.116 |
hift | -0.115 |
Token | amples |
Token ID | 12629 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
]. | +0.294 |
�� | +0.286 |
Nikol | +0.252 |
Rub | +0.251 |
chest | +0.243 |
Neg logit contributions | |
blasphemy | -0.317 |
Goat | -0.305 |
ドラ | -0.282 |
arge | -0.273 |
hift | -0.269 |
Token | of |
Token ID | 286 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
blasphemy | +1.479 |
Goat | +1.430 |
ドラ | +1.310 |
arge | +1.271 |
hift | +1.252 |
Neg logit contributions | |
]. | -1.568 |
�� | -1.551 |
Nikol | -1.364 |
Rub | -1.351 |
addle | -1.301 |
Token | promising |
Token ID | 11781 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
blasphemy | +0.048 |
Goat | +0.046 |
ドラ | +0.043 |
arge | +0.041 |
hift | +0.041 |
Neg logit contributions | |
]. | -0.052 |
�� | -0.049 |
Nikol | -0.045 |
Rub | -0.044 |
chest | -0.042 |
Token | practices |
Token ID | 6593 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
]. | +0.050 |
�� | +0.047 |
Nikol | +0.043 |
Rub | +0.043 |
chest | +0.041 |
Neg logit contributions | |
blasphemy | -0.040 |
Goat | -0.038 |
ドラ | -0.035 |
arge | -0.034 |
eeks | -0.033 |
Token | � |
Token ID | 447 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
]. | +0.285 |
�� | +0.277 |
Nikol | +0.247 |
Rub | +0.243 |
chest | +0.233 |
Neg logit contributions | |
blasphemy | -0.289 |
Goat | -0.277 |
ドラ | -0.257 |
arge | -0.249 |
hift | -0.245 |
Token | � |
Token ID | 251 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
]. | +0.035 |
�� | +0.034 |
Rub | +0.028 |
Nikol | +0.028 |
chest | +0.026 |
Neg logit contributions | |
blasphemy | -0.057 |
Goat | -0.055 |
ドラ | -0.052 |
arge | -0.051 |
yrinth | -0.050 |
Token | with |
Token ID | 351 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
blasphemy | +0.073 |
Goat | +0.071 |
ドラ | +0.067 |
arge | +0.064 |
hift | +0.063 |
Neg logit contributions | |
]. | -0.066 |
�� | -0.064 |
Nikol | -0.057 |
Rub | -0.056 |
chest | -0.053 |
Token | just |
Token ID | 655 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
]. | +0.100 |
�� | +0.098 |
Nikol | +0.087 |
Rub | +0.085 |
chest | +0.081 |
Neg logit contributions | |
blasphemy | -0.114 |
Goat | -0.109 |
ドラ | -0.103 |
arge | -0.100 |
hift | -0.098 |
Token | your |
Token ID | 534 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
]. | +0.002 |
�� | +0.002 |
Nikol | +0.001 |
Rub | +0.001 |
addle | +0.001 |
Neg logit contributions | |
blasphemy | -0.002 |
Goat | -0.002 |
ドラ | -0.002 |
arge | -0.002 |
hift | -0.002 |
Token | basic |
Token ID | 4096 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
]. | +0.121 |
�� | +0.118 |
Nikol | +0.105 |
Rub | +0.103 |
chest | +0.099 |
Neg logit contributions | |
blasphemy | -0.135 |
Goat | -0.130 |
ドラ | -0.122 |
arge | -0.118 |
hift | -0.116 |
Token | smartphone |
Token ID | 11745 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
]. | +0.105 |
�� | +0.102 |
Nikol | +0.091 |
Rub | +0.089 |
chest | +0.086 |
Neg logit contributions | |
blasphemy | -0.111 |
Goat | -0.107 |
ドラ | -0.101 |
arge | -0.097 |
hift | -0.095 |
Token | camera |
Token ID | 4676 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
]. | +0.220 |
�� | +0.213 |
Nikol | +0.193 |
Rub | +0.189 |
addle | +0.182 |
Neg logit contributions | |
blasphemy | -0.209 |
Goat | -0.202 |
ドラ | -0.189 |
arge | -0.182 |
yrinth | -0.179 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
blasphemy | +1.407 |
Goat | +1.354 |
ドラ | +1.243 |
arge | +1.202 |
hift | +1.182 |
Neg logit contributions | |
]. | -1.588 |
�� | -1.562 |
Nikol | -1.387 |
Rub | -1.374 |
chest | -1.324 |
Token | And |
Token ID | 843 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
]. | +0.199 |
�� | +0.193 |
Nikol | +0.171 |
Rub | +0.168 |
chest | +0.161 |
Neg logit contributions | |
blasphemy | -0.223 |
Goat | -0.214 |
ドラ | -0.203 |
arge | -0.196 |
yrinth | -0.192 |
Token | ro |
Token ID | 305 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
blasphemy | +0.107 |
Goat | +0.104 |
ドラ | +0.099 |
arge | +0.094 |
yrinth | +0.093 |
Neg logit contributions | |
]. | -0.070 |
�� | -0.066 |
Rub | -0.059 |
Nikol | -0.058 |
chest | -0.056 |
Token | Pan |
Token ID | 15730 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
blasphemy | +0.142 |
Goat | +0.139 |
ドラ | +0.130 |
arge | +0.128 |
yrinth | +0.127 |
Neg logit contributions | |
]. | -0.070 |
�� | -0.065 |
Rub | -0.056 |
Nikol | -0.055 |
chest | -0.051 |
Token | gives |
Token ID | 3607 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
blasphemy | +0.607 |
Goat | +0.588 |
ドラ | +0.552 |
arge | +0.535 |
hift | +0.527 |
Neg logit contributions | |
]. | -0.478 |
�� | -0.465 |
Nikol | -0.408 |
Rub | -0.401 |
chest | -0.381 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
]. | +0.020 |
�� | +0.019 |
Nikol | +0.017 |
Rub | +0.017 |
chest | +0.016 |
Neg logit contributions | |
blasphemy | -0.026 |
Goat | -0.025 |
ドラ | -0.024 |
yrinth | -0.023 |
arge | -0.023 |
Token | boys |
Token ID | 13202 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
]. | +0.386 |
�� | +0.364 |
Rub | +0.341 |
Nikol | +0.333 |
chest | +0.331 |
Neg logit contributions | |
blasphemy | -0.297 |
Goat | -0.286 |
ドラ | -0.258 |
yrinth | -0.242 |
arge | -0.240 |
Token | beware |
Token ID | 40600 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
blasphemy | +0.743 |
Goat | +0.714 |
ドラ | +0.672 |
arge | +0.665 |
hift | +0.655 |
Neg logit contributions | |
�� | -0.427 |
]. | -0.424 |
Rub | -0.356 |
Nikol | -0.351 |
chest | -0.331 |
Token |
|
Token ID | 198 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
]. | +0.017 |
�� | +0.016 |
Nikol | +0.014 |
Rub | +0.014 |
chest | +0.013 |
Neg logit contributions | |
blasphemy | -0.027 |
Goat | -0.026 |
ドラ | -0.025 |
arge | -0.024 |
hift | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
]. | +0.019 |
�� | +0.017 |
Nikol | +0.015 |
Rub | +0.015 |
chest | +0.014 |
Neg logit contributions | |
blasphemy | -0.038 |
Goat | -0.037 |
ドラ | -0.035 |
yrinth | -0.034 |
arge | -0.034 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
blasphemy | +0.059 |
Goat | +0.057 |
ドラ | +0.053 |
arge | +0.051 |
hift | +0.050 |
Neg logit contributions | |
]. | -0.051 |
�� | -0.048 |
Rub | -0.043 |
Nikol | -0.042 |
chest | -0.041 |
Token | : |
Token ID | 25 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
blasphemy | +1.601 |
Goat | +1.529 |
ドラ | +1.442 |
yrinth | +1.392 |
arge | +1.369 |
Neg logit contributions | |
]. | -1.428 |
�� | -1.335 |
Nikol | -1.216 |
Rub | -1.214 |
chest | -1.160 |
Token | j |
Token ID | 474 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
blasphemy | +0.127 |
Goat | +0.123 |
ドラ | +0.114 |
arge | +0.111 |
hift | +0.109 |
Neg logit contributions | |
]. | -0.111 |
�� | -0.109 |
Nikol | -0.095 |
Rub | -0.094 |
chest | -0.090 |
Token | wt |
Token ID | 46569 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
]. | +0.087 |
�� | +0.085 |
Nikol | +0.074 |
Rub | +0.074 |
addle | +0.071 |
Neg logit contributions | |
blasphemy | -0.091 |
Goat | -0.087 |
ドラ | -0.081 |
arge | -0.078 |
hift | -0.077 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
blasphemy | +0.329 |
Goat | +0.318 |
ドラ | +0.294 |
arge | +0.284 |
hift | +0.281 |
Neg logit contributions | |
]. | -0.310 |
�� | -0.304 |
Nikol | -0.267 |
Rub | -0.264 |
chest | -0.254 |
Token | - |
Token ID | 532 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
]. | +0.216 |
�� | +0.213 |
Nikol | +0.186 |
Rub | +0.184 |
chest | +0.177 |
Neg logit contributions | |
blasphemy | -0.227 |
Goat | -0.219 |
ドラ | -0.202 |
arge | -0.196 |
hift | -0.193 |
Token | issues |
Token ID | 2428 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
blasphemy | +0.114 |
Goat | +0.111 |
ドラ | +0.104 |
arge | +0.099 |
hift | +0.098 |
Neg logit contributions | |
]. | -0.130 |
�� | -0.125 |
Nikol | -0.114 |
Rub | -0.112 |
chest | -0.109 |
Token | that |
Token ID | 326 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
blasphemy | +0.055 |
Goat | +0.053 |
ドラ | +0.050 |
arge | +0.048 |
hift | +0.048 |
Neg logit contributions | |
]. | -0.048 |
�� | -0.047 |
Nikol | -0.042 |
Rub | -0.041 |
chest | -0.039 |
Token | dw |
Token ID | 43756 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
]. | +0.024 |
�� | +0.023 |
Nikol | +0.020 |
Rub | +0.020 |
addle | +0.019 |
Neg logit contributions | |
blasphemy | -0.027 |
Goat | -0.026 |
ドラ | -0.025 |
arge | -0.024 |
hift | -0.024 |
Token | elt |
Token ID | 2120 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
blasphemy | +0.010 |
Goat | +0.009 |
ドラ | +0.009 |
arge | +0.008 |
hift | +0.008 |
Neg logit contributions | |
]. | -0.008 |
�� | -0.008 |
Nikol | -0.007 |
Rub | -0.007 |
addle | -0.006 |
Token | un |
Token ID | 555 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
]. | +0.372 |
�� | +0.364 |
Nikol | +0.319 |
Rub | +0.315 |
chest | +0.304 |
Neg logit contributions | |
blasphemy | -0.415 |
Goat | -0.403 |
ドラ | -0.374 |
arge | -0.362 |
hift | -0.358 |
Token | spoken |
Token ID | 19842 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
blasphemy | +0.692 |
Goat | +0.672 |
ドラ | +0.628 |
arge | +0.615 |
hift | +0.605 |
Neg logit contributions | |
]. | -0.471 |
�� | -0.467 |
Nikol | -0.394 |
Rub | -0.388 |
chest | -0.367 |
Token | at |
Token ID | 379 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
blasphemy | +1.539 |
Goat | +1.481 |
ドラ | +1.361 |
arge | +1.330 |
hift | +1.306 |
Neg logit contributions | |
]. | -1.434 |
�� | -1.423 |
Nikol | -1.232 |
Rub | -1.223 |
addle | -1.170 |
Token | the |
Token ID | 262 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
blasphemy | +0.137 |
Goat | +0.132 |
ドラ | +0.124 |
arge | +0.120 |
hift | +0.119 |
Neg logit contributions | |
]. | -0.128 |
�� | -0.125 |
Nikol | -0.112 |
Rub | -0.109 |
chest | -0.105 |
Token | heart |
Token ID | 2612 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
blasphemy | +0.085 |
Goat | +0.082 |
ドラ | +0.078 |
hift | +0.076 |
arge | +0.075 |
Neg logit contributions | |
]. | -0.068 |
�� | -0.066 |
Nikol | -0.059 |
Rub | -0.057 |
chest | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
blasphemy | +0.238 |
Goat | +0.231 |
ドラ | +0.216 |
arge | +0.207 |
hift | +0.206 |
Neg logit contributions | |
]. | -0.209 |
�� | -0.198 |
Nikol | -0.178 |
Rub | -0.177 |
chest | -0.172 |
Token | Lovecraft |
Token ID | 37655 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
blasphemy | +0.122 |
Goat | +0.118 |
ドラ | +0.112 |
arge | +0.108 |
hift | +0.107 |
Neg logit contributions | |
]. | -0.115 |
�� | -0.110 |
Nikol | -0.100 |
Rub | -0.097 |
chest | -0.093 |
Token | comments |
Token ID | 3651 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
]. | +0.164 |
�� | +0.159 |
Nikol | +0.143 |
Rub | +0.141 |
chest | +0.136 |
Neg logit contributions | |
blasphemy | -0.150 |
Goat | -0.145 |
ドラ | -0.133 |
arge | -0.128 |
yrinth | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
]. | +0.038 |
�� | +0.037 |
Nikol | +0.033 |
Rub | +0.033 |
chest | +0.031 |
Neg logit contributions | |
blasphemy | -0.039 |
Goat | -0.038 |
ドラ | -0.035 |
arge | -0.034 |
hift | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -5.60e-04 |
Pos logit contributions | |
blasphemy | +0.211 |
Goat | +0.205 |
ドラ | +0.190 |
arge | +0.185 |
hift | +0.183 |
Neg logit contributions | |
]. | -0.164 |
�� | -0.161 |
Nikol | -0.139 |
Rub | -0.137 |
chest | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
]. | +0.000 |
�� | +0.000 |
Nikol | +0.000 |
Rub | +0.000 |
chest | +0.000 |
Neg logit contributions | |
blasphemy | -0.001 |
Goat | -0.001 |
ドラ | -0.000 |
arge | -0.000 |
hift | -0.000 |
Token | High |
Token ID | 11922 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
blasphemy | +0.012 |
Goat | +0.012 |
ドラ | +0.011 |
arge | +0.010 |
hift | +0.010 |
Neg logit contributions | |
]. | -0.012 |
�� | -0.011 |
Rub | -0.010 |
Nikol | -0.010 |
chest | -0.010 |
Token | lights |
Token ID | 8091 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
]. | +0.341 |
�� | +0.332 |
Nikol | +0.295 |
Rub | +0.291 |
chest | +0.279 |
Neg logit contributions | |
blasphemy | -0.372 |
Goat | -0.360 |
ドラ | -0.335 |
arge | -0.325 |
hift | -0.320 |
Token | of |
Token ID | 286 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
blasphemy | +1.608 |
Goat | +1.564 |
ドラ | +1.439 |
arge | +1.408 |
hift | +1.397 |
Neg logit contributions | |
]. | -1.309 |
�� | -1.299 |
Nikol | -1.107 |
Rub | -1.104 |
chest | -1.062 |
Token | this |
Token ID | 428 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.069 |
ドラ | +0.064 |
arge | +0.062 |
hift | +0.062 |
Neg logit contributions | |
]. | -0.063 |
�� | -0.061 |
Nikol | -0.054 |
Rub | -0.053 |
chest | -0.051 |
Token | new |
Token ID | 649 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
blasphemy | +0.172 |
Goat | +0.165 |
ドラ | +0.154 |
arge | +0.149 |
hift | +0.146 |
Neg logit contributions | |
]. | -0.162 |
�� | -0.158 |
Nikol | -0.139 |
Rub | -0.138 |
chest | -0.132 |
Token | release |
Token ID | 2650 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.069 |
ドラ | +0.064 |
arge | +0.061 |
hift | +0.060 |
Neg logit contributions | |
]. | -0.079 |
�� | -0.077 |
Nikol | -0.069 |
Rub | -0.068 |
chest | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
blasphemy | +0.467 |
Goat | +0.453 |
ドラ | +0.423 |
arge | +0.412 |
hift | +0.407 |
Neg logit contributions | |
]. | -0.333 |
�� | -0.326 |
Nikol | -0.279 |
Rub | -0.276 |
chest | -0.263 |
Token | bad |
Token ID | 2089 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
blasphemy | +0.092 |
Goat | +0.091 |
ドラ | +0.087 |
yrinth | +0.083 |
eeks | +0.081 |
Neg logit contributions | |
]. | -0.095 |
�� | -0.086 |
Nikol | -0.081 |
Rub | -0.081 |
chest | -0.077 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
blasphemy | +0.202 |
Goat | +0.196 |
ドラ | +0.184 |
yrinth | +0.179 |
arge | +0.176 |
Neg logit contributions | |
]. | -0.203 |
�� | -0.188 |
Nikol | -0.175 |
Rub | -0.172 |
addle | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
]. | +0.152 |
�� | +0.137 |
Nikol | +0.127 |
Rub | +0.127 |
chest | +0.121 |
Neg logit contributions | |
blasphemy | -0.165 |
Goat | -0.158 |
ドラ | -0.150 |
yrinth | -0.144 |
arge | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
blasphemy | +0.073 |
Goat | +0.071 |
ドラ | +0.065 |
arge | +0.064 |
dot | +0.063 |
Neg logit contributions | |
]. | -0.053 |
�� | -0.053 |
Nikol | -0.045 |
Rub | -0.045 |
addle | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
blasphemy | +0.198 |
Goat | +0.192 |
ドラ | +0.183 |
yrinth | +0.178 |
arge | +0.176 |
Neg logit contributions | |
]. | -0.103 |
�� | -0.091 |
Nikol | -0.081 |
Rub | -0.081 |
chest | -0.076 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
blasphemy | +0.188 |
Goat | +0.184 |
ドラ | +0.172 |
yrinth | +0.164 |
hift | +0.162 |
Neg logit contributions | |
]. | -0.145 |
�� | -0.129 |
Rub | -0.127 |
chest | -0.118 |
Nikol | -0.117 |
Token | : |
Token ID | 25 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
blasphemy | +1.525 |
Goat | +1.458 |
ドラ | +1.374 |
yrinth | +1.327 |
arge | +1.306 |
Neg logit contributions | |
]. | -1.363 |
�� | -1.271 |
Nikol | -1.159 |
Rub | -1.155 |
chest | -1.106 |
Token | Mike |
Token ID | 4995 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
blasphemy | +0.100 |
Goat | +0.097 |
ドラ | +0.090 |
arge | +0.087 |
hift | +0.086 |
Neg logit contributions | |
]. | -0.089 |
�� | -0.087 |
Nikol | -0.076 |
Rub | -0.075 |
chest | -0.072 |
Token | M |
Token ID | 44 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
]. | +0.157 |
�� | +0.154 |
Nikol | +0.137 |
Rub | +0.136 |
chest | +0.130 |
Neg logit contributions | |
blasphemy | -0.147 |
Goat | -0.141 |
ドラ | -0.130 |
arge | -0.126 |
hift | -0.124 |
Token | anners |
Token ID | 15672 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
blasphemy | +0.088 |
Goat | +0.081 |
ドラ | +0.065 |
arge | +0.059 |
hift | +0.056 |
Neg logit contributions | |
]. | -0.332 |
�� | -0.329 |
Nikol | -0.304 |
Rub | -0.302 |
chest | -0.295 |
Token | - |
Token ID | 532 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
blasphemy | +0.253 |
Goat | +0.245 |
ドラ | +0.226 |
arge | +0.219 |
hift | +0.216 |
Neg logit contributions | |
]. | -0.248 |
�� | -0.244 |
Nikol | -0.213 |
Rub | -0.211 |
chest | -0.203 |
Token | t |
Token ID | 83 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
]. | +0.104 |
�� | +0.101 |
Nikol | +0.092 |
Rub | +0.092 |
addle | +0.089 |
Neg logit contributions | |
blasphemy | -0.062 |
Goat | -0.058 |
ドラ | -0.052 |
hift | -0.049 |
arge | -0.049 |
Token | seriously |
Token ID | 6411 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
blasphemy | +0.188 |
Goat | +0.183 |
ドラ | +0.172 |
arge | +0.165 |
hift | +0.163 |
Neg logit contributions | |
]. | -0.153 |
�� | -0.145 |
Nikol | -0.130 |
Rub | -0.127 |
chest | -0.123 |
Token | believe |
Token ID | 1975 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
]. | +0.364 |
�� | +0.338 |
Nikol | +0.306 |
Rub | +0.293 |
chest | +0.288 |
Neg logit contributions | |
blasphemy | -0.499 |
Goat | -0.487 |
ドラ | -0.463 |
arge | -0.443 |
yrinth | -0.443 |
Token | that |
Token ID | 326 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
]. | +0.112 |
�� | +0.108 |
Nikol | +0.096 |
Rub | +0.094 |
chest | +0.091 |
Neg logit contributions | |
blasphemy | -0.131 |
Goat | -0.126 |
ドラ | -0.118 |
arge | -0.115 |
hift | -0.113 |
Token | cloud |
Token ID | 6279 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
]. | +0.024 |
�� | +0.023 |
Nikol | +0.021 |
Rub | +0.020 |
chest | +0.019 |
Neg logit contributions | |
blasphemy | -0.030 |
Goat | -0.030 |
ドラ | -0.028 |
arge | -0.027 |
hift | -0.027 |
Token | storage |
Token ID | 6143 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
]. | +0.672 |
�� | +0.640 |
Nikol | +0.586 |
Rub | +0.572 |
chest | +0.552 |
Neg logit contributions | |
blasphemy | -0.720 |
Goat | -0.706 |
ドラ | -0.653 |
arge | -0.630 |
hift | -0.627 |
Token | is |
Token ID | 318 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
blasphemy | +1.582 |
Goat | +1.531 |
ドラ | +1.423 |
arge | +1.385 |
hift | +1.367 |
Neg logit contributions | |
]. | -1.257 |
�� | -1.237 |
Nikol | -1.065 |
Rub | -1.054 |
chest | -1.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.070 |
ドラ | +0.066 |
arge | +0.064 |
hift | +0.063 |
Neg logit contributions | |
]. | -0.061 |
�� | -0.058 |
Nikol | -0.053 |
Rub | -0.052 |
chest | -0.049 |
Token | secure |
Token ID | 5713 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
]. | +0.014 |
�� | +0.014 |
Nikol | +0.012 |
Rub | +0.012 |
chest | +0.012 |
Neg logit contributions | |
blasphemy | -0.014 |
Goat | -0.014 |
ドラ | -0.013 |
arge | -0.012 |
yrinth | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
]. | +0.006 |
�� | +0.005 |
Nikol | +0.005 |
Rub | +0.005 |
chest | +0.005 |
Neg logit contributions | |
blasphemy | -0.005 |
Goat | -0.005 |
ドラ | -0.005 |
arge | -0.004 |
yrinth | -0.004 |
Token | permanent |
Token ID | 7748 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
]. | +0.060 |
�� | +0.058 |
Nikol | +0.052 |
Rub | +0.051 |
chest | +0.048 |
Neg logit contributions | |
blasphemy | -0.066 |
Goat | -0.064 |
ドラ | -0.060 |
arge | -0.058 |
hift | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
blasphemy | +0.123 |
Goat | +0.119 |
ドラ | +0.113 |
yrinth | +0.110 |
arge | +0.109 |
Neg logit contributions | |
]. | -0.064 |
�� | -0.057 |
Nikol | -0.051 |
Rub | -0.050 |
chest | -0.047 |
Token | Sean |
Token ID | 26408 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
blasphemy | +0.106 |
Goat | +0.103 |
ドラ | +0.095 |
arge | +0.091 |
yrinth | +0.091 |
Neg logit contributions | |
]. | -0.098 |
�� | -0.093 |
Rub | -0.085 |
Nikol | -0.083 |
Iv | -0.081 |
Token | Lav |
Token ID | 21438 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
blasphemy | +0.240 |
Goat | +0.232 |
ドラ | +0.217 |
arge | +0.211 |
hift | +0.208 |
Neg logit contributions | |
]. | -0.181 |
�� | -0.177 |
Nikol | -0.153 |
Rub | -0.151 |
chest | -0.144 |
Token | au |
Token ID | 559 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
blasphemy | +0.168 |
Goat | +0.158 |
ドラ | +0.147 |
hift | +0.133 |
yrinth | +0.133 |
Neg logit contributions | |
]. | -0.261 |
�� | -0.250 |
Nikol | -0.232 |
Rub | -0.230 |
chest | -0.228 |
Token | h |
Token ID | 289 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
]. | +0.270 |
�� | +0.262 |
Nikol | +0.231 |
Rub | +0.228 |
chest | +0.218 |
Neg logit contributions | |
blasphemy | -0.324 |
Goat | -0.313 |
ドラ | -0.293 |
arge | -0.283 |
hift | -0.280 |
Token | iked |
Token ID | 17951 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
blasphemy | +0.391 |
Goat | +0.380 |
ドラ | +0.352 |
arge | +0.346 |
hift | +0.339 |
Neg logit contributions | |
]. | -0.305 |
�� | -0.302 |
Nikol | -0.258 |
Rub | -0.255 |
chest | -0.243 |
Token | to |
Token ID | 284 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
blasphemy | +1.511 |
Goat | +1.469 |
ドラ | +1.340 |
arge | +1.314 |
hift | +1.300 |
Neg logit contributions | |
]. | -1.315 |
�� | -1.308 |
Nikol | -1.118 |
Rub | -1.115 |
chest | -1.071 |
Token | the |
Token ID | 262 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
blasphemy | +0.331 |
Goat | +0.320 |
ドラ | +0.296 |
arge | +0.288 |
hift | +0.284 |
Neg logit contributions | |
]. | -0.298 |
�� | -0.293 |
Nikol | -0.255 |
Rub | -0.253 |
chest | -0.243 |
Token | bottom |
Token ID | 4220 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
blasphemy | +0.208 |
Goat | +0.201 |
ドラ | +0.188 |
arge | +0.181 |
hift | +0.179 |
Neg logit contributions | |
]. | -0.194 |
�� | -0.190 |
Nikol | -0.168 |
Rub | -0.166 |
chest | -0.159 |
Token | of |
Token ID | 286 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
blasphemy | +0.215 |
Goat | +0.207 |
ドラ | +0.190 |
arge | +0.185 |
hift | +0.182 |
Neg logit contributions | |
]. | -0.213 |
�� | -0.211 |
Nikol | -0.184 |
Rub | -0.183 |
chest | -0.176 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
blasphemy | +0.269 |
Goat | +0.261 |
ドラ | +0.237 |
arge | +0.231 |
hift | +0.227 |
Neg logit contributions | |
]. | -0.274 |
�� | -0.271 |
Nikol | -0.236 |
Rub | -0.235 |
chest | -0.226 |
Token | cut |
Token ID | 2005 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
blasphemy | +0.088 |
Goat | +0.086 |
ドラ | +0.080 |
arge | +0.078 |
hift | +0.077 |
Neg logit contributions | |
]. | -0.072 |
�� | -0.069 |
Nikol | -0.061 |
Rub | -0.061 |
chest | -0.058 |
Token | off |
Token ID | 572 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
blasphemy | +0.194 |
Goat | +0.187 |
ドラ | +0.172 |
arge | +0.167 |
hift | +0.164 |
Neg logit contributions | |
]. | -0.203 |
�� | -0.198 |
Nikol | -0.176 |
Rub | -0.175 |
chest | -0.168 |
Token | funding |
Token ID | 4918 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
]. | +0.623 |
�� | +0.594 |
Nikol | +0.544 |
Rub | +0.536 |
chest | +0.519 |
Neg logit contributions | |
blasphemy | -0.557 |
Goat | -0.536 |
ドラ | -0.503 |
arge | -0.482 |
eeks | -0.477 |
Token | for |
Token ID | 329 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
blasphemy | +0.793 |
Goat | +0.767 |
ドラ | +0.710 |
arge | +0.690 |
hift | +0.680 |
Neg logit contributions | |
]. | -0.708 |
�� | -0.696 |
Nikol | -0.607 |
Rub | -0.600 |
chest | -0.576 |
Token | Planned |
Token ID | 18451 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
]. | +0.086 |
�� | +0.082 |
Nikol | +0.075 |
Rub | +0.074 |
chest | +0.072 |
Neg logit contributions | |
blasphemy | -0.076 |
Goat | -0.073 |
ドラ | -0.068 |
arge | -0.065 |
hift | -0.065 |
Token | Parenthood |
Token ID | 18461 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
]. | +0.117 |
�� | +0.110 |
Rub | +0.102 |
Nikol | +0.101 |
chest | +0.096 |
Neg logit contributions | |
blasphemy | -0.117 |
Goat | -0.112 |
ドラ | -0.106 |
yrinth | -0.103 |
hift | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
blasphemy | +1.315 |
Goat | +1.266 |
ドラ | +1.161 |
arge | +1.123 |
hift | +1.106 |
Neg logit contributions | |
]. | -1.493 |
�� | -1.467 |
Nikol | -1.304 |
Rub | -1.292 |
chest | -1.246 |
Token | Clinton |
Token ID | 2605 |
Feature activation | +8.83e-02 |
Pos logit contributions | |
blasphemy | +0.167 |
Goat | +0.162 |
ドラ | +0.151 |
arge | +0.147 |
hift | +0.145 |
Neg logit contributions | |
]. | -0.133 |
�� | -0.130 |
Nikol | -0.113 |
Rub | -0.112 |
chest | -0.107 |
Token | should |
Token ID | 815 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.070 |
ドラ | +0.065 |
arge | +0.063 |
hift | +0.063 |
Neg logit contributions | |
]. | -0.056 |
�� | -0.054 |
Nikol | -0.047 |
Rub | -0.047 |
chest | -0.045 |
Token | be |
Token ID | 307 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
]. | +0.117 |
�� | +0.111 |
Nikol | +0.096 |
Rub | +0.094 |
addle | +0.091 |
Neg logit contributions | |
blasphemy | -0.180 |
Goat | -0.175 |
ドラ | -0.166 |
arge | -0.159 |
hift | -0.158 |
Token | defending |
Token ID | 11749 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
blasphemy | +0.083 |
Goat | +0.081 |
ドラ | +0.075 |
arge | +0.073 |
hift | +0.072 |
Neg logit contributions | |
]. | -0.059 |
�� | -0.058 |
Nikol | -0.050 |
Rub | -0.049 |
chest | -0.047 |
Token | er |
Token ID | 263 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
]. | +0.053 |
�� | +0.048 |
Rub | +0.044 |
Nikol | +0.043 |
chest | +0.043 |
Neg logit contributions | |
blasphemy | -0.072 |
Goat | -0.069 |
ドラ | -0.068 |
yrinth | -0.062 |
dot | -0.061 |
Token | magnet |
Token ID | 19972 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
blasphemy | +0.044 |
Goat | +0.043 |
ドラ | +0.042 |
yrinth | +0.039 |
eeks | +0.039 |
Neg logit contributions | |
]. | -0.043 |
�� | -0.039 |
Nikol | -0.037 |
Rub | -0.037 |
chest | -0.035 |
Token | ? |
Token ID | 30 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
blasphemy | +0.226 |
Goat | +0.219 |
ドラ | +0.205 |
arge | +0.200 |
hift | +0.197 |
Neg logit contributions | |
]. | -0.159 |
�� | -0.156 |
Nikol | -0.133 |
Rub | -0.131 |
addle | -0.125 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
blasphemy | +0.179 |
Goat | +0.175 |
ドラ | +0.162 |
arge | +0.159 |
hift | +0.157 |
Neg logit contributions | |
]. | -0.117 |
�� | -0.115 |
Nikol | -0.097 |
Rub | -0.096 |
addle | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
blasphemy | +0.230 |
Goat | +0.222 |
ドラ | +0.212 |
yrinth | +0.206 |
arge | +0.204 |
Neg logit contributions | |
]. | -0.120 |
�� | -0.106 |
Nikol | -0.095 |
Rub | -0.094 |
chest | -0.088 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
blasphemy | +0.185 |
Goat | +0.179 |
ドラ | +0.166 |
arge | +0.159 |
hift | +0.158 |
Neg logit contributions | |
]. | -0.162 |
�� | -0.155 |
Rub | -0.139 |
Nikol | -0.136 |
chest | -0.132 |
Token | : |
Token ID | 25 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
blasphemy | +1.505 |
Goat | +1.436 |
ドラ | +1.355 |
yrinth | +1.311 |
arge | +1.288 |
Neg logit contributions | |
]. | -1.337 |
�� | -1.243 |
Nikol | -1.136 |
Rub | -1.134 |
chest | -1.084 |
Token | hey |
Token ID | 17207 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
blasphemy | +0.081 |
Goat | +0.078 |
ドラ | +0.073 |
arge | +0.071 |
hift | +0.070 |
Neg logit contributions | |
]. | -0.072 |
�� | -0.071 |
Nikol | -0.062 |
Rub | -0.061 |
chest | -0.059 |
Token | _ |
Token ID | 62 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
]. | +0.059 |
�� | +0.057 |
Nikol | +0.051 |
Rub | +0.050 |
chest | +0.049 |
Neg logit contributions | |
blasphemy | -0.060 |
Goat | -0.058 |
ドラ | -0.054 |
arge | -0.052 |
hift | -0.051 |
Token | ler |
Token ID | 1754 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
blasphemy | +0.466 |
Goat | +0.449 |
ドラ | +0.415 |
arge | +0.402 |
hift | +0.396 |
Neg logit contributions | |
]. | -0.452 |
�� | -0.444 |
Nikol | -0.390 |
Rub | -0.387 |
chest | -0.373 |
Token | oy |
Token ID | 726 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
]. | +0.102 |
�� | +0.099 |
Nikol | +0.088 |
Rub | +0.088 |
addle | +0.085 |
Neg logit contributions | |
blasphemy | -0.100 |
Goat | -0.095 |
ドラ | -0.089 |
arge | -0.084 |
hift | -0.084 |
Token | average |
Token ID | 2811 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
blasphemy | +0.760 |
Goat | +0.733 |
ドラ | +0.674 |
arge | +0.652 |
hift | +0.641 |
Neg logit contributions | |
]. | -0.831 |
�� | -0.813 |
Nikol | -0.722 |
Rub | -0.717 |
chest | -0.688 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
]. | +0.331 |
�� | +0.322 |
Nikol | +0.287 |
Rub | +0.285 |
chest | +0.273 |
Neg logit contributions | |
blasphemy | -0.312 |
Goat | -0.301 |
ドラ | -0.280 |
arge | -0.268 |
hift | -0.263 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
]. | +0.116 |
�� | +0.113 |
Nikol | +0.096 |
Rub | +0.095 |
chest | +0.090 |
Neg logit contributions | |
blasphemy | -0.169 |
Goat | -0.164 |
ドラ | -0.153 |
arge | -0.150 |
hift | -0.148 |
Token | H |
Token ID | 39 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
]. | +0.059 |
�� | +0.058 |
Rub | +0.051 |
Nikol | +0.051 |
chest | +0.049 |
Neg logit contributions | |
blasphemy | -0.066 |
Goat | -0.064 |
ドラ | -0.059 |
arge | -0.057 |
hift | -0.056 |
Token | omew |
Token ID | 28030 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
blasphemy | +0.317 |
Goat | +0.306 |
ドラ | +0.283 |
arge | +0.275 |
hift | +0.271 |
Neg logit contributions | |
]. | -0.299 |
�� | -0.294 |
Nikol | -0.257 |
Rub | -0.255 |
chest | -0.245 |
Token | orld |
Token ID | 1764 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
]. | +0.364 |
�� | +0.358 |
Nikol | +0.323 |
Rub | +0.320 |
chest | +0.313 |
Neg logit contributions | |
blasphemy | -0.252 |
Goat | -0.238 |
ドラ | -0.219 |
arge | -0.206 |
hift | -0.204 |
Token | : |
Token ID | 25 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
blasphemy | +1.430 |
Goat | +1.384 |
ドラ | +1.269 |
arge | +1.237 |
hift | +1.216 |
Neg logit contributions | |
]. | -1.354 |
�� | -1.339 |
Nikol | -1.166 |
Rub | -1.158 |
chest | -1.109 |
Token | Game |
Token ID | 3776 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
blasphemy | +0.140 |
Goat | +0.135 |
ドラ | +0.124 |
arge | +0.121 |
hift | +0.119 |
Neg logit contributions | |
]. | -0.146 |
�� | -0.143 |
Nikol | -0.126 |
Rub | -0.125 |
chest | -0.120 |
Token | of |
Token ID | 286 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
blasphemy | +0.434 |
Goat | +0.418 |
ドラ | +0.387 |
arge | +0.375 |
hift | +0.370 |
Neg logit contributions | |
]. | -0.427 |
�� | -0.420 |
Nikol | -0.370 |
Rub | -0.366 |
chest | -0.352 |
Token | the |
Token ID | 262 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
]. | +0.079 |
�� | +0.077 |
Nikol | +0.068 |
Rub | +0.067 |
chest | +0.064 |
Neg logit contributions | |
blasphemy | -0.092 |
Goat | -0.088 |
ドラ | -0.083 |
arge | -0.081 |
hift | -0.080 |
Token | Year |
Token ID | 6280 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
]. | +0.088 |
�� | +0.085 |
Nikol | +0.077 |
Rub | +0.075 |
chest | +0.073 |
Neg logit contributions | |
blasphemy | -0.084 |
Goat | -0.079 |
ドラ | -0.076 |
arge | -0.073 |
hift | -0.072 |
Token | tobacco |
Token ID | 11219 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
blasphemy | +0.226 |
Goat | +0.218 |
ドラ | +0.202 |
arge | +0.195 |
hift | +0.193 |
Neg logit contributions | |
]. | -0.232 |
�� | -0.226 |
Nikol | -0.201 |
Rub | -0.199 |
chest | -0.191 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
blasphemy | +0.279 |
Goat | +0.270 |
ドラ | +0.249 |
arge | +0.241 |
hift | +0.238 |
Neg logit contributions | |
]. | -0.300 |
�� | -0.292 |
Nikol | -0.261 |
Rub | -0.258 |
addle | -0.248 |
Token | : |
Token ID | 25 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
]. | +0.138 |
�� | +0.137 |
Nikol | +0.119 |
Rub | +0.118 |
chest | +0.114 |
Neg logit contributions | |
blasphemy | -0.138 |
Goat | -0.133 |
ドラ | -0.123 |
arge | -0.119 |
hift | -0.117 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
blasphemy | +0.100 |
Goat | +0.095 |
ドラ | +0.090 |
yrinth | +0.086 |
arge | +0.086 |
Neg logit contributions | |
]. | -0.101 |
�� | -0.092 |
Rub | -0.086 |
Nikol | -0.086 |
chest | -0.082 |
Token | AM |
Token ID | 3001 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
]. | +0.103 |
�� | +0.102 |
Nikol | +0.085 |
Rub | +0.084 |
chest | +0.080 |
Neg logit contributions | |
blasphemy | -0.158 |
Goat | -0.153 |
ドラ | -0.142 |
arge | -0.140 |
hift | -0.138 |
Token | ET |
Token ID | 12152 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
]. | +0.300 |
�� | +0.294 |
Nikol | +0.269 |
Rub | +0.267 |
chest | +0.258 |
Neg logit contributions | |
blasphemy | -0.160 |
Goat | -0.151 |
ドラ | -0.136 |
arge | -0.128 |
hift | -0.125 |
Token | Fri |
Token ID | 19480 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
blasphemy | +1.209 |
Goat | +1.159 |
ドラ | +1.055 |
arge | +1.017 |
hift | +1.000 |
Neg logit contributions | |
]. | -1.576 |
�� | -1.552 |
Nikol | -1.388 |
Rub | -1.377 |
chest | -1.331 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
blasphemy | +0.252 |
Goat | +0.240 |
ドラ | +0.221 |
arge | +0.212 |
hift | +0.210 |
Neg logit contributions | |
]. | -0.299 |
�� | -0.285 |
Nikol | -0.261 |
Rub | -0.261 |
addle | -0.248 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
]. | +0.137 |
�� | +0.129 |
Nikol | +0.115 |
Rub | +0.113 |
chest | +0.106 |
Neg logit contributions | |
blasphemy | -0.197 |
Goat | -0.190 |
ドラ | -0.180 |
arge | -0.175 |
yrinth | -0.173 |
Token | July |
Token ID | 2901 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
]. | +0.025 |
�� | +0.023 |
Nikol | +0.021 |
Rub | +0.021 |
chest | +0.019 |
Neg logit contributions | |
blasphemy | -0.034 |
Goat | -0.033 |
ドラ | -0.031 |
arge | -0.030 |
yrinth | -0.030 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
blasphemy | +0.483 |
Goat | +0.460 |
ドラ | +0.431 |
arge | +0.414 |
yrinth | +0.413 |
Neg logit contributions | |
]. | -0.484 |
�� | -0.467 |
Nikol | -0.421 |
Rub | -0.416 |
chest | -0.395 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
]. | +0.011 |
�� | +0.010 |
Nikol | +0.009 |
Rub | +0.009 |
chest | +0.009 |
Neg logit contributions | |
blasphemy | -0.010 |
Goat | -0.010 |
ドラ | -0.009 |
arge | -0.009 |
hift | -0.009 |
Token | great |
Token ID | 1049 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
]. | +0.008 |
�� | +0.007 |
Nikol | +0.007 |
Rub | +0.006 |
addle | +0.006 |
Neg logit contributions | |
blasphemy | -0.008 |
Goat | -0.008 |
ドラ | -0.007 |
arge | -0.007 |
hift | -0.007 |
Token | � |
Token ID | 564 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
]. | +0.339 |
�� | +0.327 |
Nikol | +0.295 |
Rub | +0.289 |
addle | +0.279 |
Neg logit contributions | |
blasphemy | -0.338 |
Goat | -0.325 |
ドラ | -0.302 |
arge | -0.292 |
eeks | -0.288 |
Token | � |
Token ID | 247 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
blasphemy | +0.237 |
Goat | +0.229 |
ドラ | +0.216 |
arge | +0.210 |
hift | +0.208 |
Neg logit contributions | |
]. | -0.145 |
�� | -0.143 |
Nikol | -0.119 |
Rub | -0.118 |
chest | -0.111 |
Token | jack |
Token ID | 19650 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
blasphemy | +0.036 |
Goat | +0.034 |
ドラ | +0.032 |
arge | +0.031 |
hift | +0.030 |
Neg logit contributions | |
]. | -0.033 |
�� | -0.032 |
Nikol | -0.029 |
Rub | -0.029 |
chest | -0.027 |
Token | marsh |
Token ID | 22397 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
]. | +0.543 |
�� | +0.525 |
Nikol | +0.447 |
Rub | +0.438 |
chest | +0.419 |
Neg logit contributions | |
blasphemy | -0.898 |
Goat | -0.874 |
ドラ | -0.816 |
arge | -0.795 |
hift | -0.788 |
Token | als |
Token ID | 874 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
]. | +2.029 |
�� | +1.965 |
Nikol | +1.805 |
Rub | +1.783 |
addle | +1.757 |
Neg logit contributions | |
blasphemy | -1.260 |
Goat | -1.194 |
ドラ | -1.083 |
hift | -0.998 |
arge | -0.990 |
Token | available |
Token ID | 1695 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
]. | +0.249 |
�� | +0.237 |
Nikol | +0.214 |
Rub | +0.208 |
chest | +0.202 |
Neg logit contributions | |
blasphemy | -0.279 |
Goat | -0.269 |
ドラ | -0.253 |
arge | -0.242 |
yrinth | -0.241 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
blasphemy | +0.533 |
Goat | +0.515 |
ドラ | +0.479 |
arge | +0.461 |
yrinth | +0.455 |
Neg logit contributions | |
]. | -0.507 |
�� | -0.491 |
Nikol | -0.437 |
Rub | -0.430 |
chest | -0.416 |
Token | them |
Token ID | 606 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
]. | +0.092 |
�� | +0.088 |
Nikol | +0.080 |
Rub | +0.079 |
addle | +0.076 |
Neg logit contributions | |
blasphemy | -0.100 |
Goat | -0.096 |
ドラ | -0.088 |
arge | -0.086 |
eeks | -0.086 |
Token | : |
Token ID | 25 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
blasphemy | +0.243 |
Goat | +0.234 |
ドラ | +0.216 |
arge | +0.208 |
yrinth | +0.205 |
Neg logit contributions | |
]. | -0.250 |
�� | -0.243 |
Nikol | -0.217 |
Rub | -0.213 |
chest | -0.207 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
blasphemy | +0.239 |
Goat | +0.232 |
ドラ | +0.217 |
arge | +0.211 |
hift | +0.209 |
Neg logit contributions | |
]. | -0.161 |
�� | -0.158 |
Nikol | -0.134 |
Rub | -0.133 |
chest | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
blasphemy | +0.242 |
Goat | +0.234 |
ドラ | +0.223 |
yrinth | +0.217 |
arge | +0.215 |
Neg logit contributions | |
]. | -0.124 |
�� | -0.109 |
Nikol | -0.098 |
Rub | -0.098 |
chest | -0.092 |
Token | Don |
Token ID | 3987 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
blasphemy | +0.146 |
Goat | +0.141 |
ドラ | +0.131 |
arge | +0.127 |
hift | +0.125 |
Neg logit contributions | |
]. | -0.122 |
�� | -0.116 |
Rub | -0.105 |
Nikol | -0.104 |
chest | -0.099 |
Token | na |
Token ID | 2616 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
blasphemy | +0.490 |
Goat | +0.473 |
ドラ | +0.436 |
arge | +0.423 |
hift | +0.417 |
Neg logit contributions | |
]. | -0.490 |
�� | -0.484 |
Nikol | -0.422 |
Rub | -0.419 |
chest | -0.403 |
Token | 's |
Token ID | 338 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
blasphemy | +0.181 |
Goat | +0.175 |
ドラ | +0.162 |
arge | +0.157 |
hift | +0.155 |
Neg logit contributions | |
]. | -0.166 |
�� | -0.163 |
Nikol | -0.143 |
Rub | -0.141 |
chest | -0.135 |
Token | cub |
Token ID | 13617 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
blasphemy | +0.151 |
Goat | +0.145 |
ドラ | +0.136 |
arge | +0.131 |
hift | +0.129 |
Neg logit contributions | |
]. | -0.132 |
�� | -0.129 |
Nikol | -0.113 |
Rub | -0.112 |
chest | -0.107 |
Token | The |
Token ID | 464 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
]. | +1.476 |
�� | +1.442 |
Nikol | +1.271 |
Rub | +1.255 |
chest | +1.203 |
Neg logit contributions | |
blasphemy | -1.643 |
Goat | -1.581 |
ドラ | -1.473 |
arge | -1.424 |
hift | -1.406 |
Token | Bear |
Token ID | 14732 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
blasphemy | +0.228 |
Goat | +0.220 |
ドラ | +0.204 |
arge | +0.198 |
hift | +0.195 |
Neg logit contributions | |
]. | -0.212 |
�� | -0.209 |
Nikol | -0.183 |
Rub | -0.181 |
chest | -0.174 |
Token | Course |
Token ID | 20537 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
blasphemy | +0.231 |
Goat | +0.222 |
ドラ | +0.206 |
arge | +0.199 |
hift | +0.196 |
Neg logit contributions | |
]. | -0.225 |
�� | -0.221 |
Nikol | -0.194 |
Rub | -0.192 |
chest | -0.185 |
Token | ended |
Token ID | 4444 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
blasphemy | +0.291 |
Goat | +0.281 |
ドラ | +0.261 |
arge | +0.254 |
hift | +0.250 |
Neg logit contributions | |
]. | -0.257 |
�� | -0.252 |
Nikol | -0.220 |
Rub | -0.218 |
chest | -0.209 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
blasphemy | +0.421 |
Goat | +0.407 |
ドラ | +0.378 |
arge | +0.368 |
hift | +0.362 |
Neg logit contributions | |
]. | -0.362 |
�� | -0.355 |
Nikol | -0.310 |
Rub | -0.306 |
chest | -0.294 |
Token | " |
Token ID | 1 |
Feature activation | +8.86e-02 |
Pos logit contributions | |
]. | +0.030 |
�� | +0.028 |
Nikol | +0.026 |
Rub | +0.025 |
chest | +0.024 |
Neg logit contributions | |
blasphemy | -0.029 |
Goat | -0.028 |
ドラ | -0.026 |
arge | -0.025 |
yrinth | -0.025 |
Token | ( |
Token ID | 357 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.069 |
ドラ | +0.065 |
arge | +0.063 |
hift | +0.062 |
Neg logit contributions | |
]. | -0.057 |
�� | -0.056 |
Nikol | -0.048 |
Rub | -0.048 |
chest | -0.046 |
Token | B |
Token ID | 33 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
]. | +0.366 |
�� | +0.355 |
Rub | +0.317 |
Nikol | +0.316 |
chest | +0.303 |
Neg logit contributions | |
blasphemy | -0.373 |
Goat | -0.360 |
ドラ | -0.330 |
arge | -0.322 |
hift | -0.318 |
Token | yr |
Token ID | 2417 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
]. | +0.356 |
�� | +0.344 |
Nikol | +0.308 |
Rub | +0.306 |
addle | +0.293 |
Neg logit contributions | |
blasphemy | -0.377 |
Goat | -0.364 |
ドラ | -0.339 |
hift | -0.323 |
arge | -0.322 |
Token | ds |
Token ID | 9310 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
]. | +0.274 |
�� | +0.264 |
Nikol | +0.235 |
Rub | +0.232 |
addle | +0.224 |
Neg logit contributions | |
blasphemy | -0.320 |
Goat | -0.309 |
ドラ | -0.290 |
arge | -0.277 |
hift | -0.275 |
Token | Cover |
Token ID | 17546 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
]. | +0.290 |
�� | +0.285 |
Nikol | +0.253 |
Rub | +0.251 |
chest | +0.242 |
Neg logit contributions | |
blasphemy | -0.274 |
Goat | -0.263 |
ドラ | -0.244 |
arge | -0.235 |
yrinth | -0.231 |
Token | ) |
Token ID | 8 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
]. | +1.709 |
�� | +1.664 |
Nikol | +1.503 |
Rub | +1.492 |
addle | +1.448 |
Neg logit contributions | |
blasphemy | -1.396 |
Goat | -1.314 |
ドラ | -1.215 |
yrinth | -1.178 |
arge | -1.174 |
Token | ( |
Token ID | 357 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
]. | +0.030 |
�� | +0.030 |
Nikol | +0.025 |
Rub | +0.025 |
addle | +0.024 |
Neg logit contributions | |
blasphemy | -0.043 |
Goat | -0.041 |
ドラ | -0.038 |
arge | -0.037 |
hift | -0.037 |
Token | via |
Token ID | 8869 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
blasphemy | +0.039 |
Goat | +0.038 |
ドラ | +0.035 |
arge | +0.034 |
hift | +0.033 |
Neg logit contributions | |
]. | -0.039 |
�� | -0.038 |
Nikol | -0.034 |
Rub | -0.034 |
chest | -0.032 |
Token | Sound |
Token ID | 9506 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
]. | +0.642 |
�� | +0.618 |
Nikol | +0.560 |
Rub | +0.550 |
chest | +0.527 |
Neg logit contributions | |
blasphemy | -0.639 |
Goat | -0.610 |
ドラ | -0.575 |
arge | -0.556 |
yrinth | -0.545 |
Token | Cloud |
Token ID | 18839 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
]. | +0.765 |
�� | +0.713 |
Nikol | +0.636 |
Rub | +0.627 |
addle | +0.593 |
Neg logit contributions | |
blasphemy | -1.166 |
Goat | -1.125 |
ドラ | -1.075 |
arge | -1.036 |
yrinth | -1.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
]. | +0.467 |
�� | +0.449 |
Nikol | +0.402 |
Rub | +0.395 |
chest | +0.381 |
Neg logit contributions | |
blasphemy | -0.495 |
Goat | -0.479 |
ドラ | -0.451 |
arge | -0.432 |
yrinth | -0.426 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
]. | +0.176 |
�� | +0.171 |
Nikol | +0.149 |
Rub | +0.146 |
chest | +0.140 |
Neg logit contributions | |
blasphemy | -0.232 |
Goat | -0.224 |
ドラ | -0.210 |
arge | -0.204 |
hift | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
]. | +0.082 |
�� | +0.071 |
Nikol | +0.064 |
Rub | +0.064 |
chest | +0.060 |
Neg logit contributions | |
blasphemy | -0.160 |
Goat | -0.155 |
ドラ | -0.148 |
yrinth | -0.145 |
arge | -0.143 |
Token | Faith |
Token ID | 45536 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
]. | +0.078 |
�� | +0.074 |
Rub | +0.066 |
Nikol | +0.065 |
chest | +0.062 |
Neg logit contributions | |
blasphemy | -0.110 |
Goat | -0.107 |
ドラ | -0.099 |
arge | -0.097 |
hift | -0.096 |
Token | 's |
Token ID | 338 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
]. | +0.300 |
�� | +0.293 |
Nikol | +0.257 |
Rub | +0.254 |
chest | +0.243 |
Neg logit contributions | |
blasphemy | -0.340 |
Goat | -0.328 |
ドラ | -0.305 |
arge | -0.296 |
hift | -0.292 |
Token | cub |
Token ID | 13617 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
]. | +0.158 |
�� | +0.153 |
Nikol | +0.136 |
Rub | +0.133 |
chest | +0.128 |
Neg logit contributions | |
blasphemy | -0.184 |
Goat | -0.178 |
ドラ | -0.167 |
arge | -0.161 |
hift | -0.159 |
Token | - |
Token ID | 532 |
Feature activation | -9.07e-02 |
Pos logit contributions | |
]. | +1.401 |
�� | +1.364 |
Nikol | +1.199 |
Rub | +1.185 |
chest | +1.132 |
Neg logit contributions | |
blasphemy | -1.685 |
Goat | -1.624 |
ドラ | -1.521 |
arge | -1.471 |
hift | -1.453 |
Token | 8 |
Token ID | 807 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
]. | +0.054 |
�� | +0.052 |
Nikol | +0.045 |
Rub | +0.044 |
chest | +0.042 |
Neg logit contributions | |
blasphemy | -0.078 |
Goat | -0.076 |
ドラ | -0.071 |
arge | -0.069 |
hift | -0.068 |
Token | / |
Token ID | 14 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
]. | +0.394 |
�� | +0.355 |
Nikol | +0.325 |
Rub | +0.323 |
chest | +0.307 |
Neg logit contributions | |
blasphemy | -0.601 |
Goat | -0.578 |
ドラ | -0.550 |
yrinth | -0.534 |
arge | -0.529 |
Token | 10 |
Token ID | 940 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
blasphemy | +0.153 |
Goat | +0.147 |
ドラ | +0.137 |
arge | +0.133 |
yrinth | +0.132 |
Neg logit contributions | |
]. | -0.128 |
�� | -0.123 |
Nikol | -0.109 |
Rub | -0.109 |
chest | -0.104 |
Token | / |
Token ID | 14 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
blasphemy | +0.154 |
Goat | +0.148 |
ドラ | +0.140 |
yrinth | +0.136 |
arge | +0.136 |
Neg logit contributions | |
]. | -0.105 |
�� | -0.097 |
Rub | -0.087 |
Nikol | -0.087 |
chest | -0.082 |
Token | then |
Token ID | 788 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
]. | +0.214 |
�� | +0.208 |
Nikol | +0.184 |
Rub | +0.180 |
chest | +0.172 |
Neg logit contributions | |
blasphemy | -0.264 |
Goat | -0.255 |
ドラ | -0.239 |
arge | -0.231 |
hift | -0.229 |
Token | rushed |
Token ID | 13999 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
]. | +0.382 |
�� | +0.367 |
Nikol | +0.329 |
Rub | +0.321 |
chest | +0.304 |
Neg logit contributions | |
blasphemy | -0.497 |
Goat | -0.481 |
ドラ | -0.454 |
arge | -0.437 |
yrinth | -0.435 |
Token | him |
Token ID | 683 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
]. | +0.035 |
�� | +0.034 |
Nikol | +0.031 |
Rub | +0.030 |
addle | +0.028 |
Neg logit contributions | |
blasphemy | -0.043 |
Goat | -0.042 |
ドラ | -0.039 |
arge | -0.038 |
yrinth | -0.038 |
Token | with |
Token ID | 351 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
]. | +0.165 |
�� | +0.158 |
Nikol | +0.141 |
Rub | +0.138 |
addle | +0.132 |
Neg logit contributions | |
blasphemy | -0.206 |
Goat | -0.199 |
ドラ | -0.188 |
arge | -0.181 |
yrinth | -0.180 |
Token | guns |
Token ID | 6541 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
]. | +0.204 |
�� | +0.199 |
Nikol | +0.176 |
Rub | +0.173 |
chest | +0.166 |
Neg logit contributions | |
blasphemy | -0.225 |
Goat | -0.218 |
ドラ | -0.203 |
arge | -0.196 |
hift | -0.193 |
Token | drawn |
Token ID | 7428 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
]. | +0.087 |
�� | +0.084 |
Nikol | +0.072 |
Rub | +0.071 |
chest | +0.068 |
Neg logit contributions | |
blasphemy | -0.129 |
Goat | -0.126 |
ドラ | -0.118 |
arge | -0.114 |
yrinth | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
]. | +1.515 |
�� | +1.443 |
Nikol | +1.315 |
Rub | +1.279 |
chest | +1.240 |
Neg logit contributions | |
blasphemy | -1.528 |
Goat | -1.485 |
ドラ | -1.399 |
yrinth | -1.331 |
arge | -1.321 |
Token | One |
Token ID | 1881 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
]. | +0.313 |
�� | +0.305 |
Nikol | +0.268 |
Rub | +0.265 |
chest | +0.253 |
Neg logit contributions | |
blasphemy | -0.362 |
Goat | -0.348 |
ドラ | -0.324 |
arge | -0.316 |
hift | -0.312 |
Token | officer |
Token ID | 3818 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
]. | +0.252 |
�� | +0.245 |
Nikol | +0.219 |
Rub | +0.216 |
chest | +0.207 |
Neg logit contributions | |
blasphemy | -0.250 |
Goat | -0.241 |
ドラ | -0.223 |
arge | -0.215 |
yrinth | -0.212 |
Token | came |
Token ID | 1625 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
blasphemy | +0.024 |
Goat | +0.024 |
ドラ | +0.022 |
arge | +0.021 |
hift | +0.021 |
Neg logit contributions | |
]. | -0.018 |
�� | -0.017 |
Nikol | -0.015 |
Rub | -0.015 |
chest | -0.014 |
Token | from |
Token ID | 422 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
blasphemy | +0.001 |
Goat | +0.001 |
ドラ | +0.001 |
arge | +0.001 |
yrinth | +0.001 |
Neg logit contributions | |
]. | -0.001 |
�� | -0.001 |
Nikol | -0.001 |
Rub | -0.001 |
chest | -0.001 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
]. | +0.146 |
�� | +0.141 |
Nikol | +0.125 |
Rub | +0.123 |
chest | +0.117 |
Neg logit contributions | |
blasphemy | -0.167 |
Goat | -0.160 |
ドラ | -0.151 |
arge | -0.146 |
hift | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
]. | +0.443 |
�� | +0.426 |
Nikol | +0.382 |
Rub | +0.376 |
chest | +0.359 |
Neg logit contributions | |
blasphemy | -0.473 |
Goat | -0.453 |
ドラ | -0.426 |
arge | -0.411 |
hift | -0.405 |
Token |
|
Token ID | 198 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
blasphemy | +0.111 |
Goat | +0.107 |
ドラ | +0.100 |
arge | +0.097 |
hift | +0.096 |
Neg logit contributions | |
]. | -0.085 |
�� | -0.083 |
Nikol | -0.072 |
Rub | -0.071 |
chest | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
blasphemy | +0.126 |
Goat | +0.122 |
ドラ | +0.116 |
yrinth | +0.113 |
arge | +0.112 |
Neg logit contributions | |
]. | -0.065 |
�� | -0.057 |
Nikol | -0.051 |
Rub | -0.051 |
chest | -0.048 |
Token | Bar |
Token ID | 10374 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
blasphemy | +0.059 |
Goat | +0.057 |
ドラ | +0.052 |
arge | +0.051 |
hift | +0.050 |
Neg logit contributions | |
]. | -0.054 |
�� | -0.052 |
Rub | -0.047 |
Nikol | -0.046 |
chest | -0.044 |
Token | ack |
Token ID | 441 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
]. | +0.415 |
�� | +0.403 |
Nikol | +0.355 |
Rub | +0.351 |
chest | +0.338 |
Neg logit contributions | |
blasphemy | -0.477 |
Goat | -0.459 |
ドラ | -0.429 |
arge | -0.412 |
hift | -0.410 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
]. | +1.579 |
�� | +1.509 |
Nikol | +1.377 |
Rub | +1.362 |
chest | +1.299 |
Neg logit contributions | |
blasphemy | -1.477 |
Goat | -1.413 |
ドラ | -1.321 |
arge | -1.250 |
hift | -1.245 |
Token | was |
Token ID | 373 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
blasphemy | +0.012 |
Goat | +0.011 |
ドラ | +0.011 |
arge | +0.010 |
hift | +0.010 |
Neg logit contributions | |
]. | -0.012 |
�� | -0.012 |
Nikol | -0.010 |
Rub | -0.010 |
chest | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
blasphemy | +0.064 |
Goat | +0.062 |
ドラ | +0.058 |
arge | +0.056 |
hift | +0.055 |
Neg logit contributions | |
]. | -0.053 |
�� | -0.052 |
Nikol | -0.045 |
Rub | -0.045 |
chest | -0.043 |
Token | trustee |
Token ID | 36882 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
]. | +0.101 |
�� | +0.099 |
Nikol | +0.088 |
Rub | +0.087 |
chest | +0.083 |
Neg logit contributions | |
blasphemy | -0.100 |
Goat | -0.096 |
ドラ | -0.089 |
arge | -0.086 |
hift | -0.085 |
Token | of |
Token ID | 286 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
]. | +0.554 |
�� | +0.530 |
Nikol | +0.475 |
Rub | +0.464 |
addle | +0.450 |
Neg logit contributions | |
blasphemy | -0.611 |
Goat | -0.586 |
ドラ | -0.553 |
arge | -0.530 |
yrinth | -0.527 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
blasphemy | +0.099 |
Goat | +0.096 |
ドラ | +0.090 |
arge | +0.087 |
hift | +0.085 |
Neg logit contributions | |
]. | -0.087 |
�� | -0.084 |
Nikol | -0.076 |
Rub | -0.074 |
chest | -0.071 |
Token | I |
Token ID | 314 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
blasphemy | +0.132 |
Goat | +0.128 |
ドラ | +0.120 |
arge | +0.117 |
hift | +0.115 |
Neg logit contributions | |
]. | -0.105 |
�� | -0.101 |
Nikol | -0.090 |
Rub | -0.088 |
chest | -0.084 |
Token | went |
Token ID | 1816 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
blasphemy | +0.147 |
Goat | +0.142 |
ドラ | +0.131 |
arge | +0.127 |
hift | +0.126 |
Neg logit contributions | |
]. | -0.134 |
�� | -0.130 |
Nikol | -0.116 |
Rub | -0.114 |
chest | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
blasphemy | +0.022 |
Goat | +0.021 |
ドラ | +0.020 |
arge | +0.020 |
hift | +0.019 |
Neg logit contributions | |
]. | -0.018 |
�� | -0.017 |
Nikol | -0.015 |
Rub | -0.015 |
addle | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
]. | +0.019 |
�� | +0.018 |
Nikol | +0.016 |
Rub | +0.016 |
chest | +0.015 |
Neg logit contributions | |
blasphemy | -0.021 |
Goat | -0.020 |
ドラ | -0.019 |
arge | -0.018 |
hift | -0.018 |
Token | drawing |
Token ID | 8263 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
blasphemy | +0.001 |
Goat | +0.001 |
ドラ | +0.001 |
arge | +0.001 |
hift | +0.001 |
Neg logit contributions | |
]. | -0.002 |
�� | -0.001 |
Nikol | -0.001 |
Rub | -0.001 |
chest | -0.001 |
Token | board |
Token ID | 3096 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
]. | +1.746 |
�� | +1.684 |
Nikol | +1.557 |
Rub | +1.530 |
chest | +1.495 |
Neg logit contributions | |
blasphemy | -1.215 |
Goat | -1.155 |
ドラ | -1.087 |
arge | -1.029 |
hift | -1.008 |
Token | on |
Token ID | 319 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
]. | +0.080 |
�� | +0.078 |
Nikol | +0.070 |
Rub | +0.069 |
chest | +0.066 |
Neg logit contributions | |
blasphemy | -0.080 |
Goat | -0.077 |
ドラ | -0.072 |
arge | -0.069 |
hift | -0.068 |
Token | what |
Token ID | 644 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.069 |
ドラ | +0.065 |
arge | +0.063 |
hift | +0.062 |
Neg logit contributions | |
]. | -0.061 |
�� | -0.059 |
Nikol | -0.052 |
Rub | -0.052 |
chest | -0.049 |
Token | I |
Token ID | 314 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
blasphemy | +0.308 |
Goat | +0.299 |
ドラ | +0.278 |
arge | +0.271 |
hift | +0.268 |
Neg logit contributions | |
]. | -0.228 |
�� | -0.224 |
Nikol | -0.192 |
Rub | -0.190 |
chest | -0.181 |
Token | could |
Token ID | 714 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
blasphemy | +0.114 |
Goat | +0.111 |
ドラ | +0.103 |
arge | +0.100 |
hift | +0.099 |
Neg logit contributions | |
]. | -0.092 |
�� | -0.089 |
Nikol | -0.078 |
Rub | -0.077 |
chest | -0.074 |
Token | campaign |
Token ID | 1923 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
]. | +1.046 |
�� | +1.012 |
Nikol | +0.912 |
Rub | +0.907 |
chest | +0.867 |
Neg logit contributions | |
blasphemy | -0.911 |
Goat | -0.887 |
ドラ | -0.822 |
yrinth | -0.783 |
eeks | -0.782 |
Token | against |
Token ID | 1028 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
blasphemy | +0.203 |
Goat | +0.197 |
ドラ | +0.184 |
arge | +0.176 |
hift | +0.175 |
Neg logit contributions | |
]. | -0.190 |
�� | -0.186 |
Nikol | -0.164 |
Rub | -0.162 |
addle | -0.155 |
Token | his |
Token ID | 465 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
]. | +0.091 |
�� | +0.088 |
Nikol | +0.078 |
Rub | +0.076 |
chest | +0.073 |
Neg logit contributions | |
blasphemy | -0.107 |
Goat | -0.104 |
ドラ | -0.099 |
arge | -0.094 |
hift | -0.094 |
Token | website |
Token ID | 3052 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
]. | +0.033 |
�� | +0.031 |
Nikol | +0.028 |
Rub | +0.027 |
chest | +0.027 |
Neg logit contributions | |
blasphemy | -0.031 |
Goat | -0.030 |
ドラ | -0.029 |
yrinth | -0.028 |
arge | -0.027 |
Token | [ |
Token ID | 685 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
]. | +0.581 |
�� | +0.563 |
Nikol | +0.506 |
Rub | +0.493 |
chest | +0.470 |
Neg logit contributions | |
blasphemy | -0.598 |
Goat | -0.575 |
ドラ | -0.553 |
arge | -0.520 |
hift | -0.519 |
Token | EPA |
Token ID | 40906 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
]. | +0.512 |
�� | +0.483 |
Rub | +0.433 |
Nikol | +0.432 |
chest | +0.413 |
Neg logit contributions | |
blasphemy | -0.542 |
Goat | -0.521 |
ドラ | -0.489 |
arge | -0.468 |
yrinth | -0.462 |
Token | ] |
Token ID | 60 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
]. | +1.143 |
�� | +1.088 |
Nikol | +0.924 |
Rub | +0.915 |
addle | +0.861 |
Neg logit contributions | |
blasphemy | -1.838 |
Goat | -1.786 |
ドラ | -1.690 |
arge | -1.638 |
hift | -1.620 |
Token |
|
Token ID | 198 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
]. | +0.356 |
�� | +0.348 |
Nikol | +0.303 |
Rub | +0.299 |
chest | +0.285 |
Neg logit contributions | |
blasphemy | -0.430 |
Goat | -0.416 |
ドラ | -0.390 |
arge | -0.376 |
hift | -0.372 |
Token |
|
Token ID | 198 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
]. | +0.197 |
�� | +0.170 |
Nikol | +0.154 |
Rub | +0.154 |
chest | +0.143 |
Neg logit contributions | |
blasphemy | -0.390 |
Goat | -0.378 |
ドラ | -0.362 |
yrinth | -0.353 |
arge | -0.347 |
Token | The |
Token ID | 464 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
]. | +0.263 |
�� | +0.246 |
Rub | +0.230 |
Nikol | +0.223 |
Iv | +0.217 |
Neg logit contributions | |
blasphemy | -0.295 |
Goat | -0.285 |
ドラ | -0.264 |
yrinth | -0.253 |
arge | -0.252 |
Token | revelations |
Token ID | 19111 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
]. | +0.168 |
�� | +0.162 |
Nikol | +0.146 |
Rub | +0.143 |
addle | +0.137 |
Neg logit contributions | |
blasphemy | -0.169 |
Goat | -0.163 |
ドラ | -0.156 |
arge | -0.145 |
hift | -0.145 |
Token | we |
Token ID | 356 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
]. | +0.192 |
�� | +0.187 |
Nikol | +0.165 |
Rub | +0.162 |
chest | +0.155 |
Neg logit contributions | |
blasphemy | -0.218 |
Goat | -0.210 |
ドラ | -0.197 |
arge | -0.190 |
hift | -0.187 |
Token | could |
Token ID | 714 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
blasphemy | +0.015 |
Goat | +0.015 |
ドラ | +0.014 |
arge | +0.014 |
hift | +0.013 |
Neg logit contributions | |
]. | -0.010 |
�� | -0.009 |
Nikol | -0.008 |
Rub | -0.008 |
addle | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
]. | +0.441 |
�� | +0.414 |
Nikol | +0.367 |
Rub | +0.358 |
addle | +0.348 |
Neg logit contributions | |
blasphemy | -0.583 |
Goat | -0.566 |
ドラ | -0.538 |
arge | -0.511 |
yrinth | -0.510 |
Token | got |
Token ID | 1392 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
]. | +0.410 |
�� | +0.395 |
Nikol | +0.351 |
Rub | +0.345 |
chest | +0.328 |
Neg logit contributions | |
blasphemy | -0.484 |
Goat | -0.469 |
ドラ | -0.441 |
arge | -0.424 |
hift | -0.419 |
Token | a |
Token ID | 257 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
]. | +0.057 |
�� | +0.055 |
Nikol | +0.049 |
Rub | +0.048 |
addle | +0.046 |
Neg logit contributions | |
blasphemy | -0.073 |
Goat | -0.071 |
ドラ | -0.067 |
arge | -0.064 |
yrinth | -0.064 |
Token | draw |
Token ID | 3197 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
]. | +0.129 |
�� | +0.125 |
Nikol | +0.110 |
Rub | +0.108 |
chest | +0.103 |
Neg logit contributions | |
blasphemy | -0.162 |
Goat | -0.157 |
ドラ | -0.147 |
arge | -0.143 |
hift | -0.141 |
Token | or |
Token ID | 393 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
]. | +1.418 |
�� | +1.316 |
Nikol | +1.207 |
Rub | +1.172 |
chest | +1.149 |
Neg logit contributions | |
blasphemy | -1.502 |
Goat | -1.458 |
ドラ | -1.385 |
yrinth | -1.300 |
arge | -1.294 |
Token | even |
Token ID | 772 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
]. | +0.179 |
�� | +0.172 |
Nikol | +0.153 |
Rub | +0.150 |
chest | +0.144 |
Neg logit contributions | |
blasphemy | -0.215 |
Goat | -0.209 |
ドラ | -0.197 |
arge | -0.188 |
hift | -0.186 |
Token | won |
Token ID | 1839 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
blasphemy | +0.263 |
Goat | +0.255 |
ドラ | +0.239 |
arge | +0.231 |
hift | +0.228 |
Neg logit contributions | |
]. | -0.207 |
�� | -0.201 |
Nikol | -0.176 |
Rub | -0.173 |
chest | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
blasphemy | +0.081 |
Goat | +0.079 |
ドラ | +0.074 |
arge | +0.071 |
yrinth | +0.070 |
Neg logit contributions | |
]. | -0.072 |
�� | -0.069 |
Nikol | -0.062 |
Rub | -0.060 |
addle | -0.058 |
Token | but |
Token ID | 475 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
]. | +0.144 |
�� | +0.139 |
Nikol | +0.126 |
Rub | +0.124 |
chest | +0.120 |
Neg logit contributions | |
blasphemy | -0.125 |
Goat | -0.120 |
ドラ | -0.113 |
arge | -0.107 |
hift | -0.105 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
blasphemy | +0.419 |
Goat | +0.405 |
ドラ | +0.379 |
arge | +0.367 |
hift | +0.363 |
Neg logit contributions | |
]. | -0.322 |
�� | -0.314 |
Nikol | -0.274 |
Rub | -0.269 |
addle | -0.258 |
Token | meet |
Token ID | 1826 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
]. | +0.087 |
�� | +0.084 |
Nikol | +0.074 |
Rub | +0.073 |
addle | +0.070 |
Neg logit contributions | |
blasphemy | -0.108 |
Goat | -0.103 |
ドラ | -0.097 |
arge | -0.094 |
hift | -0.093 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
]. | +0.065 |
�� | +0.062 |
Nikol | +0.056 |
Rub | +0.054 |
chest | +0.052 |
Neg logit contributions | |
blasphemy | -0.075 |
Goat | -0.071 |
ドラ | -0.067 |
arge | -0.065 |
yrinth | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
]. | +0.402 |
�� | +0.389 |
Nikol | +0.349 |
Rub | +0.343 |
chest | +0.331 |
Neg logit contributions | |
blasphemy | -0.411 |
Goat | -0.391 |
ドラ | -0.368 |
arge | -0.353 |
yrinth | -0.349 |
Token | her |
Token ID | 607 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
blasphemy | +0.095 |
Goat | +0.091 |
ドラ | +0.086 |
arge | +0.083 |
hift | +0.082 |
Neg logit contributions | |
]. | -0.080 |
�� | -0.078 |
Nikol | -0.068 |
Rub | -0.067 |
addle | -0.064 |
Token | cub |
Token ID | 13617 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
]. | +0.105 |
�� | +0.102 |
Nikol | +0.091 |
Rub | +0.089 |
chest | +0.086 |
Neg logit contributions | |
blasphemy | -0.109 |
Goat | -0.104 |
ドラ | -0.098 |
arge | -0.094 |
hift | -0.093 |
Token | s |
Token ID | 82 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
]. | +1.369 |
�� | +1.320 |
Nikol | +1.188 |
Rub | +1.166 |
chest | +1.123 |
Neg logit contributions | |
blasphemy | -1.502 |
Goat | -1.428 |
ドラ | -1.345 |
arge | -1.287 |
hift | -1.279 |
Token | . |
Token ID | 13 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
blasphemy | +0.164 |
Goat | +0.158 |
ドラ | +0.147 |
arge | +0.142 |
hift | +0.140 |
Neg logit contributions | |
]. | -0.160 |
�� | -0.157 |
Nikol | -0.139 |
Rub | -0.137 |
chest | -0.132 |
Token |
|
Token ID | 198 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
blasphemy | +0.062 |
Goat | +0.059 |
ドラ | +0.056 |
arge | +0.054 |
hift | +0.054 |
Neg logit contributions | |
]. | -0.050 |
�� | -0.048 |
Nikol | -0.042 |
Rub | -0.042 |
chest | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
]. | +0.013 |
�� | +0.011 |
Nikol | +0.010 |
Rub | +0.010 |
chest | +0.010 |
Neg logit contributions | |
blasphemy | -0.026 |
Goat | -0.025 |
ドラ | -0.024 |
yrinth | -0.023 |
arge | -0.023 |
Token | Thank |
Token ID | 10449 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
]. | +0.018 |
�� | +0.017 |
Rub | +0.016 |
Nikol | +0.015 |
chest | +0.015 |
Neg logit contributions | |
blasphemy | -0.021 |
Goat | -0.020 |
ドラ | -0.018 |
arge | -0.018 |
hift | -0.018 |
Token | hard |
Token ID | 1327 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
]. | +0.089 |
�� | +0.088 |
Nikol | +0.076 |
Rub | +0.075 |
chest | +0.072 |
Neg logit contributions | |
blasphemy | -0.113 |
Goat | -0.110 |
ドラ | -0.102 |
arge | -0.099 |
hift | -0.098 |
Token | liquor |
Token ID | 20030 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
]. | +0.007 |
�� | +0.006 |
Nikol | +0.006 |
Rub | +0.005 |
chest | +0.005 |
Neg logit contributions | |
blasphemy | -0.008 |
Goat | -0.008 |
ドラ | -0.007 |
arge | -0.007 |
hift | -0.007 |
Token | .) |
Token ID | 2014 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
blasphemy | +0.152 |
Goat | +0.146 |
ドラ | +0.135 |
arge | +0.128 |
hift | +0.127 |
Neg logit contributions | |
]. | -0.194 |
�� | -0.189 |
Nikol | -0.171 |
Rub | -0.169 |
chest | -0.163 |
Token | Add |
Token ID | 3060 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
]. | +0.449 |
�� | +0.429 |
Nikol | +0.381 |
Rub | +0.377 |
addle | +0.354 |
Neg logit contributions | |
blasphemy | -0.604 |
Goat | -0.575 |
ドラ | -0.547 |
arge | -0.528 |
yrinth | -0.525 |
Token | more |
Token ID | 517 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
blasphemy | +0.482 |
Goat | +0.467 |
ドラ | +0.431 |
arge | +0.421 |
hift | +0.415 |
Neg logit contributions | |
]. | -0.403 |
�� | -0.398 |
Nikol | -0.343 |
Rub | -0.340 |
chest | -0.325 |
Token | jun |
Token ID | 10891 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
blasphemy | +0.052 |
Goat | +0.051 |
ドラ | +0.047 |
arge | +0.046 |
hift | +0.045 |
Neg logit contributions | |
]. | -0.048 |
�� | -0.047 |
Nikol | -0.041 |
Rub | -0.040 |
chest | -0.039 |
Token | iper |
Token ID | 9346 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
]. | +1.229 |
�� | +1.137 |
Rub | +1.034 |
Nikol | +1.024 |
addle | +0.988 |
Neg logit contributions | |
blasphemy | -1.625 |
Goat | -1.569 |
ドラ | -1.499 |
yrinth | -1.417 |
hift | -1.381 |
Token | infusion |
Token ID | 35547 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
]. | +0.275 |
�� | +0.266 |
Nikol | +0.236 |
Rub | +0.233 |
chest | +0.224 |
Neg logit contributions | |
blasphemy | -0.294 |
Goat | -0.285 |
ドラ | -0.265 |
arge | -0.255 |
hift | -0.253 |
Token | on |
Token ID | 319 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
]. | +0.015 |
�� | +0.015 |
Nikol | +0.013 |
Rub | +0.013 |
addle | +0.013 |
Neg logit contributions | |
blasphemy | -0.015 |
Goat | -0.015 |
ドラ | -0.014 |
arge | -0.013 |
yrinth | -0.013 |
Token | top |
Token ID | 1353 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
]. | +0.018 |
�� | +0.018 |
Nikol | +0.016 |
Rub | +0.015 |
chest | +0.015 |
Neg logit contributions | |
blasphemy | -0.022 |
Goat | -0.021 |
ドラ | -0.020 |
arge | -0.019 |
hift | -0.019 |
Token | as |
Token ID | 355 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
]. | +0.469 |
�� | +0.456 |
Nikol | +0.405 |
Rub | +0.399 |
addle | +0.385 |
Neg logit contributions | |
blasphemy | -0.485 |
Goat | -0.470 |
ドラ | -0.438 |
arge | -0.420 |
yrinth | -0.416 |
Token | Dahl |
Token ID | 41471 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
]. | +0.003 |
�� | +0.003 |
Nikol | +0.003 |
Rub | +0.003 |
chest | +0.003 |
Neg logit contributions | |
blasphemy | -0.004 |
Goat | -0.004 |
ドラ | -0.003 |
arge | -0.003 |
hift | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
]. | +0.219 |
�� | +0.210 |
Nikol | +0.187 |
Rub | +0.184 |
chest | +0.174 |
Neg logit contributions | |
blasphemy | -0.281 |
Goat | -0.271 |
ドラ | -0.254 |
arge | -0.247 |
hift | -0.245 |
Token | back |
Token ID | 736 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
]. | +0.038 |
�� | +0.037 |
Nikol | +0.033 |
Rub | +0.032 |
addle | +0.031 |
Neg logit contributions | |
blasphemy | -0.046 |
Goat | -0.044 |
ドラ | -0.042 |
arge | -0.040 |
yrinth | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
]. | +0.180 |
�� | +0.174 |
Nikol | +0.152 |
Rub | +0.150 |
chest | +0.144 |
Neg logit contributions | |
blasphemy | -0.237 |
Goat | -0.231 |
ドラ | -0.216 |
arge | -0.210 |
hift | -0.206 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
]. | +0.100 |
�� | +0.097 |
Nikol | +0.087 |
Rub | +0.085 |
addle | +0.081 |
Neg logit contributions | |
blasphemy | -0.116 |
Goat | -0.112 |
ドラ | -0.105 |
arge | -0.102 |
hift | -0.100 |
Token | drawing |
Token ID | 8263 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
]. | +0.109 |
�� | +0.106 |
Nikol | +0.094 |
Rub | +0.092 |
chest | +0.088 |
Neg logit contributions | |
blasphemy | -0.130 |
Goat | -0.126 |
ドラ | -0.118 |
arge | -0.114 |
hift | -0.113 |
Token | board |
Token ID | 3096 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
]. | +1.857 |
�� | +1.815 |
Nikol | +1.669 |
Rub | +1.651 |
addle | +1.617 |
Neg logit contributions | |
blasphemy | -0.970 |
Goat | -0.918 |
ドラ | -0.846 |
arge | -0.793 |
hift | -0.775 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
blasphemy | +0.074 |
Goat | +0.071 |
ドラ | +0.067 |
arge | +0.064 |
hift | +0.063 |
Neg logit contributions | |
]. | -0.069 |
�� | -0.068 |
Nikol | -0.060 |
Rub | -0.059 |
addle | -0.057 |
Token | He |
Token ID | 679 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
]. | +0.070 |
�� | +0.068 |
Nikol | +0.060 |
Rub | +0.059 |
chest | +0.057 |
Neg logit contributions | |
blasphemy | -0.082 |
Goat | -0.079 |
ドラ | -0.074 |
arge | -0.072 |
hift | -0.071 |
Token | needed |
Token ID | 2622 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
]. | +0.379 |
�� | +0.362 |
Nikol | +0.322 |
Rub | +0.315 |
chest | +0.301 |
Neg logit contributions | |
blasphemy | -0.499 |
Goat | -0.484 |
ドラ | -0.455 |
arge | -0.441 |
hift | -0.436 |
Token | money |
Token ID | 1637 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
blasphemy | +0.298 |
Goat | +0.288 |
ドラ | +0.269 |
arge | +0.261 |
hift | +0.258 |
Neg logit contributions | |
]. | -0.254 |
�� | -0.248 |
Nikol | -0.217 |
Rub | -0.214 |
chest | -0.205 |
Token | into |
Token ID | 656 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
blasphemy | +0.699 |
Goat | +0.675 |
ドラ | +0.624 |
arge | +0.605 |
hift | +0.595 |
Neg logit contributions | |
]. | -0.682 |
�� | -0.670 |
Nikol | -0.590 |
Rub | -0.583 |
chest | -0.561 |
Token | action |
Token ID | 2223 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
blasphemy | +0.031 |
Goat | +0.030 |
ドラ | +0.028 |
arge | +0.027 |
hift | +0.027 |
Neg logit contributions | |
]. | -0.025 |
�� | -0.024 |
Nikol | -0.021 |
Rub | -0.021 |
addle | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
]. | +0.222 |
�� | +0.216 |
Nikol | +0.194 |
Rub | +0.191 |
addle | +0.183 |
Neg logit contributions | |
blasphemy | -0.215 |
Goat | -0.208 |
ドラ | -0.193 |
arge | -0.186 |
yrinth | -0.184 |
Token | producing |
Token ID | 9194 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
blasphemy | +0.064 |
Goat | +0.062 |
ドラ | +0.058 |
arge | +0.056 |
hift | +0.055 |
Neg logit contributions | |
]. | -0.051 |
�� | -0.050 |
Nikol | -0.043 |
Rub | -0.043 |
chest | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
]. | +0.290 |
�� | +0.281 |
Nikol | +0.248 |
Rub | +0.243 |
chest | +0.231 |
Neg logit contributions | |
blasphemy | -0.361 |
Goat | -0.349 |
ドラ | -0.328 |
arge | -0.319 |
hift | -0.313 |
Token | drawing |
Token ID | 8263 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
blasphemy | +0.092 |
Goat | +0.089 |
ドラ | +0.083 |
arge | +0.081 |
hift | +0.079 |
Neg logit contributions | |
]. | -0.077 |
�� | -0.076 |
Nikol | -0.066 |
Rub | -0.065 |
chest | -0.062 |
Token | or |
Token ID | 393 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
]. | +1.306 |
�� | +1.260 |
Nikol | +1.133 |
Rub | +1.104 |
addle | +1.075 |
Neg logit contributions | |
blasphemy | -1.491 |
Goat | -1.438 |
ドラ | -1.371 |
arge | -1.310 |
eeks | -1.298 |
Token | poem |
Token ID | 21247 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
blasphemy | +0.090 |
Goat | +0.088 |
ドラ | +0.081 |
arge | +0.079 |
hift | +0.078 |
Neg logit contributions | |
]. | -0.073 |
�� | -0.072 |
Nikol | -0.062 |
Rub | -0.062 |
chest | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
blasphemy | +0.332 |
Goat | +0.320 |
ドラ | +0.297 |
arge | +0.287 |
hift | +0.283 |
Neg logit contributions | |
]. | -0.319 |
�� | -0.312 |
Nikol | -0.275 |
Rub | -0.272 |
chest | -0.262 |
Token | about |
Token ID | 546 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
blasphemy | +0.081 |
Goat | +0.079 |
ドラ | +0.074 |
arge | +0.071 |
hift | +0.070 |
Neg logit contributions | |
]. | -0.068 |
�� | -0.066 |
Nikol | -0.058 |
Rub | -0.057 |
chest | -0.055 |
Token | three |
Token ID | 1115 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
blasphemy | +0.063 |
Goat | +0.061 |
ドラ | +0.059 |
arge | +0.056 |
dot | +0.055 |
Neg logit contributions | |
]. | -0.046 |
�� | -0.044 |
Nikol | -0.039 |
Rub | -0.038 |
chest | -0.036 |
Token | 41 |
Token ID | 6073 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
]. | +0.318 |
�� | +0.310 |
Nikol | +0.276 |
Rub | +0.272 |
chest | +0.261 |
Neg logit contributions | |
blasphemy | -0.313 |
Goat | -0.302 |
ドラ | -0.281 |
arge | -0.272 |
hift | -0.268 |
Token | - |
Token ID | 12 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
]. | +0.079 |
�� | +0.077 |
Nikol | +0.068 |
Rub | +0.068 |
chest | +0.065 |
Neg logit contributions | |
blasphemy | -0.084 |
Goat | -0.081 |
ドラ | -0.075 |
arge | -0.073 |
hift | -0.072 |
Token | year |
Token ID | 1941 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
]. | +0.260 |
�� | +0.239 |
Rub | +0.226 |
Nikol | +0.222 |
chest | +0.221 |
Neg logit contributions | |
blasphemy | -0.209 |
Goat | -0.201 |
ドラ | -0.182 |
yrinth | -0.175 |
hift | -0.173 |
Token | - |
Token ID | 12 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
blasphemy | +0.274 |
Goat | +0.264 |
ドラ | +0.247 |
arge | +0.239 |
hift | +0.236 |
Neg logit contributions | |
]. | -0.250 |
�� | -0.242 |
Nikol | -0.215 |
Rub | -0.212 |
chest | -0.203 |
Token | old |
Token ID | 727 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
]. | +0.307 |
�� | +0.256 |
Rub | +0.244 |
chest | +0.240 |
Nikol | +0.237 |
Neg logit contributions | |
blasphemy | -0.515 |
Goat | -0.499 |
ドラ | -0.472 |
yrinth | -0.457 |
hift | -0.447 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
blasphemy | +0.015 |
Goat | +0.015 |
ドラ | +0.014 |
arge | +0.014 |
hift | +0.013 |
Neg logit contributions | |
]. | -0.011 |
�� | -0.010 |
Nikol | -0.009 |
Rub | -0.009 |
chest | -0.008 |
Token | ick |
Token ID | 624 |
Feature activation | +7.99e-02 |
Pos logit contributions | |
]. | +1.008 |
�� | +0.900 |
addle | +0.798 |
Nikol | +0.795 |
Rub | +0.792 |
Neg logit contributions | |
blasphemy | -1.805 |
Goat | -1.769 |
ドラ | -1.673 |
hift | -1.616 |
yrinth | -1.603 |
Token | eter |
Token ID | 2357 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
blasphemy | +0.053 |
Goat | +0.051 |
ドラ | +0.047 |
arge | +0.045 |
hift | +0.044 |
Neg logit contributions | |
]. | -0.063 |
�� | -0.062 |
Nikol | -0.055 |
Rub | -0.055 |
chest | -0.053 |
Token | added |
Token ID | 2087 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
]. | +0.083 |
�� | +0.081 |
Nikol | +0.068 |
Rub | +0.067 |
chest | +0.064 |
Neg logit contributions | |
blasphemy | -0.132 |
Goat | -0.128 |
ドラ | -0.120 |
arge | -0.117 |
hift | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
]. | +0.253 |
�� | +0.252 |
Nikol | +0.221 |
Rub | +0.219 |
chest | +0.212 |
Neg logit contributions | |
blasphemy | -0.227 |
Goat | -0.217 |
ドラ | -0.198 |
arge | -0.192 |
hift | -0.190 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
]. | +0.148 |
�� | +0.146 |
Nikol | +0.122 |
Rub | +0.121 |
chest | +0.116 |
Neg logit contributions | |
blasphemy | -0.224 |
Goat | -0.218 |
ドラ | -0.203 |
arge | -0.198 |
dot | -0.195 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
blasphemy | +0.006 |
Goat | +0.005 |
ドラ | +0.005 |
arge | +0.005 |
hift | +0.005 |
Neg logit contributions | |
]. | -0.004 |
�� | -0.004 |
Nikol | -0.003 |
Rub | -0.003 |
chest | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
]. | +0.007 |
�� | +0.007 |
Nikol | +0.006 |
Rub | +0.006 |
addle | +0.006 |
Neg logit contributions | |
blasphemy | -0.008 |
Goat | -0.008 |
ドラ | -0.008 |
arge | -0.007 |
dot | -0.007 |
Token | turtles |
Token ID | 36288 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
blasphemy | +0.014 |
Goat | +0.014 |
ドラ | +0.013 |
arge | +0.012 |
hift | +0.012 |
Neg logit contributions | |
]. | -0.015 |
�� | -0.015 |
Nikol | -0.013 |
Rub | -0.013 |
chest | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
]. | +0.377 |
�� | +0.360 |
Nikol | +0.312 |
Rub | +0.305 |
addle | +0.287 |
Neg logit contributions | |
blasphemy | -0.645 |
Goat | -0.627 |
ドラ | -0.598 |
arge | -0.574 |
yrinth | -0.572 |
Token | mut |
Token ID | 4517 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
]. | +0.088 |
�� | +0.085 |
Nikol | +0.076 |
Rub | +0.074 |
chest | +0.071 |
Neg logit contributions | |
blasphemy | -0.100 |
Goat | -0.097 |
ドラ | -0.092 |
arge | -0.088 |
hift | -0.087 |
Token | ating |
Token ID | 803 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
blasphemy | +0.264 |
Goat | +0.256 |
ドラ | +0.240 |
arge | +0.233 |
hift | +0.231 |
Neg logit contributions | |
]. | -0.175 |
�� | -0.171 |
Nikol | -0.145 |
Rub | -0.143 |
chest | -0.136 |
Token | ... |
Token ID | 986 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
]. | +1.341 |
�� | +1.274 |
Nikol | +1.166 |
Rub | +1.136 |
addle | +1.098 |
Neg logit contributions | |
blasphemy | -1.460 |
Goat | -1.402 |
ドラ | -1.354 |
arge | -1.284 |
yrinth | -1.272 |
Token | becoming |
Token ID | 5033 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
]. | +0.316 |
�� | +0.307 |
Nikol | +0.271 |
Rub | +0.268 |
chest | +0.256 |
Neg logit contributions | |
blasphemy | -0.368 |
Goat | -0.355 |
ドラ | -0.334 |
arge | -0.322 |
hift | -0.318 |
Token | more |
Token ID | 517 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
]. | +0.169 |
�� | +0.163 |
Nikol | +0.145 |
Rub | +0.144 |
addle | +0.138 |
Neg logit contributions | |
blasphemy | -0.191 |
Goat | -0.184 |
ドラ | -0.175 |
arge | -0.168 |
yrinth | -0.166 |
Token | human |
Token ID | 1692 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
blasphemy | +0.283 |
Goat | +0.272 |
ドラ | +0.255 |
arge | +0.246 |
hift | +0.243 |
Neg logit contributions | |
]. | -0.269 |
�� | -0.263 |
Nikol | -0.232 |
Rub | -0.230 |
addle | -0.221 |
Token | - |
Token ID | 12 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
blasphemy | +0.670 |
Goat | +0.646 |
ドラ | +0.594 |
arge | +0.576 |
hift | +0.568 |
Neg logit contributions | |
]. | -0.688 |
�� | -0.679 |
Nikol | -0.597 |
Rub | -0.592 |
chest | -0.569 |
Token | Donna |
Token ID | 29216 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
blasphemy | +0.084 |
Goat | +0.081 |
ドラ | +0.076 |
arge | +0.074 |
hift | +0.072 |
Neg logit contributions | |
]. | -0.068 |
�� | -0.066 |
Nikol | -0.058 |
Rub | -0.057 |
chest | -0.054 |
Token | brought |
Token ID | 3181 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
]. | +0.151 |
�� | +0.148 |
Nikol | +0.130 |
Rub | +0.128 |
chest | +0.123 |
Neg logit contributions | |
blasphemy | -0.169 |
Goat | -0.163 |
ドラ | -0.151 |
arge | -0.147 |
hift | -0.145 |
Token | in |
Token ID | 287 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
blasphemy | +0.150 |
Goat | +0.144 |
ドラ | +0.135 |
arge | +0.131 |
hift | +0.129 |
Neg logit contributions | |
]. | -0.136 |
�� | -0.132 |
Nikol | -0.117 |
Rub | -0.115 |
addle | -0.111 |
Token | her |
Token ID | 607 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
blasphemy | +0.215 |
Goat | +0.207 |
ドラ | +0.194 |
arge | +0.188 |
hift | +0.185 |
Neg logit contributions | |
]. | -0.183 |
�� | -0.179 |
Nikol | -0.157 |
Rub | -0.154 |
addle | -0.148 |
Token | four |
Token ID | 1440 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
]. | +0.057 |
�� | +0.056 |
Nikol | +0.049 |
Rub | +0.049 |
chest | +0.047 |
Neg logit contributions | |
blasphemy | -0.065 |
Goat | -0.063 |
ドラ | -0.059 |
arge | -0.057 |
hift | -0.056 |
Token | cub |
Token ID | 13617 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
blasphemy | +0.326 |
Goat | +0.316 |
ドラ | +0.293 |
arge | +0.286 |
hift | +0.282 |
Neg logit contributions | |
]. | -0.257 |
�� | -0.253 |
Nikol | -0.218 |
Rub | -0.215 |
chest | -0.206 |
Token | s |
Token ID | 82 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
]. | +1.230 |
�� | +1.183 |
Nikol | +1.050 |
Rub | +1.045 |
chest | +0.992 |
Neg logit contributions | |
blasphemy | -1.577 |
Goat | -1.510 |
ドラ | -1.428 |
arge | -1.371 |
hift | -1.367 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
blasphemy | +0.154 |
Goat | +0.149 |
ドラ | +0.138 |
arge | +0.134 |
hift | +0.132 |
Neg logit contributions | |
]. | -0.147 |
�� | -0.144 |
Nikol | -0.127 |
Rub | -0.125 |
chest | -0.120 |
Token | Shortly |
Token ID | 27265 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
blasphemy | +0.254 |
Goat | +0.244 |
ドラ | +0.228 |
arge | +0.222 |
hift | +0.219 |
Neg logit contributions | |
]. | -0.210 |
�� | -0.204 |
Nikol | -0.179 |
Rub | -0.177 |
chest | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
blasphemy | +0.083 |
Goat | +0.080 |
ドラ | +0.074 |
arge | +0.071 |
yrinth | +0.070 |
Neg logit contributions | |
]. | -0.088 |
�� | -0.085 |
Nikol | -0.076 |
Rub | -0.075 |
chest | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
]. | +0.004 |
�� | +0.004 |
Nikol | +0.003 |
Rub | +0.003 |
chest | +0.003 |
Neg logit contributions | |
blasphemy | -0.004 |
Goat | -0.004 |
ドラ | -0.004 |
arge | -0.004 |
hift | -0.004 |
Token | could |
Token ID | 714 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
]. | +0.097 |
�� | +0.095 |
Nikol | +0.080 |
Rub | +0.079 |
chest | +0.075 |
Neg logit contributions | |
blasphemy | -0.155 |
Goat | -0.150 |
ドラ | -0.141 |
arge | -0.138 |
hift | -0.136 |
Token | soon |
Token ID | 2582 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
]. | +0.295 |
�� | +0.283 |
Nikol | +0.246 |
Rub | +0.240 |
addle | +0.232 |
Neg logit contributions | |
blasphemy | -0.408 |
Goat | -0.396 |
ドラ | -0.375 |
arge | -0.359 |
yrinth | -0.356 |
Token | seek |
Token ID | 5380 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
]. | +0.432 |
�� | +0.411 |
Nikol | +0.359 |
Rub | +0.351 |
addle | +0.339 |
Neg logit contributions | |
blasphemy | -0.616 |
Goat | -0.598 |
ドラ | -0.567 |
arge | -0.543 |
yrinth | -0.539 |
Token | ways |
Token ID | 2842 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
blasphemy | +0.320 |
Goat | +0.309 |
ドラ | +0.288 |
arge | +0.280 |
hift | +0.277 |
Neg logit contributions | |
]. | -0.257 |
�� | -0.253 |
Nikol | -0.217 |
Rub | -0.216 |
addle | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
]. | +0.283 |
�� | +0.278 |
Nikol | +0.239 |
Rub | +0.237 |
chest | +0.226 |
Neg logit contributions | |
blasphemy | -0.350 |
Goat | -0.338 |
ドラ | -0.314 |
arge | -0.306 |
hift | -0.303 |
Token | drawing |
Token ID | 8263 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
]. | +0.043 |
�� | +0.042 |
Nikol | +0.036 |
Rub | +0.036 |
chest | +0.034 |
Neg logit contributions | |
blasphemy | -0.056 |
Goat | -0.054 |
ドラ | -0.051 |
arge | -0.049 |
hift | -0.049 |
Token | Moscow |
Token ID | 9070 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
]. | +1.182 |
�� | +1.115 |
Nikol | +1.017 |
Rub | +0.972 |
chest | +0.939 |
Neg logit contributions | |
blasphemy | -1.602 |
Goat | -1.559 |
ドラ | -1.472 |
arge | -1.420 |
yrinth | -1.405 |
Token | back |
Token ID | 736 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
]. | +0.717 |
�� | +0.685 |
Nikol | +0.616 |
Rub | +0.602 |
addle | +0.580 |
Neg logit contributions | |
blasphemy | -0.850 |
Goat | -0.823 |
ドラ | -0.770 |
arge | -0.745 |
hift | -0.740 |
Token | into |
Token ID | 656 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
]. | +0.222 |
�� | +0.213 |
Nikol | +0.188 |
Rub | +0.184 |
chest | +0.177 |
Neg logit contributions | |
blasphemy | -0.286 |
Goat | -0.277 |
ドラ | -0.260 |
arge | -0.251 |
hift | -0.248 |
Token | the |
Token ID | 262 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
]. | +0.122 |
�� | +0.119 |
Nikol | +0.105 |
Rub | +0.104 |
chest | +0.100 |
Neg logit contributions | |
blasphemy | -0.125 |
Goat | -0.121 |
ドラ | -0.112 |
arge | -0.108 |
hift | -0.107 |
Token | fold |
Token ID | 5591 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
blasphemy | +0.003 |
Goat | +0.003 |
ドラ | +0.003 |
arge | +0.003 |
hift | +0.003 |
Neg logit contributions | |
]. | -0.004 |
�� | -0.003 |
Nikol | -0.003 |
Rub | -0.003 |
chest | -0.003 |
Token | complaint |
Token ID | 8224 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
blasphemy | +0.038 |
Goat | +0.037 |
ドラ | +0.035 |
arge | +0.034 |
hift | +0.033 |
Neg logit contributions | |
]. | -0.032 |
�� | -0.031 |
Nikol | -0.027 |
Rub | -0.027 |
chest | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
blasphemy | +0.550 |
Goat | +0.534 |
ドラ | +0.499 |
arge | +0.484 |
hift | +0.478 |
Neg logit contributions | |
]. | -0.432 |
�� | -0.422 |
Nikol | -0.366 |
Rub | -0.361 |
chest | -0.345 |
Token | Tal |
Token ID | 7193 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
]. | +0.011 |
�� | +0.010 |
Nikol | +0.009 |
Rub | +0.009 |
chest | +0.009 |
Neg logit contributions | |
blasphemy | -0.010 |
Goat | -0.010 |
ドラ | -0.009 |
arge | -0.009 |
hift | -0.009 |
Token | athi |
Token ID | 44202 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
blasphemy | +0.138 |
Goat | +0.133 |
ドラ | +0.124 |
arge | +0.119 |
hift | +0.118 |
Neg logit contributions | |
]. | -0.131 |
�� | -0.128 |
Nikol | -0.113 |
Rub | -0.112 |
chest | -0.107 |
Token | R |
Token ID | 371 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
]. | +0.005 |
�� | +0.005 |
Nikol | +0.004 |
Rub | +0.004 |
addle | +0.004 |
Neg logit contributions | |
blasphemy | -0.004 |
Goat | -0.004 |
ドラ | -0.003 |
arge | -0.003 |
hift | -0.003 |
Token | ohan |
Token ID | 22436 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
]. | +0.501 |
�� | +0.490 |
Nikol | +0.440 |
Rub | +0.435 |
addle | +0.423 |
Neg logit contributions | |
blasphemy | -0.452 |
Goat | -0.434 |
ドラ | -0.403 |
hift | -0.380 |
yrinth | -0.379 |
Token | Va |
Token ID | 17668 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
]. | +1.413 |
�� | +1.374 |
Nikol | +1.232 |
Rub | +1.218 |
chest | +1.169 |
Neg logit contributions | |
blasphemy | -1.349 |
Goat | -1.304 |
ドラ | -1.227 |
yrinth | -1.168 |
arge | -1.161 |
Token | ib |
Token ID | 571 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
]. | +0.138 |
�� | +0.136 |
Nikol | +0.120 |
Rub | +0.119 |
chest | +0.114 |
Neg logit contributions | |
blasphemy | -0.134 |
Goat | -0.129 |
ドラ | -0.118 |
arge | -0.116 |
hift | -0.113 |
Token | h |
Token ID | 71 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
]. | +0.150 |
�� | +0.146 |
Nikol | +0.125 |
Rub | +0.124 |
chest | +0.118 |
Neg logit contributions | |
blasphemy | -0.210 |
Goat | -0.203 |
ドラ | -0.190 |
arge | -0.185 |
hift | -0.183 |
Token | av |
Token ID | 615 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
]. | +0.129 |
�� | +0.126 |
Nikol | +0.111 |
Rub | +0.110 |
chest | +0.106 |
Neg logit contributions | |
blasphemy | -0.140 |
Goat | -0.135 |
ドラ | -0.125 |
arge | -0.121 |
hift | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
]. | +0.200 |
�� | +0.195 |
Nikol | +0.174 |
Rub | +0.172 |
addle | +0.166 |
Neg logit contributions | |
blasphemy | -0.197 |
Goat | -0.190 |
ドラ | -0.176 |
arge | -0.168 |
hift | -0.168 |
Token | while |
Token ID | 981 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
blasphemy | +0.397 |
Goat | +0.383 |
ドラ | +0.355 |
arge | +0.344 |
hift | +0.339 |
Neg logit contributions | |
]. | -0.360 |
�� | -0.352 |
Nikol | -0.309 |
Rub | -0.305 |
chest | -0.293 |
Token | the |
Token ID | 262 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
blasphemy | +0.110 |
Goat | +0.106 |
ドラ | +0.100 |
arge | +0.096 |
hift | +0.095 |
Neg logit contributions | |
]. | -0.091 |
�� | -0.088 |
Nikol | -0.078 |
Rub | -0.076 |
chest | -0.073 |
Token | mother |
Token ID | 2802 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
blasphemy | +0.054 |
Goat | +0.052 |
ドラ | +0.049 |
arge | +0.047 |
hift | +0.046 |
Neg logit contributions | |
]. | -0.053 |
�� | -0.051 |
Nikol | -0.046 |
Rub | -0.045 |
chest | -0.043 |
Token | is |
Token ID | 318 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
blasphemy | +0.010 |
Goat | +0.010 |
ドラ | +0.009 |
arge | +0.009 |
hift | +0.009 |
Neg logit contributions | |
]. | -0.008 |
�� | -0.008 |
Nikol | -0.007 |
Rub | -0.007 |
chest | -0.007 |
Token | tranquil |
Token ID | 46944 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
]. | +0.022 |
�� | +0.022 |
Nikol | +0.019 |
Rub | +0.019 |
chest | +0.018 |
Neg logit contributions | |
blasphemy | -0.026 |
Goat | -0.025 |
ドラ | -0.023 |
arge | -0.023 |
hift | -0.022 |
Token | ized |
Token ID | 1143 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
blasphemy | +0.144 |
Goat | +0.139 |
ドラ | +0.127 |
arge | +0.123 |
hift | +0.122 |
Neg logit contributions | |
]. | -0.153 |
�� | -0.151 |
Nikol | -0.133 |
Rub | -0.132 |
chest | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
]. | +1.328 |
�� | +1.266 |
Nikol | +1.137 |
Rub | +1.115 |
chest | +1.077 |
Neg logit contributions | |
blasphemy | -1.453 |
Goat | -1.391 |
ドラ | -1.315 |
arge | -1.256 |
yrinth | -1.248 |
Token | It |
Token ID | 632 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
]. | +0.101 |
�� | +0.098 |
Nikol | +0.086 |
Rub | +0.085 |
chest | +0.081 |
Neg logit contributions | |
blasphemy | -0.127 |
Goat | -0.122 |
ドラ | -0.115 |
arge | -0.112 |
hift | -0.110 |
Token | would |
Token ID | 561 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
]. | +0.089 |
�� | +0.087 |
Nikol | +0.076 |
Rub | +0.075 |
chest | +0.072 |
Neg logit contributions | |
blasphemy | -0.109 |
Goat | -0.105 |
ドラ | -0.098 |
arge | -0.095 |
hift | -0.094 |
Token | be |
Token ID | 307 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
]. | +0.022 |
�� | +0.021 |
Nikol | +0.018 |
Rub | +0.017 |
addle | +0.016 |
Neg logit contributions | |
blasphemy | -0.039 |
Goat | -0.038 |
ドラ | -0.036 |
arge | -0.035 |
hift | -0.035 |
Token | interesting |
Token ID | 3499 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
]. | +0.117 |
�� | +0.111 |
Nikol | +0.100 |
Rub | +0.098 |
chest | +0.094 |
Neg logit contributions | |
blasphemy | -0.134 |
Goat | -0.131 |
ドラ | -0.125 |
arge | -0.119 |
yrinth | -0.117 |
Token | earing |
Token ID | 6648 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
]. | +0.573 |
�� | +0.560 |
Nikol | +0.493 |
Rub | +0.489 |
addle | +0.470 |
Neg logit contributions | |
blasphemy | -0.595 |
Goat | -0.574 |
ドラ | -0.531 |
arge | -0.512 |
hift | -0.507 |
Token | : |
Token ID | 25 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
blasphemy | +0.378 |
Goat | +0.365 |
ドラ | +0.337 |
arge | +0.327 |
hift | +0.323 |
Neg logit contributions | |
]. | -0.349 |
�� | -0.344 |
Nikol | -0.300 |
Rub | -0.298 |
chest | -0.285 |
Token | Size |
Token ID | 12849 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
blasphemy | +0.003 |
Goat | +0.003 |
ドラ | +0.003 |
arge | +0.002 |
hift | +0.002 |
Neg logit contributions | |
]. | -0.003 |
�� | -0.003 |
Nikol | -0.002 |
Rub | -0.002 |
chest | -0.002 |
Token | C |
Token ID | 327 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
]. | +0.492 |
�� | +0.480 |
Nikol | +0.419 |
Rub | +0.415 |
chest | +0.399 |
Neg logit contributions | |
blasphemy | -0.579 |
Goat | -0.558 |
ドラ | -0.522 |
arge | -0.505 |
hift | -0.497 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
]. | +0.318 |
�� | +0.309 |
Nikol | +0.273 |
Rub | +0.271 |
addle | +0.260 |
Neg logit contributions | |
blasphemy | -0.339 |
Goat | -0.326 |
ドラ | -0.304 |
arge | -0.291 |
hift | -0.289 |
Token | cent |
Token ID | 1247 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
]. | +0.672 |
�� | +0.658 |
Nikol | +0.582 |
Rub | +0.578 |
chest | +0.557 |
Neg logit contributions | |
blasphemy | -0.670 |
Goat | -0.643 |
ドラ | -0.601 |
arge | -0.578 |
hift | -0.570 |
Token | ering |
Token ID | 1586 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
]. | +1.445 |
�� | +1.415 |
Nikol | +1.252 |
Rub | +1.242 |
chest | +1.203 |
Neg logit contributions | |
blasphemy | -1.316 |
Goat | -1.269 |
ドラ | -1.188 |
arge | -1.125 |
hift | -1.111 |
Token |
|
Token ID | 198 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
]. | +0.483 |
�� | +0.469 |
Nikol | +0.417 |
Rub | +0.411 |
addle | +0.398 |
Neg logit contributions | |
blasphemy | -0.503 |
Goat | -0.485 |
ドラ | -0.458 |
arge | -0.436 |
hift | -0.430 |
Token |
|
Token ID | 198 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
]. | +0.239 |
�� | +0.204 |
Rub | +0.194 |
Nikol | +0.185 |
chest | +0.179 |
Neg logit contributions | |
blasphemy | -0.492 |
Goat | -0.473 |
ドラ | -0.449 |
yrinth | -0.443 |
arge | -0.436 |
Token | Have |
Token ID | 11980 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
]. | +0.378 |
�� | +0.364 |
Rub | +0.333 |
Nikol | +0.323 |
chest | +0.319 |
Neg logit contributions | |
blasphemy | -0.379 |
Goat | -0.365 |
ドラ | -0.334 |
arge | -0.322 |
hift | -0.320 |
Token | you |
Token ID | 345 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
]. | +0.521 |
�� | +0.514 |
Nikol | +0.450 |
Rub | +0.447 |
chest | +0.430 |
Neg logit contributions | |
blasphemy | -0.550 |
Goat | -0.530 |
ドラ | -0.494 |
arge | -0.474 |
hift | -0.468 |
Token | . |
Token ID | 13 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
]. | +0.369 |
�� | +0.359 |
Nikol | +0.321 |
Rub | +0.316 |
addle | +0.304 |
Neg logit contributions | |
blasphemy | -0.363 |
Goat | -0.348 |
ドラ | -0.323 |
arge | -0.311 |
yrinth | -0.306 |
Token | This |
Token ID | 770 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
blasphemy | +0.039 |
Goat | +0.038 |
ドラ | +0.035 |
arge | +0.034 |
hift | +0.034 |
Neg logit contributions | |
]. | -0.031 |
�� | -0.030 |
Nikol | -0.026 |
Rub | -0.026 |
chest | -0.025 |
Token | finally |
Token ID | 3443 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
blasphemy | +0.222 |
Goat | +0.214 |
ドラ | +0.201 |
arge | +0.195 |
yrinth | +0.192 |
Neg logit contributions | |
]. | -0.173 |
�� | -0.166 |
Nikol | -0.146 |
Rub | -0.144 |
addle | -0.137 |
Token | came |
Token ID | 1625 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
]. | +0.332 |
�� | +0.315 |
Nikol | +0.282 |
Rub | +0.275 |
addle | +0.260 |
Neg logit contributions | |
blasphemy | -0.441 |
Goat | -0.427 |
ドラ | -0.401 |
arge | -0.389 |
yrinth | -0.385 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
]. | +0.048 |
�� | +0.046 |
Nikol | +0.040 |
Rub | +0.040 |
addle | +0.038 |
Neg logit contributions | |
blasphemy | -0.065 |
Goat | -0.062 |
ドラ | -0.059 |
arge | -0.057 |
yrinth | -0.056 |
Token | storage |
Token ID | 6143 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
blasphemy | +0.158 |
Goat | +0.153 |
ドラ | +0.142 |
arge | +0.138 |
hift | +0.136 |
Neg logit contributions | |
]. | -0.133 |
�� | -0.131 |
Nikol | -0.113 |
Rub | -0.112 |
chest | -0.108 |
Token | - |
Token ID | 12 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
blasphemy | +1.272 |
Goat | +1.227 |
ドラ | +1.132 |
arge | +1.098 |
hift | +1.081 |
Neg logit contributions | |
]. | -1.271 |
�� | -1.253 |
Nikol | -1.100 |
Rub | -1.089 |
chest | -1.048 |
Token | optim |
Token ID | 40085 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
blasphemy | +0.201 |
Goat | +0.195 |
ドラ | +0.181 |
arge | +0.175 |
hift | +0.173 |
Neg logit contributions | |
]. | -0.173 |
�� | -0.169 |
Nikol | -0.148 |
Rub | -0.147 |
chest | -0.141 |
Token | ized |
Token ID | 1143 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
]. | +0.078 |
�� | +0.077 |
Nikol | +0.068 |
Rub | +0.068 |
chest | +0.065 |
Neg logit contributions | |
blasphemy | -0.069 |
Goat | -0.066 |
ドラ | -0.061 |
arge | -0.059 |
hift | -0.058 |
Token | instance |
Token ID | 4554 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
]. | +0.790 |
�� | +0.758 |
Nikol | +0.688 |
Rub | +0.676 |
addle | +0.647 |
Neg logit contributions | |
blasphemy | -0.784 |
Goat | -0.755 |
ドラ | -0.702 |
arge | -0.675 |
yrinth | -0.672 |
Token | types |
Token ID | 3858 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
blasphemy | +0.170 |
Goat | +0.164 |
ドラ | +0.151 |
arge | +0.146 |
hift | +0.145 |
Neg logit contributions | |
]. | -0.171 |
�� | -0.167 |
Nikol | -0.148 |
Rub | -0.146 |
chest | -0.141 |
Token | tobacco |
Token ID | 11219 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
blasphemy | +0.226 |
Goat | +0.218 |
ドラ | +0.202 |
arge | +0.195 |
hift | +0.193 |
Neg logit contributions | |
]. | -0.232 |
�� | -0.226 |
Nikol | -0.201 |
Rub | -0.199 |
chest | -0.191 |
Token | 11 |
Token ID | 1367 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
blasphemy | +0.279 |
Goat | +0.270 |
ドラ | +0.249 |
arge | +0.241 |
hift | +0.238 |
Neg logit contributions | |
]. | -0.300 |
�� | -0.292 |
Nikol | -0.261 |
Rub | -0.258 |
addle | -0.248 |
Token | : |
Token ID | 25 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
]. | +0.138 |
�� | +0.137 |
Nikol | +0.119 |
Rub | +0.118 |
chest | +0.114 |
Neg logit contributions | |
blasphemy | -0.138 |
Goat | -0.133 |
ドラ | -0.123 |
arge | -0.119 |
hift | -0.117 |
Token | 50 |
Token ID | 1120 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
blasphemy | +0.100 |
Goat | +0.095 |
ドラ | +0.090 |
yrinth | +0.086 |
arge | +0.086 |
Neg logit contributions | |
]. | -0.101 |
�� | -0.092 |
Rub | -0.086 |
Nikol | -0.086 |
chest | -0.082 |
Token | AM |
Token ID | 3001 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
]. | +0.103 |
�� | +0.102 |
Nikol | +0.085 |
Rub | +0.084 |
chest | +0.080 |
Neg logit contributions | |
blasphemy | -0.158 |
Goat | -0.153 |
ドラ | -0.142 |
arge | -0.140 |
hift | -0.138 |
Token | ET |
Token ID | 12152 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
]. | +0.300 |
�� | +0.294 |
Nikol | +0.269 |
Rub | +0.267 |
chest | +0.258 |
Neg logit contributions | |
blasphemy | -0.160 |
Goat | -0.151 |
ドラ | -0.136 |
arge | -0.128 |
hift | -0.125 |
Token | Fri |
Token ID | 19480 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
blasphemy | +1.209 |
Goat | +1.159 |
ドラ | +1.055 |
arge | +1.017 |
hift | +1.000 |
Neg logit contributions | |
]. | -1.576 |
�� | -1.552 |
Nikol | -1.388 |
Rub | -1.377 |
chest | -1.331 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
blasphemy | +0.252 |
Goat | +0.240 |
ドラ | +0.221 |
arge | +0.212 |
hift | +0.210 |
Neg logit contributions | |
]. | -0.299 |
�� | -0.285 |
Nikol | -0.261 |
Rub | -0.261 |
addle | -0.248 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
]. | +0.137 |
�� | +0.129 |
Nikol | +0.115 |
Rub | +0.113 |
chest | +0.106 |
Neg logit contributions | |
blasphemy | -0.197 |
Goat | -0.190 |
ドラ | -0.180 |
arge | -0.175 |
yrinth | -0.173 |
Token | July |
Token ID | 2901 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
]. | +0.025 |
�� | +0.023 |
Nikol | +0.021 |
Rub | +0.021 |
chest | +0.019 |
Neg logit contributions | |
blasphemy | -0.034 |
Goat | -0.033 |
ドラ | -0.031 |
arge | -0.030 |
yrinth | -0.030 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
blasphemy | +0.483 |
Goat | +0.460 |
ドラ | +0.431 |
arge | +0.414 |
yrinth | +0.413 |
Neg logit contributions | |
]. | -0.484 |
�� | -0.467 |
Nikol | -0.421 |
Rub | -0.416 |
chest | -0.395 |
Token | / |
Token ID | 14 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
blasphemy | +0.359 |
Goat | +0.347 |
ドラ | +0.323 |
arge | +0.315 |
hift | +0.311 |
Neg logit contributions | |
]. | -0.289 |
�� | -0.286 |
Nikol | -0.247 |
Rub | -0.244 |
addle | -0.232 |
Token | research |
Token ID | 34033 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
blasphemy | +0.671 |
Goat | +0.648 |
ドラ | +0.596 |
arge | +0.578 |
hift | +0.570 |
Neg logit contributions | |
]. | -0.665 |
�� | -0.650 |
Nikol | -0.573 |
Rub | -0.568 |
chest | -0.547 |
Token | / |
Token ID | 14 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
]. | +0.006 |
�� | +0.006 |
Nikol | +0.005 |
Rub | +0.005 |
chest | +0.005 |
Neg logit contributions | |
blasphemy | -0.008 |
Goat | -0.008 |
ドラ | -0.007 |
arge | -0.007 |
hift | -0.007 |
Token | pub |
Token ID | 12984 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
blasphemy | +0.458 |
Goat | +0.442 |
ドラ | +0.407 |
arge | +0.393 |
hift | +0.388 |
Neg logit contributions | |
]. | -0.455 |
�� | -0.444 |
Nikol | -0.391 |
Rub | -0.389 |
chest | -0.375 |
Token | / |
Token ID | 14 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
blasphemy | +0.881 |
Goat | +0.845 |
ドラ | +0.795 |
arge | +0.771 |
hift | +0.757 |
Neg logit contributions | |
]. | -0.791 |
�� | -0.791 |
Nikol | -0.691 |
Rub | -0.674 |
addle | -0.644 |
Token | alcohol |
Token ID | 42142 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
blasphemy | +0.427 |
Goat | +0.412 |
ドラ | +0.379 |
arge | +0.367 |
hift | +0.362 |
Neg logit contributions | |
]. | -0.421 |
�� | -0.411 |
Nikol | -0.361 |
Rub | -0.360 |
chest | -0.347 |
Token | - |
Token ID | 12 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
blasphemy | +1.290 |
Goat | +1.246 |
ドラ | +1.160 |
arge | +1.131 |
hift | +1.114 |
Neg logit contributions | |
]. | -1.097 |
�� | -1.093 |
Nikol | -0.947 |
Rub | -0.928 |
chest | -0.888 |
Token | laws |
Token ID | 29317 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
blasphemy | +0.193 |
Goat | +0.187 |
ドラ | +0.172 |
arge | +0.167 |
hift | +0.165 |
Neg logit contributions | |
]. | -0.175 |
�� | -0.169 |
Nikol | -0.148 |
Rub | -0.148 |
chest | -0.143 |
Token | / |
Token ID | 14 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
blasphemy | +0.773 |
Goat | +0.747 |
ドラ | +0.691 |
arge | +0.672 |
hift | +0.664 |
Neg logit contributions | |
]. | -0.710 |
�� | -0.704 |
Nikol | -0.614 |
Rub | -0.605 |
addle | -0.581 |
Token | 08 |
Token ID | 2919 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
blasphemy | +0.078 |
Goat | +0.076 |
ドラ | +0.070 |
arge | +0.067 |
hift | +0.067 |
Neg logit contributions | |
]. | -0.078 |
�� | -0.076 |
Nikol | -0.067 |
Rub | -0.067 |
chest | -0.064 |
Token | history |
Token ID | 23569 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
]. | +0.188 |
�� | +0.185 |
Nikol | +0.161 |
Rub | +0.159 |
chest | +0.152 |
Neg logit contributions | |
blasphemy | -0.221 |
Goat | -0.213 |
ドラ | -0.198 |
arge | -0.193 |
hift | -0.190 |
Token | 1 |
Token ID | 352 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
]. | +0.005 |
�� | +0.005 |
Nikol | +0.005 |
Rub | +0.004 |
chest | +0.004 |
Neg logit contributions | |
blasphemy | -0.008 |
Goat | -0.008 |
ドラ | -0.008 |
arge | -0.007 |
hift | -0.007 |
Token | p |
Token ID | 279 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
blasphemy | +0.032 |
Goat | +0.032 |
ドラ | +0.029 |
arge | +0.029 |
hift | +0.028 |
Neg logit contributions | |
]. | -0.023 |
�� | -0.022 |
Nikol | -0.019 |
Rub | -0.019 |
chest | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
blasphemy | +0.153 |
Goat | +0.147 |
ドラ | +0.139 |
yrinth | +0.135 |
hift | +0.131 |
Neg logit contributions | |
]. | -0.137 |
�� | -0.120 |
Nikol | -0.115 |
Rub | -0.115 |
chest | -0.111 |
Token | m |
Token ID | 76 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
blasphemy | +0.103 |
Goat | +0.098 |
ドラ | +0.092 |
yrinth | +0.090 |
arge | +0.087 |
Neg logit contributions | |
]. | -0.078 |
�� | -0.066 |
Nikol | -0.063 |
Rub | -0.063 |
chest | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
]. | +0.215 |
�� | +0.195 |
Nikol | +0.185 |
Rub | +0.180 |
chest | +0.174 |
Neg logit contributions | |
blasphemy | -0.239 |
Goat | -0.228 |
ドラ | -0.216 |
yrinth | -0.206 |
hift | -0.204 |
Token | ET |
Token ID | 12152 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
blasphemy | +0.219 |
Goat | +0.207 |
ドラ | +0.181 |
arge | +0.173 |
hift | +0.168 |
Neg logit contributions | |
]. | -0.448 |
�� | -0.445 |
Nikol | -0.402 |
Rub | -0.401 |
chest | -0.390 |
Token | on |
Token ID | 319 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
blasphemy | +1.085 |
Goat | +1.048 |
ドラ | +0.936 |
arge | +0.915 |
dot | +0.899 |
Neg logit contributions | |
�� | -1.385 |
]. | -1.377 |
Nikol | -1.207 |
Rub | -1.204 |
chest | -1.170 |
Token | Sunday |
Token ID | 3502 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
blasphemy | +0.162 |
Goat | +0.155 |
ドラ | +0.143 |
arge | +0.137 |
hift | +0.135 |
Neg logit contributions | |
]. | -0.214 |
�� | -0.209 |
Nikol | -0.189 |
Rub | -0.187 |
chest | -0.180 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
]. | +0.057 |
�� | +0.056 |
Nikol | +0.049 |
Rub | +0.049 |
chest | +0.048 |
Neg logit contributions | |
blasphemy | -0.049 |
Goat | -0.048 |
ドラ | -0.043 |
arge | -0.042 |
dot | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
blasphemy | +0.307 |
Goat | +0.301 |
ドラ | +0.278 |
arge | +0.273 |
dot | +0.269 |
Neg logit contributions | |
]. | -0.207 |
�� | -0.202 |
Nikol | -0.169 |
Rub | -0.168 |
addle | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
blasphemy | +0.212 |
Goat | +0.205 |
ドラ | +0.195 |
yrinth | +0.189 |
arge | +0.188 |
Neg logit contributions | |
]. | -0.111 |
�� | -0.101 |
Nikol | -0.089 |
Rub | -0.088 |
chest | -0.083 |
Token | 22 |
Token ID | 2534 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
]. | +0.220 |
�� | +0.217 |
Nikol | +0.189 |
Rub | +0.186 |
chest | +0.179 |
Neg logit contributions | |
blasphemy | -0.255 |
Goat | -0.246 |
ドラ | -0.226 |
arge | -0.221 |
hift | -0.218 |
Token | 23 |
Token ID | 2242 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
]. | +0.184 |
�� | +0.182 |
Nikol | +0.156 |
Rub | +0.153 |
addle | +0.147 |
Neg logit contributions | |
blasphemy | -0.266 |
Goat | -0.257 |
ドラ | -0.238 |
arge | -0.233 |
hift | -0.232 |
Token | 24 |
Token ID | 1987 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
]. | +0.050 |
�� | +0.050 |
Nikol | +0.043 |
Rub | +0.042 |
addle | +0.041 |
Neg logit contributions | |
blasphemy | -0.068 |
Goat | -0.066 |
ドラ | -0.060 |
arge | -0.059 |
dot | -0.058 |
Token | SELECT |
Token ID | 33493 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
blasphemy | +0.335 |
Goat | +0.323 |
ドラ | +0.297 |
arge | +0.290 |
dot | +0.287 |
Neg logit contributions | |
]. | -0.265 |
�� | -0.262 |
Nikol | -0.230 |
Rub | -0.224 |
addle | -0.216 |
Token | REG |
Token ID | 23337 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
blasphemy | +0.539 |
Goat | +0.522 |
ドラ | +0.488 |
arge | +0.473 |
hift | +0.468 |
Neg logit contributions | |
]. | -0.425 |
�� | -0.414 |
Nikol | -0.359 |
Rub | -0.355 |
chest | -0.339 |
Token | EXP |
Token ID | 49864 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
]. | +0.280 |
�� | +0.272 |
Nikol | +0.238 |
Rub | +0.236 |
chest | +0.226 |
Neg logit contributions | |
blasphemy | -0.319 |
Goat | -0.308 |
ドラ | -0.287 |
arge | -0.278 |
hift | -0.275 |
Token | _ |
Token ID | 62 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
blasphemy | +1.337 |
Goat | +1.298 |
ドラ | +1.200 |
arge | +1.176 |
hift | +1.156 |
Neg logit contributions | |
]. | -1.091 |
�� | -1.088 |
Nikol | -0.933 |
Rub | -0.920 |
chest | -0.887 |
Token | EX |
Token ID | 6369 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
blasphemy | +0.371 |
Goat | +0.356 |
ドラ | +0.328 |
arge | +0.318 |
hift | +0.314 |
Neg logit contributions | |
]. | -0.378 |
�� | -0.366 |
Nikol | -0.325 |
Rub | -0.325 |
chest | -0.312 |
Token | TR |
Token ID | 5446 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
]. | +0.021 |
�� | +0.021 |
Nikol | +0.018 |
Rub | +0.018 |
chest | +0.017 |
Neg logit contributions | |
blasphemy | -0.024 |
Goat | -0.024 |
ドラ | -0.022 |
arge | -0.021 |
hift | -0.021 |
Token | ACT |
Token ID | 10659 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
blasphemy | +0.220 |
Goat | +0.212 |
ドラ | +0.198 |
arge | +0.192 |
hift | +0.189 |
Neg logit contributions | |
]. | -0.187 |
�� | -0.183 |
Nikol | -0.160 |
Rub | -0.158 |
addle | -0.151 |
Token | ( |
Token ID | 357 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
blasphemy | +0.629 |
Goat | +0.609 |
ドラ | +0.566 |
arge | +0.551 |
hift | +0.544 |
Neg logit contributions | |
]. | -0.495 |
�� | -0.488 |
Nikol | -0.421 |
Rub | -0.415 |
chest | -0.397 |
Token | pesky |
Token ID | 49109 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
blasphemy | +0.534 |
Goat | +0.514 |
ドラ | +0.482 |
arge | +0.467 |
hift | +0.459 |
Neg logit contributions | |
]. | -0.479 |
�� | -0.464 |
Nikol | -0.411 |
Rub | -0.405 |
chest | -0.388 |
Token | � |
Token ID | 564 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
]. | +0.038 |
�� | +0.036 |
Nikol | +0.033 |
Rub | +0.033 |
chest | +0.032 |
Neg logit contributions | |
blasphemy | -0.032 |
Goat | -0.031 |
ドラ | -0.029 |
arge | -0.028 |
dot | -0.027 |
Token | � |
Token ID | 250 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
blasphemy | +0.348 |
Goat | +0.337 |
ドラ | +0.315 |
arge | +0.307 |
hift | +0.303 |
Neg logit contributions | |
]. | -0.250 |
�� | -0.246 |
Nikol | -0.210 |
Rub | -0.208 |
chest | -0.198 |
Token | c |
Token ID | 66 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
blasphemy | +0.121 |
Goat | +0.116 |
ドラ | +0.106 |
arge | +0.103 |
hift | +0.102 |
Neg logit contributions | |
]. | -0.132 |
�� | -0.125 |
Rub | -0.115 |
Nikol | -0.114 |
chest | -0.110 |
Token | annot |
Token ID | 34574 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
blasphemy | +0.071 |
Goat | +0.068 |
ドラ | +0.063 |
hift | +0.059 |
arge | +0.059 |
Neg logit contributions | |
]. | -0.091 |
�� | -0.087 |
Nikol | -0.079 |
Rub | -0.079 |
addle | -0.076 |
Token | be |
Token ID | 307 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
blasphemy | +0.036 |
Goat | +0.035 |
ドラ | +0.032 |
arge | +0.031 |
hift | +0.031 |
Neg logit contributions | |
]. | -0.034 |
�� | -0.034 |
Nikol | -0.030 |
Rub | -0.029 |
chest | -0.028 |
Token | destroyed |
Token ID | 6572 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
blasphemy | +0.203 |
Goat | +0.195 |
ドラ | +0.182 |
arge | +0.175 |
hift | +0.173 |
Neg logit contributions | |
]. | -0.199 |
�� | -0.192 |
Nikol | -0.171 |
Rub | -0.168 |
chest | -0.162 |
Token | � |
Token ID | 447 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
]. | +0.157 |
�� | +0.151 |
Nikol | +0.135 |
Rub | +0.132 |
chest | +0.128 |
Neg logit contributions | |
blasphemy | -0.160 |
Goat | -0.154 |
ドラ | -0.142 |
arge | -0.138 |
hift | -0.136 |
Token | � |
Token ID | 251 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
blasphemy | +0.206 |
Goat | +0.201 |
ドラ | +0.191 |
arge | +0.185 |
yrinth | +0.184 |
Neg logit contributions | |
]. | -0.107 |
�� | -0.106 |
Rub | -0.085 |
Nikol | -0.083 |
chest | -0.078 |
Token | effects |
Token ID | 3048 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
blasphemy | +0.463 |
Goat | +0.447 |
ドラ | +0.415 |
arge | +0.399 |
hift | +0.395 |
Neg logit contributions | |
]. | -0.455 |
�� | -0.440 |
Nikol | -0.392 |
Rub | -0.387 |
chest | -0.374 |
Token | , |
Token ID | 11 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
blasphemy | +0.240 |
Goat | +0.232 |
ドラ | +0.216 |
arge | +0.209 |
yrinth | +0.206 |
Neg logit contributions | |
]. | -0.204 |
�� | -0.197 |
Nikol | -0.174 |
Rub | -0.171 |
chest | -0.164 |
Token | which |
Token ID | 543 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
]. | +0.184 |
�� | +0.179 |
Nikol | +0.159 |
Rub | +0.156 |
chest | +0.149 |
Neg logit contributions | |
blasphemy | -0.201 |
Goat | -0.194 |
ドラ | -0.182 |
arge | -0.175 |
hift | -0.173 |
Token | she |
Token ID | 673 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
]. | +0.399 |
�� | +0.381 |
Nikol | +0.342 |
Rub | +0.329 |
chest | +0.314 |
Neg logit contributions | |
blasphemy | -0.553 |
Goat | -0.533 |
ドラ | -0.509 |
arge | -0.491 |
hift | -0.486 |
Token | describes |
Token ID | 8477 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
]. | +0.198 |
�� | +0.184 |
Nikol | +0.168 |
Rub | +0.163 |
chest | +0.156 |
Neg logit contributions | |
blasphemy | -0.243 |
Goat | -0.236 |
ドラ | -0.222 |
arge | -0.213 |
hift | -0.211 |
Token | as |
Token ID | 355 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
blasphemy | +0.187 |
Goat | +0.180 |
ドラ | +0.163 |
arge | +0.158 |
hift | +0.158 |
Neg logit contributions | |
]. | -0.202 |
�� | -0.201 |
Nikol | -0.176 |
Rub | -0.176 |
addle | -0.170 |
Token | " |
Token ID | 366 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
]. | +0.207 |
�� | +0.201 |
Nikol | +0.176 |
Rub | +0.173 |
chest | +0.166 |
Neg logit contributions | |
blasphemy | -0.253 |
Goat | -0.245 |
ドラ | -0.229 |
arge | -0.222 |
hift | -0.219 |
Token | sweet |
Token ID | 34751 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
blasphemy | +0.288 |
Goat | +0.279 |
ドラ | +0.259 |
arge | +0.252 |
hift | +0.249 |
Neg logit contributions | |
]. | -0.237 |
�� | -0.232 |
Nikol | -0.202 |
Rub | -0.200 |
chest | -0.191 |
Token | and |
Token ID | 290 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
blasphemy | +0.369 |
Goat | +0.355 |
ドラ | +0.327 |
arge | +0.314 |
hift | +0.309 |
Neg logit contributions | |
]. | -0.434 |
�� | -0.424 |
Nikol | -0.380 |
Rub | -0.376 |
chest | -0.363 |
Token | Southern |
Token ID | 8050 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
]. | +0.187 |
�� | +0.183 |
Nikol | +0.161 |
Rub | +0.159 |
chest | +0.153 |
Neg logit contributions | |
blasphemy | -0.201 |
Goat | -0.194 |
ドラ | -0.180 |
arge | -0.174 |
hift | -0.172 |
Token | " |
Token ID | 1 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
]. | +0.322 |
�� | +0.319 |
Nikol | +0.284 |
Rub | +0.281 |
chest | +0.271 |
Neg logit contributions | |
blasphemy | -0.254 |
Goat | -0.244 |
ドラ | -0.221 |
arge | -0.214 |
hift | -0.210 |
Token | -- |
Token ID | 1377 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
blasphemy | +0.188 |
Goat | +0.182 |
ドラ | +0.167 |
arge | +0.162 |
hift | +0.160 |
Neg logit contributions | |
]. | -0.192 |
�� | -0.189 |
Nikol | -0.166 |
Rub | -0.165 |
chest | -0.159 |
Token | and |
Token ID | 290 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
]. | +0.368 |
�� | +0.359 |
Nikol | +0.320 |
Rub | +0.314 |
addle | +0.301 |
Neg logit contributions | |
blasphemy | -0.377 |
Goat | -0.364 |
ドラ | -0.342 |
arge | -0.329 |
hift | -0.325 |
Token | time |
Token ID | 640 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
blasphemy | +0.073 |
Goat | +0.070 |
ドラ | +0.064 |
arge | +0.061 |
hift | +0.060 |
Neg logit contributions | |
]. | -0.114 |
�� | -0.112 |
Nikol | -0.102 |
Rub | -0.101 |
addle | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | -5.29e-03 |
Pos logit contributions | |
blasphemy | +0.012 |
Goat | +0.011 |
ドラ | +0.010 |
arge | +0.010 |
hift | +0.010 |
Neg logit contributions | |
]. | -0.014 |
�� | -0.014 |
Nikol | -0.012 |
Rub | -0.012 |
chest | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
]. | +0.003 |
�� | +0.003 |
Nikol | +0.003 |
Rub | +0.003 |
chest | +0.003 |
Neg logit contributions | |
blasphemy | -0.004 |
Goat | -0.004 |
ドラ | -0.004 |
arge | -0.004 |
hift | -0.004 |
Token | Gators |
Token ID | 47470 |
Feature activation | +8.61e-02 |
Pos logit contributions | |
blasphemy | +0.089 |
Goat | +0.086 |
ドラ | +0.081 |
arge | +0.078 |
hift | +0.077 |
Neg logit contributions | |
]. | -0.071 |
�� | -0.069 |
Nikol | -0.061 |
Rub | -0.060 |
addle | -0.057 |
Token | nearly |
Token ID | 3016 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
blasphemy | +0.072 |
Goat | +0.070 |
ドラ | +0.065 |
arge | +0.063 |
hift | +0.063 |
Neg logit contributions | |
]. | -0.053 |
�� | -0.052 |
Nikol | -0.044 |
Rub | -0.044 |
chest | -0.042 |
Token | fell |
Token ID | 3214 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
blasphemy | +0.127 |
Goat | +0.123 |
ドラ | +0.115 |
arge | +0.112 |
hift | +0.110 |
Neg logit contributions | |
]. | -0.097 |
�� | -0.095 |
Nikol | -0.082 |
Rub | -0.081 |
chest | -0.077 |
Token | to |
Token ID | 284 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
blasphemy | +0.305 |
Goat | +0.295 |
ドラ | +0.275 |
arge | +0.268 |
hift | +0.264 |
Neg logit contributions | |
]. | -0.236 |
�� | -0.231 |
Nikol | -0.199 |
Rub | -0.197 |
chest | -0.188 |
Token | the |
Token ID | 262 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
]. | +0.117 |
�� | +0.112 |
Nikol | +0.099 |
Rub | +0.097 |
addle | +0.092 |
Neg logit contributions | |
blasphemy | -0.146 |
Goat | -0.142 |
ドラ | -0.134 |
arge | -0.129 |
yrinth | -0.128 |
Token | Lob |
Token ID | 32684 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
]. | +0.025 |
�� | +0.024 |
Nikol | +0.022 |
Rub | +0.021 |
addle | +0.020 |
Neg logit contributions | |
blasphemy | -0.026 |
Goat | -0.025 |
ドラ | -0.024 |
arge | -0.023 |
yrinth | -0.022 |
Token | os |
Token ID | 418 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
blasphemy | +0.112 |
Goat | +0.105 |
ドラ | +0.095 |
arge | +0.088 |
hift | +0.087 |
Neg logit contributions | |
]. | -0.216 |
�� | -0.211 |
Nikol | -0.195 |
Rub | -0.193 |
addle | -0.187 |
Token | in |
Token ID | 287 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
]. | +0.295 |
�� | +0.286 |
Nikol | +0.256 |
Rub | +0.251 |
chest | +0.242 |
Neg logit contributions | |
blasphemy | -0.316 |
Goat | -0.306 |
ドラ | -0.284 |
arge | -0.275 |
yrinth | -0.269 |
Token | Whole |
Token ID | 23431 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
]. | +0.127 |
�� | +0.121 |
Nikol | +0.104 |
Rub | +0.103 |
chest | +0.097 |
Neg logit contributions | |
blasphemy | -0.201 |
Goat | -0.192 |
ドラ | -0.185 |
arge | -0.178 |
yrinth | -0.177 |
Token | Lot |
Token ID | 15099 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
]. | +0.166 |
�� | +0.154 |
Nikol | +0.141 |
Rub | +0.138 |
chest | +0.131 |
Neg logit contributions | |
blasphemy | -0.198 |
Goat | -0.184 |
ドラ | -0.181 |
yrinth | -0.174 |
arge | -0.170 |
Token | Better |
Token ID | 11625 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
blasphemy | +0.175 |
Goat | +0.167 |
ドラ | +0.155 |
arge | +0.149 |
hift | +0.147 |
Neg logit contributions | |
]. | -0.195 |
�� | -0.192 |
Nikol | -0.170 |
Rub | -0.169 |
chest | -0.163 |
Token | " |
Token ID | 1 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
blasphemy | +0.142 |
Goat | +0.136 |
ドラ | +0.123 |
arge | +0.118 |
hift | +0.116 |
Neg logit contributions | |
]. | -0.207 |
�� | -0.203 |
Nikol | -0.183 |
Rub | -0.182 |
chest | -0.176 |
Token | ( |
Token ID | 357 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
blasphemy | +0.158 |
Goat | +0.153 |
ドラ | +0.142 |
arge | +0.138 |
hift | +0.137 |
Neg logit contributions | |
]. | -0.127 |
�� | -0.125 |
Nikol | -0.108 |
Rub | -0.107 |
chest | -0.102 |
Token | above |
Token ID | 29370 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
]. | +0.252 |
�� | +0.245 |
Rub | +0.217 |
Nikol | +0.217 |
chest | +0.208 |
Neg logit contributions | |
blasphemy | -0.257 |
Goat | -0.248 |
ドラ | -0.228 |
arge | -0.222 |
hift | -0.219 |
Token | ), |
Token ID | 828 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
blasphemy | +0.337 |
Goat | +0.324 |
ドラ | +0.297 |
arge | +0.287 |
hift | +0.283 |
Neg logit contributions | |
]. | -0.408 |
�� | -0.401 |
Nikol | -0.358 |
Rub | -0.354 |
chest | -0.342 |
Token | which |
Token ID | 543 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
]. | +0.037 |
�� | +0.037 |
Nikol | +0.032 |
Rub | +0.032 |
chest | +0.030 |
Neg logit contributions | |
blasphemy | -0.043 |
Goat | -0.041 |
ドラ | -0.038 |
arge | -0.037 |
hift | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
]. | +0.331 |
�� | +0.322 |
Nikol | +0.282 |
Rub | +0.277 |
chest | +0.263 |
Neg logit contributions | |
blasphemy | -0.444 |
Goat | -0.430 |
ドラ | -0.403 |
arge | -0.392 |
hift | -0.387 |
Token | previously |
Token ID | 4271 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
]. | +0.137 |
�� | +0.132 |
Nikol | +0.118 |
Rub | +0.116 |
chest | +0.110 |
Neg logit contributions | |
blasphemy | -0.158 |
Goat | -0.153 |
ドラ | -0.143 |
arge | -0.139 |
hift | -0.137 |
Token | available |
Token ID | 1695 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
]. | +0.171 |
�� | +0.164 |
Nikol | +0.147 |
Rub | +0.145 |
chest | +0.138 |
Neg logit contributions | |
blasphemy | -0.191 |
Goat | -0.185 |
ドラ | -0.172 |
arge | -0.167 |
yrinth | -0.165 |
Token | These |
Token ID | 2312 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
blasphemy | +0.299 |
Goat | +0.288 |
ドラ | +0.269 |
arge | +0.263 |
hift | +0.259 |
Neg logit contributions | |
]. | -0.231 |
�� | -0.223 |
Nikol | -0.197 |
Rub | -0.194 |
chest | -0.184 |
Token | were |
Token ID | 547 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
blasphemy | +0.195 |
Goat | +0.189 |
ドラ | +0.175 |
arge | +0.169 |
hift | +0.166 |
Neg logit contributions | |
]. | -0.196 |
�� | -0.189 |
Nikol | -0.170 |
Rub | -0.167 |
chest | -0.161 |
Token | real |
Token ID | 1103 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
blasphemy | +0.221 |
Goat | +0.215 |
ドラ | +0.200 |
arge | +0.193 |
hift | +0.190 |
Neg logit contributions | |
]. | -0.202 |
�� | -0.195 |
Nikol | -0.175 |
Rub | -0.171 |
chest | -0.164 |
Token | crises |
Token ID | 25712 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
blasphemy | +0.456 |
Goat | +0.441 |
ドラ | +0.402 |
arge | +0.389 |
hift | +0.382 |
Neg logit contributions | |
]. | -0.541 |
�� | -0.521 |
Nikol | -0.473 |
Rub | -0.465 |
chest | -0.452 |
Token | . |
Token ID | 13 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
]. | +0.096 |
�� | +0.093 |
Nikol | +0.084 |
Rub | +0.082 |
chest | +0.079 |
Neg logit contributions | |
blasphemy | -0.092 |
Goat | -0.089 |
ドラ | -0.083 |
arge | -0.080 |
yrinth | -0.079 |
Token | No |
Token ID | 1400 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
blasphemy | +0.351 |
Goat | +0.335 |
ドラ | +0.315 |
arge | +0.307 |
hift | +0.302 |
Neg logit contributions | |
]. | -0.293 |
�� | -0.278 |
Nikol | -0.251 |
Rub | -0.247 |
chest | -0.234 |
Token | comparable |
Token ID | 13975 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
blasphemy | +0.393 |
Goat | +0.380 |
ドラ | +0.351 |
arge | +0.340 |
hift | +0.334 |
Neg logit contributions | |
]. | -0.389 |
�� | -0.382 |
Nikol | -0.337 |
Rub | -0.333 |
chest | -0.320 |
Token | situation |
Token ID | 3074 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
blasphemy | +0.193 |
Goat | +0.187 |
ドラ | +0.174 |
arge | +0.167 |
yrinth | +0.164 |
Neg logit contributions | |
]. | -0.208 |
�� | -0.202 |
Nikol | -0.182 |
Rub | -0.179 |
chest | -0.172 |
Token | existed |
Token ID | 11196 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
blasphemy | +0.379 |
Goat | +0.367 |
ドラ | +0.342 |
arge | +0.333 |
hift | +0.328 |
Neg logit contributions | |
]. | -0.300 |
�� | -0.294 |
Nikol | -0.254 |
Rub | -0.251 |
chest | -0.240 |
Token | in |
Token ID | 287 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
blasphemy | +0.754 |
Goat | +0.729 |
ドラ | +0.676 |
arge | +0.656 |
hift | +0.647 |
Neg logit contributions | |
]. | -0.681 |
�� | -0.668 |
Nikol | -0.585 |
Rub | -0.578 |
chest | -0.554 |
Token | December |
Token ID | 3426 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
blasphemy | +0.284 |
Goat | +0.274 |
ドラ | +0.257 |
arge | +0.248 |
hift | +0.244 |
Neg logit contributions | |
]. | -0.257 |
�� | -0.250 |
Nikol | -0.222 |
Rub | -0.218 |
chest | -0.209 |
Token | controlled |
Token ID | 14401 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
]. | +0.302 |
�� | +0.292 |
Nikol | +0.256 |
Rub | +0.255 |
chest | +0.244 |
Neg logit contributions | |
blasphemy | -0.357 |
Goat | -0.345 |
ドラ | -0.320 |
arge | -0.311 |
hift | -0.307 |
Token | by |
Token ID | 416 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
]. | +0.182 |
�� | +0.181 |
Nikol | +0.160 |
Rub | +0.159 |
chest | +0.154 |
Neg logit contributions | |
blasphemy | -0.155 |
Goat | -0.149 |
ドラ | -0.136 |
arge | -0.132 |
dot | -0.130 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
]. | +0.283 |
�� | +0.277 |
Nikol | +0.244 |
Rub | +0.242 |
chest | +0.232 |
Neg logit contributions | |
blasphemy | -0.287 |
Goat | -0.277 |
ドラ | -0.256 |
arge | -0.248 |
hift | -0.245 |
Token | average |
Token ID | 2811 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
]. | +0.128 |
�� | +0.124 |
Nikol | +0.110 |
Rub | +0.109 |
chest | +0.105 |
Neg logit contributions | |
blasphemy | -0.128 |
Goat | -0.123 |
ドラ | -0.114 |
arge | -0.110 |
hift | -0.109 |
Token | gain |
Token ID | 4461 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
]. | +0.167 |
�� | +0.161 |
Nikol | +0.141 |
Rub | +0.139 |
chest | +0.133 |
Neg logit contributions | |
blasphemy | -0.202 |
Goat | -0.195 |
ドラ | -0.183 |
arge | -0.177 |
hift | -0.174 |
Token | ]. |
Token ID | 4083 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
]. | +0.131 |
�� | +0.127 |
Nikol | +0.107 |
Rub | +0.105 |
chest | +0.099 |
Neg logit contributions | |
blasphemy | -0.229 |
Goat | -0.223 |
ドラ | -0.209 |
arge | -0.204 |
hift | -0.202 |
Token | Applied |
Token ID | 27684 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
]. | +0.335 |
�� | +0.316 |
Nikol | +0.285 |
Rub | +0.280 |
chest | +0.265 |
Neg logit contributions | |
blasphemy | -0.389 |
Goat | -0.370 |
ドラ | -0.350 |
arge | -0.341 |
hift | -0.334 |
Token | to |
Token ID | 284 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
]. | +0.075 |
�� | +0.073 |
Nikol | +0.064 |
Rub | +0.063 |
addle | +0.060 |
Neg logit contributions | |
blasphemy | -0.093 |
Goat | -0.090 |
ドラ | -0.084 |
arge | -0.081 |
hift | -0.081 |
Token | this |
Token ID | 428 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
blasphemy | +0.068 |
Goat | +0.065 |
ドラ | +0.061 |
arge | +0.059 |
hift | +0.058 |
Neg logit contributions | |
]. | -0.066 |
�� | -0.064 |
Nikol | -0.057 |
Rub | -0.056 |
addle | -0.053 |
Token | problem |
Token ID | 1917 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
blasphemy | +0.135 |
Goat | +0.130 |
ドラ | +0.120 |
arge | +0.116 |
hift | +0.114 |
Neg logit contributions | |
]. | -0.146 |
�� | -0.142 |
Nikol | -0.127 |
Rub | -0.125 |
addle | -0.120 |
Token | , |
Token ID | 11 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
blasphemy | +0.638 |
Goat | +0.615 |
ドラ | +0.563 |
arge | +0.546 |
hift | +0.539 |
Neg logit contributions | |
]. | -0.692 |
�� | -0.684 |
Nikol | -0.603 |
Rub | -0.598 |
chest | -0.577 |
Token | first |
Token ID | 717 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
blasphemy | +0.105 |
Goat | +0.101 |
ドラ | +0.094 |
arge | +0.091 |
yrinth | +0.090 |
Neg logit contributions | |
]. | -0.101 |
�� | -0.098 |
Nikol | -0.087 |
Rub | -0.086 |
chest | -0.082 |
Token | base |
Token ID | 2779 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
blasphemy | +0.096 |
Goat | +0.092 |
ドラ | +0.084 |
arge | +0.080 |
hift | +0.079 |
Neg logit contributions | |
]. | -0.128 |
�� | -0.124 |
Nikol | -0.113 |
Rub | -0.112 |
addle | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
blasphemy | +0.337 |
Goat | +0.324 |
ドラ | +0.301 |
arge | +0.290 |
hift | +0.285 |
Neg logit contributions | |
]. | -0.353 |
�� | -0.342 |
Nikol | -0.308 |
Rub | -0.303 |
addle | -0.292 |
Token | The |
Token ID | 383 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
blasphemy | +0.143 |
Goat | +0.137 |
ドラ | +0.128 |
arge | +0.125 |
hift | +0.123 |
Neg logit contributions | |
]. | -0.118 |
�� | -0.114 |
Nikol | -0.102 |
Rub | -0.100 |
chest | -0.095 |
Token | outfield |
Token ID | 28307 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
]. | +0.096 |
�� | +0.093 |
Nikol | +0.084 |
Rub | +0.083 |
chest | +0.079 |
Neg logit contributions | |
blasphemy | -0.093 |
Goat | -0.089 |
ドラ | -0.083 |
arge | -0.080 |
hift | -0.079 |
Token | has |
Token ID | 468 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
]. | +0.434 |
�� | +0.420 |
Nikol | +0.372 |
Rub | +0.367 |
addle | +0.351 |
Neg logit contributions | |
blasphemy | -0.513 |
Goat | -0.497 |
ドラ | -0.463 |
arge | -0.450 |
hift | -0.443 |
Token | Bryce |
Token ID | 39560 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
]. | +0.038 |
�� | +0.037 |
Nikol | +0.032 |
Rub | +0.032 |
addle | +0.030 |
Neg logit contributions | |
blasphemy | -0.052 |
Goat | -0.051 |
ドラ | -0.048 |
arge | -0.046 |
hift | -0.046 |
Token | Harper |
Token ID | 12686 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
blasphemy | +0.135 |
Goat | +0.128 |
ドラ | +0.117 |
arge | +0.111 |
hift | +0.109 |
Neg logit contributions | |
]. | -0.205 |
�� | -0.201 |
Nikol | -0.182 |
Rub | -0.180 |
chest | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
]. | +0.229 |
�� | +0.223 |
Nikol | +0.199 |
Rub | +0.198 |
chest | +0.189 |
Neg logit contributions | |
blasphemy | -0.217 |
Goat | -0.209 |
ドラ | -0.193 |
arge | -0.187 |
hift | -0.184 |
Token | Den |
Token ID | 5601 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
blasphemy | +0.031 |
Goat | +0.030 |
ドラ | +0.028 |
arge | +0.027 |
hift | +0.027 |
Neg logit contributions | |
]. | -0.025 |
�� | -0.024 |
Nikol | -0.022 |
Rub | -0.021 |
chest | -0.020 |
Token | ard |
Token ID | 446 |
Feature activation | +8.98e-02 |
Pos logit contributions | |
]. | +0.113 |
�� | +0.108 |
Nikol | +0.092 |
Rub | +0.091 |
addle | +0.087 |
Neg logit contributions | |
blasphemy | -0.189 |
Goat | -0.184 |
ドラ | -0.173 |
hift | -0.167 |
arge | -0.167 |
Token | cases |
Token ID | 2663 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
]. | +0.348 |
�� | +0.330 |
Nikol | +0.301 |
Rub | +0.295 |
chest | +0.287 |
Neg logit contributions | |
blasphemy | -0.331 |
Goat | -0.321 |
ドラ | -0.299 |
arge | -0.286 |
eeks | -0.284 |
Token | of |
Token ID | 286 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
blasphemy | +0.479 |
Goat | +0.466 |
ドラ | +0.437 |
arge | +0.427 |
hift | +0.422 |
Neg logit contributions | |
]. | -0.289 |
�� | -0.283 |
Nikol | -0.237 |
Rub | -0.234 |
chest | -0.221 |
Token | cancer |
Token ID | 4890 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
blasphemy | +0.124 |
Goat | +0.119 |
ドラ | +0.109 |
arge | +0.104 |
hift | +0.102 |
Neg logit contributions | |
]. | -0.187 |
�� | -0.180 |
Nikol | -0.166 |
Rub | -0.164 |
chest | -0.159 |
Token | are |
Token ID | 389 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
]. | +0.073 |
�� | +0.071 |
Nikol | +0.060 |
Rub | +0.059 |
addle | +0.056 |
Neg logit contributions | |
blasphemy | -0.123 |
Goat | -0.120 |
ドラ | -0.112 |
arge | -0.109 |
hift | -0.108 |
Token | due |
Token ID | 2233 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
blasphemy | +0.098 |
Goat | +0.095 |
ドラ | +0.090 |
arge | +0.086 |
yrinth | +0.085 |
Neg logit contributions | |
]. | -0.074 |
�� | -0.071 |
Nikol | -0.063 |
Rub | -0.061 |
chest | -0.059 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
blasphemy | +0.074 |
Goat | +0.072 |
ドラ | +0.067 |
arge | +0.065 |
hift | +0.064 |
Neg logit contributions | |
]. | -0.061 |
�� | -0.060 |
Nikol | -0.052 |
Rub | -0.051 |
IDER | -0.049 |
Token | water |
Token ID | 1660 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
blasphemy | +0.102 |
Goat | +0.098 |
ドラ | +0.092 |
arge | +0.088 |
yrinth | +0.087 |
Neg logit contributions | |
]. | -0.100 |
�� | -0.097 |
Nikol | -0.087 |
Rub | -0.085 |
chest | -0.082 |
Token | pollution |
Token ID | 12231 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
blasphemy | +0.232 |
Goat | +0.224 |
ドラ | +0.202 |
arge | +0.190 |
yrinth | +0.188 |
Neg logit contributions | |
]. | -0.393 |
�� | -0.380 |
Nikol | -0.350 |
Rub | -0.345 |
chest | -0.337 |
Token | , |
Token ID | 11 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
blasphemy | +0.252 |
Goat | +0.243 |
ドラ | +0.226 |
arge | +0.218 |
yrinth | +0.215 |
Neg logit contributions | |
]. | -0.251 |
�� | -0.242 |
Nikol | -0.217 |
Rub | -0.213 |
addle | -0.205 |
Token | � |
Token ID | 447 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
blasphemy | +0.026 |
Goat | +0.025 |
ドラ | +0.023 |
arge | +0.023 |
hift | +0.022 |
Neg logit contributions | |
]. | -0.020 |
�� | -0.019 |
Nikol | -0.017 |
Rub | -0.017 |
chest | -0.016 |
Token | � |
Token ID | 251 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
]. | +0.045 |
�� | +0.044 |
Nikol | +0.038 |
Rub | +0.038 |
chest | +0.036 |
Neg logit contributions | |
blasphemy | -0.065 |
Goat | -0.063 |
ドラ | -0.059 |
arge | -0.057 |
hift | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
blasphemy | +0.104 |
Goat | +0.100 |
ドラ | +0.091 |
arge | +0.088 |
hift | +0.086 |
Neg logit contributions | |
]. | -0.126 |
�� | -0.125 |
Nikol | -0.111 |
Rub | -0.109 |
addle | -0.106 |
Token | protecting |
Token ID | 10192 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
]. | +0.259 |
�� | +0.249 |
Nikol | +0.223 |
Rub | +0.219 |
chest | +0.208 |
Neg logit contributions | |
blasphemy | -0.318 |
Goat | -0.310 |
ドラ | -0.289 |
arge | -0.280 |
hift | -0.277 |
Token | Israel |
Token ID | 2692 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
]. | +0.445 |
�� | +0.419 |
Nikol | +0.384 |
Rub | +0.374 |
chest | +0.355 |
Neg logit contributions | |
blasphemy | -0.524 |
Goat | -0.511 |
ドラ | -0.477 |
arge | -0.463 |
geist | -0.460 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
]. | +0.072 |
�� | +0.070 |
Nikol | +0.062 |
Rub | +0.062 |
addle | +0.059 |
Neg logit contributions | |
blasphemy | -0.069 |
Goat | -0.067 |
ドラ | -0.061 |
arge | -0.059 |
hift | -0.059 |
Token | Europe |
Token ID | 2031 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
]. | +0.130 |
�� | +0.126 |
Nikol | +0.111 |
Rub | +0.110 |
chest | +0.105 |
Neg logit contributions | |
blasphemy | -0.157 |
Goat | -0.152 |
ドラ | -0.142 |
arge | -0.138 |
hift | -0.137 |
Token | against |
Token ID | 1028 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
blasphemy | +0.051 |
Goat | +0.049 |
ドラ | +0.045 |
arge | +0.044 |
hift | +0.044 |
Neg logit contributions | |
]. | -0.053 |
�� | -0.051 |
Nikol | -0.045 |
Rub | -0.045 |
addle | -0.043 |
Token | short |
Token ID | 1790 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
blasphemy | +0.190 |
Goat | +0.184 |
ドラ | +0.170 |
arge | +0.166 |
hift | +0.164 |
Neg logit contributions | |
]. | -0.167 |
�� | -0.163 |
Nikol | -0.144 |
Rub | -0.141 |
chest | -0.136 |
Token | - |
Token ID | 12 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
blasphemy | +0.468 |
Goat | +0.451 |
ドラ | +0.413 |
arge | +0.404 |
hift | +0.398 |
Neg logit contributions | |
]. | -0.436 |
�� | -0.416 |
Nikol | -0.375 |
Rub | -0.368 |
chest | -0.356 |
Token | and |
Token ID | 290 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
]. | +0.183 |
�� | +0.175 |
Nikol | +0.157 |
Rub | +0.155 |
chest | +0.149 |
Neg logit contributions | |
blasphemy | -0.192 |
Goat | -0.184 |
ドラ | -0.170 |
arge | -0.164 |
hift | -0.162 |
Token | medium |
Token ID | 7090 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
]. | +0.244 |
�� | +0.232 |
Nikol | +0.211 |
Rub | +0.206 |
chest | +0.199 |
Neg logit contributions | |
blasphemy | -0.231 |
Goat | -0.222 |
ドラ | -0.203 |
arge | -0.197 |
eeks | -0.195 |
Token | - |
Token ID | 12 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
]. | +1.153 |
Nikol | +0.924 |
Rub | +0.905 |
chest | +0.894 |
�� | +0.889 |
Neg logit contributions | |
blasphemy | -1.601 |
Goat | -1.550 |
ドラ | -1.443 |
yrinth | -1.414 |
geist | -1.403 |
Token | have |
Token ID | 423 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
blasphemy | +0.031 |
Goat | +0.030 |
ドラ | +0.028 |
arge | +0.027 |
hift | +0.027 |
Neg logit contributions | |
]. | -0.022 |
�� | -0.021 |
Nikol | -0.018 |
Rub | -0.018 |
addle | -0.017 |
Token | default |
Token ID | 4277 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
]. | +0.272 |
�� | +0.258 |
Nikol | +0.229 |
Rub | +0.226 |
addle | +0.216 |
Neg logit contributions | |
blasphemy | -0.336 |
Goat | -0.325 |
ドラ | -0.309 |
arge | -0.296 |
hift | -0.292 |
Token | values |
Token ID | 3815 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
]. | +0.055 |
�� | +0.053 |
Nikol | +0.048 |
Rub | +0.048 |
chest | +0.046 |
Neg logit contributions | |
blasphemy | -0.040 |
Goat | -0.039 |
ドラ | -0.036 |
arge | -0.034 |
hift | -0.033 |
Token | etc |
Token ID | 3503 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
blasphemy | +0.547 |
Goat | +0.528 |
ドラ | +0.490 |
arge | +0.474 |
yrinth | +0.466 |
Neg logit contributions | |
]. | -0.509 |
�� | -0.494 |
Nikol | -0.437 |
Rub | -0.430 |
addle | -0.413 |
Token | .) |
Token ID | 2014 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
blasphemy | +0.499 |
Goat | +0.479 |
ドラ | +0.437 |
arge | +0.421 |
hift | +0.414 |
Neg logit contributions | |
]. | -0.637 |
�� | -0.625 |
Nikol | -0.560 |
Rub | -0.555 |
chest | -0.536 |
Token | and |
Token ID | 290 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
]. | +0.326 |
�� | +0.318 |
Nikol | +0.274 |
Rub | +0.271 |
chest | +0.258 |
Neg logit contributions | |
blasphemy | -0.440 |
Goat | -0.426 |
ドラ | -0.399 |
arge | -0.387 |
hift | -0.382 |
Token | what |
Token ID | 644 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
]. | +0.059 |
�� | +0.056 |
Nikol | +0.050 |
Rub | +0.049 |
chest | +0.047 |
Neg logit contributions | |
blasphemy | -0.071 |
Goat | -0.069 |
ドラ | -0.065 |
arge | -0.063 |
hift | -0.062 |
Token | scope |
Token ID | 8354 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
blasphemy | +0.055 |
Goat | +0.053 |
ドラ | +0.050 |
arge | +0.048 |
hift | +0.048 |
Neg logit contributions | |
]. | -0.043 |
�� | -0.041 |
Nikol | -0.036 |
Rub | -0.035 |
chest | -0.034 |
Token | do |
Token ID | 466 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
blasphemy | +0.443 |
Goat | +0.428 |
ドラ | +0.396 |
arge | +0.386 |
hift | +0.381 |
Neg logit contributions | |
]. | -0.378 |
�� | -0.372 |
Nikol | -0.322 |
Rub | -0.319 |
chest | -0.306 |
Token | those |
Token ID | 883 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
]. | +0.457 |
�� | +0.439 |
Nikol | +0.391 |
Rub | +0.385 |
chest | +0.369 |
Neg logit contributions | |
blasphemy | -0.503 |
Goat | -0.487 |
ドラ | -0.456 |
arge | -0.439 |
hift | -0.432 |
Token | parameters |
Token ID | 10007 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
blasphemy | +0.306 |
Goat | +0.295 |
ドラ | +0.271 |
arge | +0.258 |
hift | +0.253 |
Neg logit contributions | |
]. | -0.406 |
�� | -0.393 |
Nikol | -0.357 |
Rub | -0.352 |
chest | -0.340 |
Token | eled |
Token ID | 18449 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
blasphemy | +0.312 |
Goat | +0.302 |
ドラ | +0.281 |
arge | +0.272 |
hift | +0.269 |
Neg logit contributions | |
]. | -0.247 |
�� | -0.239 |
Nikol | -0.208 |
Rub | -0.207 |
addle | -0.199 |
Token | them |
Token ID | 606 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
]. | +0.734 |
�� | +0.702 |
Nikol | +0.635 |
Rub | +0.618 |
addle | +0.597 |
Neg logit contributions | |
blasphemy | -0.796 |
Goat | -0.771 |
ドラ | -0.730 |
arge | -0.700 |
yrinth | -0.693 |
Token | in |
Token ID | 287 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
blasphemy | +0.139 |
Goat | +0.134 |
ドラ | +0.125 |
arge | +0.121 |
hift | +0.119 |
Neg logit contributions | |
]. | -0.125 |
�� | -0.122 |
Nikol | -0.107 |
Rub | -0.106 |
chest | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
]. | +0.004 |
�� | +0.004 |
Nikol | +0.004 |
Rub | +0.004 |
addle | +0.004 |
Neg logit contributions | |
blasphemy | -0.005 |
Goat | -0.005 |
ドラ | -0.004 |
arge | -0.004 |
hift | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
blasphemy | +0.048 |
Goat | +0.046 |
ドラ | +0.043 |
arge | +0.042 |
hift | +0.041 |
Neg logit contributions | |
]. | -0.042 |
�� | -0.041 |
Nikol | -0.036 |
Rub | -0.036 |
chest | -0.034 |
Token | room |
Token ID | 2119 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
blasphemy | +0.128 |
Goat | +0.124 |
ドラ | +0.116 |
arge | +0.112 |
hift | +0.110 |
Neg logit contributions | |
]. | -0.118 |
�� | -0.115 |
Nikol | -0.101 |
Rub | -0.100 |
chest | -0.096 |
Token | after |
Token ID | 706 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
]. | +0.997 |
�� | +0.964 |
Nikol | +0.866 |
Rub | +0.856 |
chest | +0.831 |
Neg logit contributions | |
blasphemy | -0.925 |
Goat | -0.894 |
ドラ | -0.836 |
arge | -0.793 |
hift | -0.785 |
Token | the |
Token ID | 262 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
]. | +0.228 |
�� | +0.222 |
Nikol | +0.195 |
Rub | +0.191 |
chest | +0.183 |
Neg logit contributions | |
blasphemy | -0.281 |
Goat | -0.273 |
ドラ | -0.256 |
arge | -0.247 |
hift | -0.244 |
Token | manner |
Token ID | 5642 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
]. | +0.124 |
�� | +0.121 |
Nikol | +0.108 |
Rub | +0.106 |
chest | +0.102 |
Neg logit contributions | |
blasphemy | -0.122 |
Goat | -0.118 |
ドラ | -0.110 |
arge | -0.106 |
hift | -0.105 |
Token | of |
Token ID | 286 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
]. | +0.570 |
�� | +0.556 |
Nikol | +0.492 |
Rub | +0.483 |
chest | +0.464 |
Neg logit contributions | |
blasphemy | -0.610 |
Goat | -0.591 |
ドラ | -0.551 |
arge | -0.531 |
hift | -0.523 |
Token | a |
Token ID | 257 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
]. | +0.084 |
�� | +0.082 |
Nikol | +0.072 |
Rub | +0.071 |
chest | +0.068 |
Neg logit contributions | |
blasphemy | -0.097 |
Goat | -0.094 |
ドラ | -0.088 |
arge | -0.085 |
hift | -0.084 |
Token | ist |
Token ID | 396 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
blasphemy | +0.195 |
Goat | +0.189 |
ドラ | +0.176 |
arge | +0.171 |
hift | +0.170 |
Neg logit contributions | |
]. | -0.141 |
�� | -0.138 |
Nikol | -0.118 |
Rub | -0.117 |
chest | -0.112 |
Token | hopping |
Token ID | 47153 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
]. | +0.119 |
�� | +0.116 |
Nikol | +0.104 |
Rub | +0.102 |
chest | +0.100 |
Neg logit contributions | |
blasphemy | -0.111 |
Goat | -0.106 |
ドラ | -0.099 |
arge | -0.095 |
hift | -0.094 |
Token | ambitions |
Token ID | 22455 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
blasphemy | +0.165 |
Goat | +0.158 |
ドラ | +0.148 |
arge | +0.142 |
hift | +0.140 |
Neg logit contributions | |
]. | -0.173 |
�� | -0.169 |
Nikol | -0.151 |
Rub | -0.149 |
chest | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
blasphemy | +0.224 |
Goat | +0.216 |
ドラ | +0.198 |
arge | +0.192 |
hift | +0.189 |
Neg logit contributions | |
]. | -0.242 |
�� | -0.239 |
Nikol | -0.210 |
Rub | -0.209 |
chest | -0.201 |
Token | Sly |
Token ID | 31615 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
blasphemy | +0.116 |
Goat | +0.112 |
ドラ | +0.104 |
arge | +0.102 |
hift | +0.100 |
Neg logit contributions | |
]. | -0.092 |
�� | -0.090 |
Nikol | -0.079 |
Rub | -0.077 |
chest | -0.074 |
Token | Cooper |
Token ID | 10382 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
blasphemy | +0.638 |
Goat | +0.614 |
ドラ | +0.568 |
arge | +0.550 |
hift | +0.543 |
Neg logit contributions | |
]. | -0.634 |
�� | -0.623 |
Nikol | -0.550 |
Rub | -0.544 |
addle | -0.524 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
]. | +0.909 |
�� | +0.887 |
Nikol | +0.790 |
Rub | +0.779 |
chest | +0.747 |
Neg logit contributions | |
blasphemy | -0.922 |
Goat | -0.888 |
ドラ | -0.822 |
arge | -0.800 |
hift | -0.786 |
Token | the |
Token ID | 262 |
Feature activation | +9.55e-02 |
Pos logit contributions | |
blasphemy | +0.140 |
Goat | +0.135 |
ドラ | +0.126 |
arge | +0.122 |
hift | +0.121 |
Neg logit contributions | |
]. | -0.121 |
�� | -0.119 |
Nikol | -0.105 |
Rub | -0.103 |
chest | -0.099 |
Token | Th |
Token ID | 536 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
blasphemy | +0.066 |
Goat | +0.063 |
ドラ | +0.059 |
arge | +0.057 |
hift | +0.056 |
Neg logit contributions | |
]. | -0.072 |
�� | -0.070 |
Nikol | -0.063 |
Rub | -0.062 |
addle | -0.060 |
Token | iev |
Token ID | 11203 |
Feature activation | -9.02e-04 |
Pos logit contributions | |
blasphemy | +0.055 |
Goat | +0.052 |
ドラ | +0.049 |
hift | +0.046 |
arge | +0.046 |
Neg logit contributions | |
]. | -0.055 |
�� | -0.053 |
Nikol | -0.047 |
Rub | -0.047 |
addle | -0.046 |
Token | ius |
Token ID | 3754 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
]. | +0.001 |
�� | +0.001 |
Nikol | +0.000 |
Rub | +0.000 |
chest | +0.000 |
Neg logit contributions | |
blasphemy | -0.001 |
Goat | -0.001 |
ドラ | -0.001 |
arge | -0.001 |
hift | -0.001 |
Token | House |
Token ID | 2097 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
]. | +0.330 |
�� | +0.311 |
Nikol | +0.281 |
Rub | +0.279 |
chest | +0.264 |
Neg logit contributions | |
blasphemy | -0.395 |
Goat | -0.383 |
ドラ | -0.365 |
hift | -0.347 |
arge | -0.347 |
Token | Majority |
Token ID | 22171 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
]. | +0.116 |
�� | +0.113 |
Rub | +0.100 |
Nikol | +0.100 |
chest | +0.096 |
Neg logit contributions | |
blasphemy | -0.106 |
Goat | -0.102 |
ドラ | -0.096 |
arge | -0.091 |
hift | -0.091 |
Token | Whip |
Token ID | 40930 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
]. | +0.170 |
�� | +0.167 |
Nikol | +0.147 |
Rub | +0.147 |
chest | +0.140 |
Neg logit contributions | |
blasphemy | -0.178 |
Goat | -0.170 |
ドラ | -0.159 |
arge | -0.153 |
hift | -0.152 |
Token | Steve |
Token ID | 6542 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
]. | +0.368 |
�� | +0.355 |
Nikol | +0.306 |
Rub | +0.298 |
chest | +0.284 |
Neg logit contributions | |
blasphemy | -0.609 |
Goat | -0.588 |
ドラ | -0.560 |
hift | -0.537 |
yrinth | -0.537 |
Token | Scal |
Token ID | 34529 |
Feature activation | -5.78e-02 |
Pos logit contributions | |
]. | +0.707 |
�� | +0.689 |
Nikol | +0.628 |
Rub | +0.623 |
chest | +0.604 |
Neg logit contributions | |
blasphemy | -0.450 |
Goat | -0.425 |
ドラ | -0.390 |
arge | -0.368 |
hift | -0.367 |
Token | ise |
Token ID | 786 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
]. | +0.034 |
�� | +0.034 |
Nikol | +0.029 |
Rub | +0.028 |
ItemTracker | +0.026 |
Neg logit contributions | |
blasphemy | -0.049 |
Goat | -0.048 |
ドラ | -0.045 |
arge | -0.045 |
dot | -0.044 |
Token | ( |
Token ID | 357 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
]. | +0.818 |
�� | +0.789 |
Nikol | +0.684 |
Rub | +0.674 |
chest | +0.639 |
Neg logit contributions | |
blasphemy | -1.146 |
Goat | -1.112 |
ドラ | -1.046 |
arge | -1.009 |
hift | -1.004 |
Token | R |
Token ID | 49 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
]. | +0.192 |
�� | +0.187 |
Rub | +0.167 |
Nikol | +0.166 |
chest | +0.160 |
Neg logit contributions | |
blasphemy | -0.182 |
Goat | -0.175 |
ドラ | -0.161 |
arge | -0.155 |
hift | -0.154 |
Token | - |
Token ID | 12 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
]. | +0.533 |
�� | +0.526 |
Nikol | +0.461 |
Rub | +0.456 |
chest | +0.438 |
Neg logit contributions | |
blasphemy | -0.548 |
Goat | -0.528 |
ドラ | -0.487 |
arge | -0.474 |
hift | -0.466 |
Token | La |
Token ID | 14772 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
blasphemy | +0.041 |
Goat | +0.039 |
ドラ | +0.034 |
arge | +0.033 |
hift | +0.032 |
Neg logit contributions | |
]. | -0.073 |
�� | -0.073 |
Nikol | -0.066 |
Rub | -0.065 |
addle | -0.063 |
Token | .), |
Token ID | 12179 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
]. | +0.624 |
�� | +0.608 |
Nikol | +0.541 |
Rub | +0.537 |
addle | +0.513 |
Neg logit contributions | |
blasphemy | -0.608 |
Goat | -0.587 |
ドラ | -0.541 |
arge | -0.524 |
hift | -0.517 |
Token | effort |
Token ID | 3626 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
blasphemy | +0.139 |
Goat | +0.134 |
ドラ | +0.125 |
arge | +0.120 |
hift | +0.119 |
Neg logit contributions | |
]. | -0.135 |
�� | -0.131 |
Nikol | -0.117 |
Rub | -0.116 |
addle | -0.111 |
Token | by |
Token ID | 416 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
blasphemy | +0.481 |
Goat | +0.465 |
ドラ | +0.433 |
arge | +0.421 |
hift | +0.416 |
Neg logit contributions | |
]. | -0.387 |
�� | -0.380 |
Nikol | -0.328 |
Rub | -0.325 |
chest | -0.311 |
Token | Republican |
Token ID | 3415 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
blasphemy | +0.057 |
Goat | +0.054 |
ドラ | +0.051 |
arge | +0.049 |
hift | +0.048 |
Neg logit contributions | |
]. | -0.052 |
�� | -0.051 |
Nikol | -0.045 |
Rub | -0.044 |
chest | -0.043 |
Token | state |
Token ID | 1181 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
blasphemy | +0.045 |
Goat | +0.044 |
ドラ | +0.041 |
arge | +0.040 |
hift | +0.039 |
Neg logit contributions | |
]. | -0.033 |
�� | -0.032 |
Nikol | -0.028 |
Rub | -0.028 |
chest | -0.026 |
Token | attorneys |
Token ID | 14449 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
blasphemy | +0.127 |
Goat | +0.122 |
ドラ | +0.115 |
arge | +0.111 |
hift | +0.110 |
Neg logit contributions | |
]. | -0.103 |
�� | -0.100 |
Nikol | -0.088 |
Rub | -0.087 |
chest | -0.083 |
Token | general |
Token ID | 2276 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
blasphemy | +0.104 |
Goat | +0.100 |
ドラ | +0.093 |
arge | +0.088 |
yrinth | +0.088 |
Neg logit contributions | |
]. | -0.128 |
�� | -0.122 |
Nikol | -0.112 |
Rub | -0.110 |
chest | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
]. | +0.786 |
�� | +0.771 |
Nikol | +0.674 |
Rub | +0.663 |
chest | +0.634 |
Neg logit contributions | |
blasphemy | -0.960 |
Goat | -0.928 |
ドラ | -0.867 |
arge | -0.840 |
hift | -0.832 |
Token | oppose |
Token ID | 12856 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
blasphemy | +0.084 |
Goat | +0.081 |
ドラ | +0.076 |
arge | +0.074 |
hift | +0.073 |
Neg logit contributions | |
]. | -0.067 |
�� | -0.064 |
Nikol | -0.056 |
Rub | -0.056 |
chest | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
]. | +0.508 |
�� | +0.492 |
Nikol | +0.437 |
Rub | +0.431 |
chest | +0.411 |
Neg logit contributions | |
blasphemy | -0.567 |
Goat | -0.546 |
ドラ | -0.513 |
arge | -0.494 |
hift | -0.489 |
Token | confirmation |
Token ID | 12641 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
blasphemy | +0.044 |
Goat | +0.042 |
ドラ | +0.040 |
arge | +0.038 |
hift | +0.038 |
Neg logit contributions | |
]. | -0.040 |
�� | -0.039 |
Nikol | -0.035 |
Rub | -0.034 |
chest | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
blasphemy | +0.099 |
Goat | +0.096 |
ドラ | +0.088 |
arge | +0.086 |
hift | +0.084 |
Neg logit contributions | |
]. | -0.099 |
�� | -0.098 |
Nikol | -0.086 |
Rub | -0.085 |
addle | -0.082 |
Token | instead |
Token ID | 2427 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
blasphemy | +0.292 |
Goat | +0.282 |
ドラ | +0.262 |
arge | +0.252 |
hift | +0.249 |
Neg logit contributions | |
]. | -0.300 |
�� | -0.293 |
Nikol | -0.260 |
Rub | -0.256 |
addle | -0.248 |
Token | of |
Token ID | 286 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
blasphemy | +0.196 |
Goat | +0.189 |
ドラ | +0.173 |
arge | +0.169 |
hift | +0.167 |
Neg logit contributions | |
]. | -0.204 |
�� | -0.202 |
Nikol | -0.177 |
Rub | -0.176 |
chest | -0.169 |
Token | his |
Token ID | 465 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
blasphemy | +0.251 |
Goat | +0.243 |
ドラ | +0.230 |
arge | +0.221 |
yrinth | +0.219 |
Neg logit contributions | |
]. | -0.214 |
�� | -0.206 |
Nikol | -0.185 |
Rub | -0.181 |
chest | -0.173 |
Token | less |
Token ID | 1342 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
blasphemy | +0.202 |
Goat | +0.196 |
ドラ | +0.184 |
arge | +0.178 |
hift | +0.176 |
Neg logit contributions | |
]. | -0.169 |
�� | -0.163 |
Nikol | -0.144 |
Rub | -0.142 |
chest | -0.136 |
Token | appreci |
Token ID | 5763 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
]. | +0.038 |
�� | +0.037 |
Nikol | +0.033 |
Rub | +0.033 |
chest | +0.031 |
Neg logit contributions | |
blasphemy | -0.041 |
Goat | -0.040 |
ドラ | -0.037 |
arge | -0.036 |
hift | -0.035 |
Token | ative |
Token ID | 876 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
]. | +0.098 |
�� | +0.096 |
Nikol | +0.085 |
Rub | +0.084 |
chest | +0.081 |
Neg logit contributions | |
blasphemy | -0.087 |
Goat | -0.083 |
ドラ | -0.076 |
arge | -0.074 |
hift | -0.073 |
Token | peers |
Token ID | 14495 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
]. | +0.853 |
�� | +0.811 |
Nikol | +0.752 |
Rub | +0.732 |
chest | +0.712 |
Neg logit contributions | |
blasphemy | -0.782 |
Goat | -0.747 |
ドラ | -0.707 |
yrinth | -0.677 |
arge | -0.674 |
Token | . |
Token ID | 13 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
]. | +0.094 |
�� | +0.091 |
Nikol | +0.081 |
Rub | +0.080 |
addle | +0.077 |
Neg logit contributions | |
blasphemy | -0.092 |
Goat | -0.089 |
ドラ | -0.083 |
arge | -0.080 |
yrinth | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
blasphemy | +0.043 |
Goat | +0.042 |
ドラ | +0.039 |
arge | +0.038 |
hift | +0.038 |
Neg logit contributions | |
]. | -0.033 |
�� | -0.032 |
Nikol | -0.028 |
Rub | -0.028 |
chest | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
]. | +0.001 |
�� | +0.001 |
Rub | +0.001 |
Nikol | +0.001 |
chest | +0.001 |
Neg logit contributions | |
blasphemy | -0.002 |
Goat | -0.002 |
ドラ | -0.002 |
yrinth | -0.002 |
arge | -0.002 |
Token | Amazing |
Token ID | 42770 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
blasphemy | +0.010 |
Goat | +0.010 |
ドラ | +0.009 |
arge | +0.009 |
hift | +0.009 |
Neg logit contributions | |
]. | -0.009 |
�� | -0.009 |
Rub | -0.008 |
Nikol | -0.008 |
chest | -0.007 |