Token | x |
Token ID | 2124 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
Canad | +0.112 |
Veh | +0.104 |
oward | +0.103 |
�� | +0.099 |
Crate | +0.098 |
Neg logit contributions | |
Jinn | -0.112 |
naire | -0.095 |
neys | -0.088 |
Nether | -0.083 |
pton | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Jinn | +0.071 |
naire | +0.061 |
neys | +0.058 |
Nether | +0.055 |
pton | +0.054 |
Neg logit contributions | |
Canad | -0.060 |
Veh | -0.056 |
oward | -0.056 |
�� | -0.053 |
Crate | -0.052 |
Token | x |
Token ID | 87 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
Canad | +0.081 |
Veh | +0.076 |
oward | +0.075 |
�� | +0.072 |
Crate | +0.071 |
Neg logit contributions | |
Jinn | -0.080 |
naire | -0.068 |
neys | -0.063 |
Nether | -0.059 |
pton | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
Canad | +0.060 |
Veh | +0.055 |
oward | +0.055 |
�� | +0.052 |
Crate | +0.052 |
Neg logit contributions | |
Jinn | -0.070 |
naire | -0.060 |
neys | -0.056 |
Nether | -0.053 |
pton | -0.053 |
Token | x |
Token ID | 87 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Canad | +0.555 |
Veh | +0.519 |
oward | +0.512 |
�� | +0.499 |
Crate | +0.488 |
Neg logit contributions | |
Jinn | -0.530 |
naire | -0.451 |
neys | -0.418 |
pton | -0.393 |
Nether | -0.391 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Canad | +1.588 |
Veh | +1.448 |
oward | +1.417 |
�� | +1.414 |
Crate | +1.335 |
Neg logit contributions | |
Jinn | -2.293 |
naire | -2.019 |
neys | -1.887 |
Nether | -1.801 |
pton | -1.798 |
Token | 148 |
Token ID | 18294 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Canad | +1.863 |
Veh | +1.592 |
oward | +1.524 |
Lavrov | +1.431 |
�� | +1.411 |
Neg logit contributions | |
Jinn | -4.830 |
naire | -4.383 |
neys | -4.146 |
Nether | -4.029 |
acle | -3.998 |
Token | 10 |
Token ID | 838 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
Canad | +0.586 |
Veh | +0.537 |
oward | +0.536 |
�� | +0.513 |
Crate | +0.498 |
Neg logit contributions | |
Jinn | -0.879 |
naire | -0.766 |
neys | -0.723 |
Nether | -0.693 |
pton | -0.687 |
Token | 42 |
Token ID | 3682 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
Canad | +0.040 |
Veh | +0.038 |
oward | +0.037 |
�� | +0.036 |
Crate | +0.035 |
Neg logit contributions | |
Jinn | -0.042 |
naire | -0.036 |
neys | -0.034 |
Nether | -0.032 |
pton | -0.032 |
Token | 170 |
Token ID | 17279 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
Canad | +0.281 |
Veh | +0.259 |
oward | +0.257 |
�� | +0.245 |
Crate | +0.242 |
Neg logit contributions | |
Jinn | -0.360 |
naire | -0.312 |
neys | -0.292 |
Nether | -0.278 |
pton | -0.277 |
Token | x |
Token ID | 2124 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
Canad | +0.397 |
Veh | +0.371 |
oward | +0.368 |
�� | +0.355 |
Crate | +0.348 |
Neg logit contributions | |
Jinn | -0.392 |
naire | -0.332 |
neys | -0.308 |
Nether | -0.291 |
pton | -0.290 |
Token | x |
Token ID | 2124 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
Canad | +0.300 |
Veh | +0.280 |
oward | +0.278 |
�� | +0.267 |
Crate | +0.263 |
Neg logit contributions | |
Jinn | -0.298 |
naire | -0.253 |
neys | -0.235 |
Nether | -0.222 |
pton | -0.221 |
Token | . |
Token ID | 13 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
Jinn | +0.046 |
naire | +0.040 |
neys | +0.037 |
Nether | +0.035 |
pton | +0.035 |
Neg logit contributions | |
Canad | -0.039 |
Veh | -0.036 |
oward | -0.036 |
�� | -0.034 |
Crate | -0.034 |
Token | x |
Token ID | 87 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Canad | +0.078 |
Veh | +0.073 |
oward | +0.072 |
�� | +0.069 |
Crate | +0.068 |
Neg logit contributions | |
Jinn | -0.076 |
naire | -0.065 |
neys | -0.060 |
Nether | -0.056 |
pton | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Canad | +0.171 |
Veh | +0.159 |
oward | +0.157 |
�� | +0.151 |
Crate | +0.148 |
Neg logit contributions | |
Jinn | -0.199 |
naire | -0.172 |
neys | -0.160 |
Nether | -0.152 |
pton | -0.152 |
Token | x |
Token ID | 87 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Canad | +1.490 |
Veh | +1.393 |
oward | +1.373 |
�� | +1.362 |
Lavrov | +1.315 |
Neg logit contributions | |
Jinn | -1.384 |
naire | -1.179 |
neys | -1.094 |
pton | -1.029 |
Nether | -1.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
Canad | +1.372 |
Veh | +1.270 |
oward | +1.259 |
�� | +1.251 |
Lavrov | +1.184 |
Neg logit contributions | |
Jinn | -1.660 |
naire | -1.439 |
neys | -1.347 |
Nether | -1.277 |
pton | -1.274 |
Token | 108 |
Token ID | 15711 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
Canad | +2.161 |
Veh | +1.954 |
oward | +1.928 |
�� | +1.827 |
Lavrov | +1.815 |
Neg logit contributions | |
Jinn | -4.131 |
naire | -3.693 |
neys | -3.511 |
Nether | -3.373 |
acle | -3.357 |
Token | 10 |
Token ID | 838 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Canad | +0.483 |
Veh | +0.443 |
oward | +0.441 |
�� | +0.421 |
Crate | +0.411 |
Neg logit contributions | |
Jinn | -0.726 |
naire | -0.633 |
neys | -0.597 |
Nether | -0.572 |
pton | -0.568 |
Token | 46 |
Token ID | 3510 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Jinn | +0.054 |
naire | +0.046 |
neys | +0.043 |
Nether | +0.040 |
pton | +0.040 |
Neg logit contributions | |
Canad | -0.049 |
Veh | -0.046 |
oward | -0.045 |
�� | -0.043 |
Crate | -0.043 |
Token | 358 |
Token ID | 31128 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Canad | +0.174 |
Veh | +0.161 |
oward | +0.159 |
�� | +0.151 |
Crate | +0.150 |
Neg logit contributions | |
Jinn | -0.228 |
naire | -0.198 |
neys | -0.186 |
Nether | -0.177 |
pton | -0.176 |
Token | x |
Token ID | 2124 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
Canad | +0.284 |
Veh | +0.265 |
oward | +0.264 |
�� | +0.254 |
Crate | +0.250 |
Neg logit contributions | |
Jinn | -0.283 |
naire | -0.239 |
neys | -0.223 |
Nether | -0.210 |
pton | -0.209 |
Token | might |
Token ID | 1244 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Jinn | +1.546 |
naire | +1.313 |
neys | +1.215 |
Nether | +1.143 |
pton | +1.136 |
Neg logit contributions | |
Canad | -1.588 |
Veh | -1.485 |
oward | -1.476 |
Crate | -1.408 |
Lavrov | -1.401 |
Token | want |
Token ID | 765 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Canad | +0.849 |
Veh | +0.768 |
oward | +0.758 |
�� | +0.722 |
Lavrov | +0.706 |
Neg logit contributions | |
Jinn | -1.404 |
naire | -1.227 |
neys | -1.159 |
pton | -1.116 |
Nether | -1.112 |
Token | to |
Token ID | 284 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Canad | +0.116 |
Veh | +0.108 |
oward | +0.107 |
�� | +0.102 |
Crate | +0.101 |
Neg logit contributions | |
Jinn | -0.121 |
naire | -0.103 |
neys | -0.096 |
Nether | -0.091 |
pton | -0.090 |
Token | per |
Token ID | 583 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Canad | +1.096 |
Veh | +1.022 |
oward | +1.008 |
�� | +0.965 |
Crate | +0.947 |
Neg logit contributions | |
Jinn | -1.364 |
naire | -1.172 |
neys | -1.086 |
pton | -1.044 |
Nether | -1.037 |
Token | use |
Token ID | 1904 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Canad | +0.294 |
Veh | +0.264 |
oward | +0.258 |
�� | +0.241 |
Lavrov | +0.237 |
Neg logit contributions | |
Jinn | -0.632 |
naire | -0.563 |
neys | -0.533 |
pton | -0.513 |
Nether | -0.513 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Canad | +0.271 |
Veh | +0.252 |
oward | +0.248 |
�� | +0.237 |
Crate | +0.235 |
Neg logit contributions | |
Jinn | -0.315 |
naire | -0.270 |
neys | -0.253 |
Nether | -0.239 |
pton | -0.239 |
Token | Here |
Token ID | 3423 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Canad | +2.030 |
oward | +1.871 |
�� | +1.871 |
Veh | +1.844 |
� | +1.708 |
Neg logit contributions | |
Jinn | -3.803 |
naire | -3.261 |
neys | -3.175 |
Nether | -3.054 |
pton | -3.029 |
Token | is |
Token ID | 318 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Canad | +0.798 |
Veh | +0.736 |
oward | +0.729 |
�� | +0.693 |
Crate | +0.690 |
Neg logit contributions | |
Jinn | -1.003 |
naire | -0.862 |
neys | -0.812 |
Nether | -0.773 |
pton | -0.768 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Jinn | +0.482 |
naire | +0.412 |
neys | +0.383 |
Nether | +0.361 |
pton | +0.361 |
Neg logit contributions | |
Canad | -0.458 |
Veh | -0.427 |
oward | -0.424 |
�� | -0.402 |
Crate | -0.401 |
Token | link |
Token ID | 2792 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Canad | +0.811 |
Veh | +0.744 |
oward | +0.738 |
�� | +0.691 |
Crate | +0.690 |
Neg logit contributions | |
Jinn | -1.162 |
naire | -1.018 |
neys | -0.963 |
Nether | -0.911 |
pton | -0.905 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Jinn | +1.176 |
naire | +1.014 |
neys | +0.947 |
pton | +0.903 |
Nether | +0.899 |
Neg logit contributions | |
Canad | -0.983 |
Veh | -0.916 |
oward | -0.908 |
Lavrov | -0.857 |
Crate | -0.857 |
Token | is |
Token ID | 318 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Canad | +0.798 |
Veh | +0.736 |
oward | +0.729 |
�� | +0.693 |
Crate | +0.690 |
Neg logit contributions | |
Jinn | -1.003 |
naire | -0.862 |
neys | -0.812 |
Nether | -0.773 |
pton | -0.768 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Jinn | +0.482 |
naire | +0.412 |
neys | +0.383 |
Nether | +0.361 |
pton | +0.361 |
Neg logit contributions | |
Canad | -0.458 |
Veh | -0.427 |
oward | -0.424 |
�� | -0.402 |
Crate | -0.401 |
Token | link |
Token ID | 2792 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Canad | +0.811 |
Veh | +0.744 |
oward | +0.738 |
�� | +0.691 |
Crate | +0.690 |
Neg logit contributions | |
Jinn | -1.162 |
naire | -1.018 |
neys | -0.963 |
Nether | -0.911 |
pton | -0.905 |
Token | for |
Token ID | 329 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Jinn | +1.176 |
naire | +1.014 |
neys | +0.947 |
pton | +0.903 |
Nether | +0.899 |
Neg logit contributions | |
Canad | -0.983 |
Veh | -0.916 |
oward | -0.908 |
Lavrov | -0.857 |
Crate | -0.857 |
Token | buying |
Token ID | 7067 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Canad | +0.857 |
oward | +0.798 |
Veh | +0.798 |
�� | +0.756 |
Crate | +0.755 |
Neg logit contributions | |
Jinn | -0.894 |
naire | -0.753 |
neys | -0.712 |
Nether | -0.670 |
pton | -0.660 |
Token | the |
Token ID | 262 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Canad | +1.113 |
Veh | +1.046 |
oward | +1.040 |
�� | +0.997 |
Crate | +0.984 |
Neg logit contributions | |
Jinn | -1.084 |
naire | -0.897 |
neys | -0.854 |
Nether | -0.808 |
pton | -0.792 |
Token | second |
Token ID | 1218 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Canad | +2.433 |
oward | +2.281 |
Veh | +2.280 |
�� | +2.171 |
Crate | +2.114 |
Neg logit contributions | |
Jinn | -3.328 |
naire | -2.783 |
neys | -2.693 |
Nether | -2.608 |
pton | -2.549 |
Token | edition |
Token ID | 8313 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
Canad | +0.818 |
Veh | +0.753 |
oward | +0.748 |
�� | +0.706 |
Crate | +0.697 |
Neg logit contributions | |
Jinn | -1.165 |
naire | -1.018 |
neys | -0.959 |
Nether | -0.912 |
pton | -0.904 |
Token | of |
Token ID | 286 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Canad | +0.055 |
Veh | +0.051 |
oward | +0.051 |
�� | +0.048 |
Crate | +0.048 |
Neg logit contributions | |
Jinn | -0.057 |
naire | -0.048 |
neys | -0.045 |
Nether | -0.042 |
pton | -0.042 |
Token | my |
Token ID | 616 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Canad | +0.497 |
Veh | +0.463 |
oward | +0.460 |
�� | +0.439 |
Crate | +0.434 |
Neg logit contributions | |
Jinn | -0.502 |
naire | -0.422 |
neys | -0.396 |
Nether | -0.376 |
pton | -0.371 |
Token | 1993 |
Token ID | 9656 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Canad | +0.831 |
oward | +0.766 |
Veh | +0.758 |
�� | +0.709 |
Crate | +0.706 |
Neg logit contributions | |
Jinn | -1.227 |
naire | -1.056 |
neys | -1.009 |
Nether | -0.966 |
pton | -0.956 |
Token | x |
Token ID | 2124 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
Canad | +0.374 |
Veh | +0.348 |
oward | +0.347 |
�� | +0.333 |
Crate | +0.328 |
Neg logit contributions | |
Jinn | -0.370 |
naire | -0.313 |
neys | -0.291 |
Nether | -0.274 |
pton | -0.274 |
Token | . |
Token ID | 13 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
Jinn | +0.053 |
naire | +0.046 |
neys | +0.043 |
Nether | +0.041 |
pton | +0.040 |
Neg logit contributions | |
Canad | -0.045 |
Veh | -0.042 |
oward | -0.041 |
�� | -0.039 |
Crate | -0.039 |
Token | x |
Token ID | 87 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
Canad | +0.051 |
Veh | +0.047 |
oward | +0.047 |
�� | +0.045 |
Crate | +0.045 |
Neg logit contributions | |
Jinn | -0.050 |
naire | -0.042 |
neys | -0.039 |
Nether | -0.037 |
pton | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Canad | +0.045 |
Veh | +0.042 |
oward | +0.042 |
�� | +0.040 |
Crate | +0.039 |
Neg logit contributions | |
Jinn | -0.053 |
naire | -0.046 |
neys | -0.043 |
Nether | -0.041 |
pton | -0.040 |
Token | x |
Token ID | 87 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Canad | +0.369 |
Veh | +0.345 |
oward | +0.341 |
�� | +0.331 |
Crate | +0.325 |
Neg logit contributions | |
Jinn | -0.356 |
naire | -0.303 |
neys | -0.281 |
pton | -0.264 |
Nether | -0.263 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Canad | +1.110 |
Veh | +1.030 |
oward | +1.012 |
�� | +1.004 |
Crate | +0.963 |
Neg logit contributions | |
Jinn | -1.223 |
naire | -1.057 |
neys | -0.979 |
pton | -0.930 |
Nether | -0.926 |
Token | 146 |
Token ID | 20964 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Canad | +1.723 |
Veh | +1.504 |
oward | +1.409 |
�� | +1.394 |
Lavrov | +1.356 |
Neg logit contributions | |
Jinn | -3.758 |
naire | -3.429 |
neys | -3.210 |
pton | -3.114 |
Nether | -3.090 |
Token | 112 |
Token ID | 13539 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
Canad | +0.562 |
Veh | +0.515 |
oward | +0.514 |
�� | +0.490 |
Crate | +0.478 |
Neg logit contributions | |
Jinn | -0.835 |
naire | -0.728 |
neys | -0.686 |
Nether | -0.657 |
pton | -0.652 |
Token | 9 |
Token ID | 24 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Jinn | +0.001 |
naire | +0.001 |
neys | +0.001 |
Nether | +0.001 |
pton | +0.001 |
Neg logit contributions | |
Canad | -0.001 |
Veh | -0.001 |
oward | -0.001 |
�� | -0.001 |
Crate | -0.001 |
Token | 222 |
Token ID | 23148 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Canad | +0.248 |
Veh | +0.228 |
oward | +0.226 |
�� | +0.215 |
Crate | +0.213 |
Neg logit contributions | |
Jinn | -0.329 |
naire | -0.286 |
neys | -0.269 |
Nether | -0.256 |
pton | -0.255 |
Token | x |
Token ID | 2124 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Canad | +0.340 |
Veh | +0.317 |
oward | +0.315 |
�� | +0.304 |
Crate | +0.298 |
Neg logit contributions | |
Jinn | -0.337 |
naire | -0.285 |
neys | -0.265 |
Nether | -0.250 |
pton | -0.249 |
Token | x |
Token ID | 2124 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
Canad | +0.281 |
Veh | +0.262 |
oward | +0.261 |
�� | +0.250 |
Crate | +0.247 |
Neg logit contributions | |
Jinn | -0.279 |
naire | -0.237 |
neys | -0.220 |
Nether | -0.208 |
pton | -0.207 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Jinn | +0.040 |
naire | +0.035 |
neys | +0.032 |
Nether | +0.031 |
pton | +0.031 |
Neg logit contributions | |
Canad | -0.034 |
Veh | -0.032 |
oward | -0.031 |
�� | -0.030 |
Crate | -0.030 |
Token | x |
Token ID | 87 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
Canad | +0.118 |
Veh | +0.110 |
oward | +0.109 |
�� | +0.105 |
Crate | +0.104 |
Neg logit contributions | |
Jinn | -0.115 |
naire | -0.098 |
neys | -0.091 |
pton | -0.086 |
Nether | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Canad | +0.045 |
Veh | +0.042 |
oward | +0.042 |
�� | +0.040 |
Crate | +0.039 |
Neg logit contributions | |
Jinn | -0.053 |
naire | -0.046 |
neys | -0.043 |
Nether | -0.041 |
pton | -0.041 |
Token | x |
Token ID | 87 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
Canad | +0.325 |
Veh | +0.303 |
oward | +0.300 |
�� | +0.291 |
Crate | +0.286 |
Neg logit contributions | |
Jinn | -0.314 |
naire | -0.267 |
neys | -0.247 |
pton | -0.233 |
Nether | -0.232 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Canad | +0.709 |
Veh | +0.658 |
oward | +0.652 |
�� | +0.637 |
Crate | +0.616 |
Neg logit contributions | |
Jinn | -0.803 |
naire | -0.692 |
neys | -0.643 |
Nether | -0.610 |
pton | -0.610 |
Token | 151 |
Token ID | 24309 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Canad | +1.956 |
Veh | +1.786 |
oward | +1.772 |
�� | +1.688 |
Scand | +1.665 |
Neg logit contributions | |
Jinn | -2.525 |
naire | -2.202 |
neys | -2.040 |
pton | -1.966 |
Nether | -1.966 |
Token | 103 |
Token ID | 15349 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Canad | +0.464 |
Veh | +0.424 |
oward | +0.423 |
�� | +0.402 |
Crate | +0.393 |
Neg logit contributions | |
Jinn | -0.741 |
naire | -0.648 |
neys | -0.613 |
Nether | -0.587 |
pton | -0.583 |
Token | 30 |
Token ID | 1270 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Canad | +0.324 |
Veh | +0.304 |
oward | +0.302 |
�� | +0.292 |
Crate | +0.287 |
Neg logit contributions | |
Jinn | -0.286 |
naire | -0.240 |
neys | -0.222 |
Nether | -0.208 |
pton | -0.207 |
Token | 29 |
Token ID | 1959 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Jinn | +0.107 |
naire | +0.090 |
neys | +0.084 |
Nether | +0.078 |
pton | +0.078 |
Neg logit contributions | |
Canad | -0.115 |
Veh | -0.107 |
oward | -0.107 |
�� | -0.102 |
Crate | -0.101 |
Token | x |
Token ID | 2124 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Canad | +0.307 |
Veh | +0.286 |
oward | +0.285 |
�� | +0.274 |
Crate | +0.270 |
Neg logit contributions | |
Jinn | -0.305 |
naire | -0.258 |
neys | -0.240 |
Nether | -0.227 |
pton | -0.226 |
Token | person |
Token ID | 1048 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Jinn | +0.278 |
naire | +0.238 |
neys | +0.222 |
Nether | +0.210 |
pton | +0.209 |
Neg logit contributions | |
Canad | -0.254 |
Veh | -0.236 |
oward | -0.234 |
�� | -0.222 |
Crate | -0.222 |
Token | of |
Token ID | 286 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Canad | +0.133 |
Veh | +0.124 |
oward | +0.123 |
�� | +0.117 |
Crate | +0.116 |
Neg logit contributions | |
Jinn | -0.154 |
naire | -0.133 |
neys | -0.124 |
Nether | -0.118 |
pton | -0.117 |
Token | interest |
Token ID | 1393 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
Jinn | +0.543 |
naire | +0.464 |
neys | +0.432 |
pton | +0.407 |
Nether | +0.406 |
Neg logit contributions | |
Canad | -0.517 |
Veh | -0.481 |
oward | -0.477 |
�� | -0.452 |
Crate | -0.452 |
Token | at |
Token ID | 379 |
Feature activation | -8.76e-02 |
Pos logit contributions | |
Canad | +0.018 |
Veh | +0.017 |
oward | +0.016 |
�� | +0.016 |
Crate | +0.016 |
Neg logit contributions | |
Jinn | -0.020 |
naire | -0.017 |
neys | -0.016 |
Nether | -0.015 |
pton | -0.015 |
Token | Brigham |
Token ID | 37434 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
Jinn | +0.077 |
naire | +0.065 |
neys | +0.061 |
Nether | +0.057 |
pton | +0.057 |
Neg logit contributions | |
Canad | -0.074 |
Veh | -0.069 |
oward | -0.068 |
�� | -0.065 |
Crate | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
Canad | +0.279 |
Veh | +0.260 |
oward | +0.259 |
�� | +0.246 |
Crate | +0.244 |
Neg logit contributions | |
Jinn | -0.297 |
naire | -0.253 |
neys | -0.236 |
Nether | -0.223 |
pton | -0.223 |
Token | Women |
Token ID | 6926 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
Canad | +1.902 |
oward | +1.814 |
Veh | +1.765 |
�� | +1.718 |
Lavrov | +1.658 |
Neg logit contributions | |
Jinn | -2.535 |
naire | -2.141 |
neys | -2.047 |
pton | -1.973 |
Nether | -1.972 |
Token | 's |
Token ID | 338 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
Jinn | +0.231 |
naire | +0.199 |
neys | +0.187 |
Nether | +0.177 |
pton | +0.176 |
Neg logit contributions | |
Canad | -0.192 |
Veh | -0.178 |
oward | -0.176 |
�� | -0.167 |
Crate | -0.166 |
Token | Hospital |
Token ID | 9256 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
Jinn | +0.044 |
naire | +0.038 |
neys | +0.036 |
Nether | +0.034 |
pton | +0.034 |
Neg logit contributions | |
Canad | -0.029 |
Veh | -0.027 |
oward | -0.026 |
�� | -0.025 |
Crate | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
Jinn | +0.197 |
naire | +0.169 |
neys | +0.159 |
Nether | +0.150 |
pton | +0.150 |
Neg logit contributions | |
Canad | -0.167 |
Veh | -0.155 |
oward | -0.153 |
�� | -0.145 |
Crate | -0.145 |
Token | two |
Token ID | 734 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Canad | +0.150 |
Veh | +0.139 |
oward | +0.138 |
�� | +0.131 |
Crate | +0.130 |
Neg logit contributions | |
Jinn | -0.185 |
naire | -0.159 |
neys | -0.149 |
Nether | -0.142 |
pton | -0.141 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Canad | +0.460 |
Veh | +0.421 |
oward | +0.420 |
�� | +0.396 |
Crate | +0.389 |
Neg logit contributions | |
Jinn | -0.666 |
naire | -0.580 |
neys | -0.549 |
Nether | -0.525 |
pton | -0.524 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Canad | +1.149 |
oward | +1.076 |
Veh | +1.063 |
�� | +1.023 |
Lavrov | +1.011 |
Neg logit contributions | |
Jinn | -1.156 |
naire | -0.979 |
neys | -0.921 |
Nether | -0.875 |
pton | -0.859 |
Token | new |
Token ID | 649 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Canad | +0.742 |
oward | +0.682 |
Veh | +0.679 |
�� | +0.644 |
Lavrov | +0.634 |
Neg logit contributions | |
Jinn | -1.012 |
naire | -0.880 |
neys | -0.830 |
Nether | -0.797 |
pton | -0.792 |
Token | features |
Token ID | 3033 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Canad | +0.843 |
oward | +0.768 |
Veh | +0.759 |
�� | +0.720 |
� | +0.697 |
Neg logit contributions | |
Jinn | -1.451 |
naire | -1.279 |
neys | -1.221 |
Nether | -1.172 |
pton | -1.153 |
Token | ( |
Token ID | 357 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
Canad | +1.063 |
Veh | +0.988 |
oward | +0.986 |
�� | +0.943 |
Crate | +0.925 |
Neg logit contributions | |
Jinn | -1.194 |
naire | -1.020 |
neys | -0.955 |
Nether | -0.909 |
pton | -0.905 |
Token | including |
Token ID | 8201 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Canad | +0.049 |
Veh | +0.045 |
oward | +0.045 |
�� | +0.043 |
Crate | +0.043 |
Neg logit contributions | |
Jinn | -0.051 |
naire | -0.044 |
neys | -0.041 |
Nether | -0.038 |
pton | -0.038 |
Token | off |
Token ID | 572 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Canad | +1.488 |
Veh | +1.353 |
oward | +1.329 |
�� | +1.268 |
Lavrov | +1.212 |
Neg logit contributions | |
Jinn | -2.911 |
naire | -2.567 |
neys | -2.470 |
Nether | -2.423 |
pton | -2.396 |
Token | - |
Token ID | 12 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Canad | +0.190 |
Veh | +0.177 |
oward | +0.176 |
�� | +0.167 |
Crate | +0.166 |
Neg logit contributions | |
Jinn | -0.215 |
naire | -0.184 |
neys | -0.173 |
Nether | -0.163 |
pton | -0.162 |
Token | TV |
Token ID | 6849 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Canad | +0.436 |
Veh | +0.412 |
oward | +0.409 |
�� | +0.392 |
Lavrov | +0.389 |
Neg logit contributions | |
Jinn | -0.334 |
naire | -0.277 |
neys | -0.256 |
pton | -0.238 |
Nether | -0.236 |
Token | play |
Token ID | 711 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
Canad | +0.829 |
oward | +0.767 |
Veh | +0.760 |
�� | +0.727 |
Crate | +0.705 |
Neg logit contributions | |
Jinn | -1.228 |
naire | -1.069 |
neys | -1.028 |
Nether | -0.977 |
pton | -0.971 |
Token | ) |
Token ID | 8 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Jinn | +0.084 |
naire | +0.071 |
neys | +0.066 |
Nether | +0.062 |
pton | +0.062 |
Neg logit contributions | |
Canad | -0.082 |
Veh | -0.077 |
oward | -0.076 |
�� | -0.073 |
Crate | -0.072 |
Token | migrants |
Token ID | 12783 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Canad | +1.727 |
oward | +1.607 |
Veh | +1.596 |
�� | +1.519 |
Crate | +1.482 |
Neg logit contributions | |
Jinn | -2.478 |
naire | -2.083 |
neys | -1.976 |
Nether | -1.921 |
pton | -1.919 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Canad | +1.534 |
Veh | +1.454 |
oward | +1.436 |
�� | +1.413 |
� | +1.339 |
Neg logit contributions | |
Jinn | -1.886 |
naire | -1.610 |
neys | -1.525 |
Nether | -1.446 |
pton | -1.414 |
Token | ways |
Token ID | 2842 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Canad | +0.847 |
Veh | +0.791 |
oward | +0.788 |
�� | +0.755 |
Crate | +0.735 |
Neg logit contributions | |
Jinn | -1.035 |
naire | -0.885 |
neys | -0.827 |
pton | -0.797 |
Nether | -0.793 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Canad | +0.466 |
Veh | +0.436 |
oward | +0.433 |
�� | +0.415 |
Crate | +0.408 |
Neg logit contributions | |
Jinn | -0.479 |
naire | -0.409 |
neys | -0.382 |
Nether | -0.359 |
pton | -0.359 |
Token | looms |
Token ID | 46234 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Canad | +1.314 |
oward | +1.211 |
Veh | +1.207 |
�� | +1.155 |
Crate | +1.104 |
Neg logit contributions | |
Jinn | -1.962 |
naire | -1.737 |
neys | -1.641 |
Nether | -1.566 |
pton | -1.556 |
Token | over |
Token ID | 625 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Canad | +1.448 |
Veh | +1.341 |
oward | +1.329 |
�� | +1.259 |
Crate | +1.234 |
Neg logit contributions | |
Jinn | -2.096 |
naire | -1.788 |
neys | -1.701 |
Nether | -1.645 |
pton | -1.623 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Canad | +2.123 |
oward | +2.025 |
Veh | +2.015 |
lov | +1.912 |
�� | +1.902 |
Neg logit contributions | |
Jinn | -2.248 |
naire | -1.907 |
neys | -1.811 |
pton | -1.751 |
Nether | -1.736 |
Token | 2020 |
Token ID | 12131 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Canad | +2.002 |
Veh | +1.904 |
oward | +1.880 |
�� | +1.800 |
lov | +1.781 |
Neg logit contributions | |
Jinn | -1.978 |
naire | -1.643 |
neys | -1.538 |
Nether | -1.504 |
pton | -1.484 |
Token | race |
Token ID | 3234 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Canad | +1.161 |
Veh | +1.067 |
oward | +1.057 |
�� | +1.008 |
Crate | +0.981 |
Neg logit contributions | |
Jinn | -1.580 |
naire | -1.360 |
neys | -1.284 |
pton | -1.237 |
Nether | -1.235 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Canad | +0.718 |
oward | +0.663 |
Veh | +0.660 |
�� | +0.630 |
Crate | +0.607 |
Neg logit contributions | |
Jinn | -1.041 |
naire | -0.906 |
neys | -0.858 |
Nether | -0.818 |
pton | -0.804 |
Token | goes |
Token ID | 2925 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Canad | +1.014 |
Veh | +0.937 |
oward | +0.927 |
�� | +0.884 |
Crate | +0.871 |
Neg logit contributions | |
Jinn | -1.464 |
naire | -1.270 |
neys | -1.213 |
Nether | -1.145 |
pton | -1.141 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
Jinn | +0.149 |
naire | +0.128 |
neys | +0.120 |
Nether | +0.113 |
pton | +0.113 |
Neg logit contributions | |
Canad | -0.133 |
Veh | -0.124 |
oward | -0.123 |
�� | -0.117 |
Crate | -0.116 |
Token | Remember |
Token ID | 16676 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Canad | +0.065 |
Veh | +0.060 |
oward | +0.059 |
�� | +0.057 |
Crate | +0.056 |
Neg logit contributions | |
Jinn | -0.083 |
naire | -0.072 |
neys | -0.068 |
Nether | -0.064 |
pton | -0.064 |
Token | Na |
Token ID | 11013 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Jinn | +0.208 |
naire | +0.178 |
neys | +0.167 |
Nether | +0.158 |
pton | +0.157 |
Neg logit contributions | |
Canad | -0.183 |
Veh | -0.170 |
oward | -0.168 |
�� | -0.160 |
Crate | -0.159 |
Token | V |
Token ID | 53 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Jinn | +1.205 |
naire | +1.036 |
neys | +0.973 |
Nether | +0.921 |
pton | +0.917 |
Neg logit contributions | |
Canad | -0.988 |
Veh | -0.916 |
oward | -0.906 |
Crate | -0.855 |
�� | -0.849 |
Token | or |
Token ID | 273 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
Canad | +0.391 |
Veh | +0.365 |
oward | +0.362 |
�� | +0.350 |
Crate | +0.347 |
Neg logit contributions | |
Jinn | -0.341 |
naire | -0.286 |
neys | -0.265 |
pton | -0.247 |
Nether | -0.247 |
Token | ro |
Token ID | 305 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Canad | +0.360 |
Veh | +0.320 |
oward | +0.319 |
�� | +0.297 |
Crate | +0.288 |
Neg logit contributions | |
Jinn | -0.826 |
naire | -0.733 |
neys | -0.701 |
pton | -0.675 |
Nether | -0.674 |
Token | Bowman |
Token ID | 38774 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Canad | +1.973 |
oward | +1.854 |
Veh | +1.853 |
�� | +1.790 |
Crate | +1.714 |
Neg logit contributions | |
Jinn | -2.429 |
naire | -2.077 |
neys | -1.942 |
Nether | -1.877 |
pton | -1.863 |
Token | at |
Token ID | 379 |
Feature activation | +6.23e-02 |
Pos logit contributions | |
Canad | +0.484 |
Veh | +0.450 |
oward | +0.446 |
�� | +0.425 |
Crate | +0.422 |
Neg logit contributions | |
Jinn | -0.561 |
naire | -0.482 |
neys | -0.450 |
Nether | -0.426 |
pton | -0.426 |
Token | the |
Token ID | 262 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
Canad | +0.052 |
Veh | +0.048 |
oward | +0.048 |
�� | +0.045 |
Crate | +0.045 |
Neg logit contributions | |
Jinn | -0.055 |
naire | -0.047 |
neys | -0.044 |
Nether | -0.042 |
pton | -0.042 |
Token | goal |
Token ID | 3061 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
Canad | +0.356 |
Veh | +0.327 |
oward | +0.326 |
�� | +0.307 |
Crate | +0.304 |
Neg logit contributions | |
Jinn | -0.504 |
naire | -0.437 |
neys | -0.412 |
Nether | -0.394 |
pton | -0.391 |
Token | line |
Token ID | 1627 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
Canad | +0.621 |
Veh | +0.575 |
oward | +0.566 |
�� | +0.540 |
Crate | +0.537 |
Neg logit contributions | |
Jinn | -0.810 |
naire | -0.699 |
neys | -0.654 |
Nether | -0.627 |
pton | -0.622 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Jinn | +0.002 |
naire | +0.001 |
neys | +0.001 |
Nether | +0.001 |
pton | +0.001 |
Neg logit contributions | |
Canad | -0.001 |
Veh | -0.001 |
oward | -0.001 |
�� | -0.001 |
Crate | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Jinn | +0.275 |
naire | +0.238 |
neys | +0.224 |
Nether | +0.213 |
pton | +0.212 |
Neg logit contributions | |
Canad | -0.210 |
Veh | -0.194 |
oward | -0.192 |
�� | -0.181 |
Crate | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Jinn | +0.023 |
naire | +0.020 |
neys | +0.018 |
Nether | +0.017 |
pton | +0.017 |
Neg logit contributions | |
Canad | -0.021 |
Veh | -0.019 |
oward | -0.019 |
�� | -0.018 |
Crate | -0.018 |
Token | Now |
Token ID | 3844 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
Jinn | +0.197 |
naire | +0.168 |
neys | +0.157 |
Nether | +0.148 |
pton | +0.147 |
Neg logit contributions | |
Canad | -0.184 |
Veh | -0.171 |
oward | -0.169 |
�� | -0.161 |
Crate | -0.161 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Jinn | +0.006 |
naire | +0.005 |
neys | +0.005 |
Nether | +0.005 |
pton | +0.005 |
Neg logit contributions | |
Canad | -0.005 |
Veh | -0.005 |
oward | -0.005 |
�� | -0.004 |
Crate | -0.004 |
Token | : |
Token ID | 25 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Jinn | +0.110 |
naire | +0.094 |
neys | +0.087 |
Nether | +0.082 |
pton | +0.082 |
Neg logit contributions | |
Canad | -0.107 |
Veh | -0.100 |
oward | -0.099 |
�� | -0.094 |
Crate | -0.094 |
Token | Watch |
Token ID | 6305 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Canad | +1.581 |
Veh | +1.455 |
oward | +1.448 |
�� | +1.423 |
Lavrov | +1.311 |
Neg logit contributions | |
Jinn | -2.805 |
naire | -2.436 |
neys | -2.317 |
Nether | -2.233 |
pton | -2.214 |
Token | this |
Token ID | 428 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
Canad | +0.143 |
Veh | +0.132 |
oward | +0.132 |
�� | +0.125 |
Crate | +0.124 |
Neg logit contributions | |
Jinn | -0.158 |
naire | -0.135 |
neys | -0.127 |
Nether | -0.120 |
pton | -0.120 |
Token | : |
Token ID | 25 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
Canad | +0.734 |
Veh | +0.681 |
oward | +0.680 |
�� | +0.652 |
Crate | +0.642 |
Neg logit contributions | |
Jinn | -0.720 |
naire | -0.608 |
neys | -0.566 |
Nether | -0.537 |
pton | -0.534 |
Token | Top |
Token ID | 5849 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Jinn | +0.058 |
naire | +0.051 |
neys | +0.048 |
Nether | +0.045 |
pton | +0.045 |
Neg logit contributions | |
Canad | -0.045 |
Veh | -0.041 |
oward | -0.041 |
�� | -0.039 |
Crate | -0.039 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
Canad | +0.140 |
Veh | +0.129 |
oward | +0.129 |
�� | +0.122 |
Crate | +0.121 |
Neg logit contributions | |
Jinn | -0.179 |
naire | -0.155 |
neys | -0.145 |
Nether | -0.138 |
pton | -0.137 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Jinn | +1.274 |
naire | +1.071 |
neys | +0.991 |
Nether | +0.933 |
pton | +0.928 |
Neg logit contributions | |
Canad | -1.369 |
Veh | -1.287 |
oward | -1.268 |
Crate | -1.221 |
�� | -1.219 |
Token | feed |
Token ID | 3745 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Jinn | +1.517 |
naire | +1.298 |
neys | +1.217 |
pton | +1.159 |
Nether | +1.139 |
Neg logit contributions | |
Canad | -1.246 |
Veh | -1.152 |
oward | -1.126 |
Crate | -1.084 |
�� | -1.081 |
Token | by |
Token ID | 416 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Jinn | +0.881 |
naire | +0.725 |
neys | +0.669 |
pton | +0.620 |
Nether | +0.617 |
Neg logit contributions | |
Canad | -1.150 |
Veh | -1.078 |
oward | -1.067 |
Crate | -1.032 |
Lavrov | -1.023 |
Token | going |
Token ID | 1016 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Jinn | +0.608 |
naire | +0.517 |
neys | +0.476 |
pton | +0.448 |
Nether | +0.444 |
Neg logit contributions | |
Canad | -0.657 |
Veh | -0.614 |
oward | -0.608 |
Crate | -0.581 |
�� | -0.579 |
Token | here |
Token ID | 994 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Jinn | +1.360 |
naire | +1.158 |
neys | +1.076 |
pton | +1.019 |
Nether | +1.006 |
Neg logit contributions | |
Canad | -1.303 |
Veh | -1.215 |
oward | -1.199 |
Crate | -1.149 |
Lavrov | -1.143 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
Jinn | +0.025 |
naire | +0.021 |
neys | +0.020 |
Nether | +0.019 |
pton | +0.019 |
Neg logit contributions | |
Canad | -0.021 |
Veh | -0.019 |
oward | -0.019 |
�� | -0.018 |
Crate | -0.018 |
Token | But |
Token ID | 887 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Canad | +1.057 |
Veh | +0.926 |
oward | +0.898 |
�� | +0.869 |
Scand | +0.797 |
Neg logit contributions | |
Jinn | -3.184 |
naire | -2.794 |
neys | -2.672 |
Nether | -2.624 |
pton | -2.580 |
Token | please |
Token ID | 3387 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Jinn | +0.375 |
naire | +0.319 |
neys | +0.297 |
Nether | +0.279 |
pton | +0.279 |
Neg logit contributions | |
Canad | -0.370 |
Veh | -0.344 |
oward | -0.342 |
�� | -0.325 |
Crate | -0.325 |
Token | note |
Token ID | 3465 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Jinn | +0.792 |
naire | +0.697 |
neys | +0.656 |
Nether | +0.624 |
pton | +0.623 |
Neg logit contributions | |
Canad | -0.518 |
Veh | -0.473 |
oward | -0.469 |
Crate | -0.439 |
Lavrov | -0.438 |
Token | that |
Token ID | 326 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Canad | +1.633 |
Veh | +1.535 |
oward | +1.504 |
�� | +1.451 |
Crate | +1.436 |
Neg logit contributions | |
Jinn | -1.755 |
naire | -1.483 |
neys | -1.407 |
Nether | -1.319 |
pton | -1.300 |
Token | my |
Token ID | 616 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Jinn | +0.581 |
naire | +0.498 |
neys | +0.463 |
pton | +0.437 |
Nether | +0.437 |
Neg logit contributions | |
Canad | -0.538 |
Veh | -0.500 |
oward | -0.496 |
Crate | -0.472 |
Lavrov | -0.469 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.91e-01 |
Pos logit contributions | |
Canad | +0.977 |
Veh | +0.915 |
oward | +0.912 |
�� | +0.875 |
Crate | +0.856 |
Neg logit contributions | |
Jinn | -0.974 |
naire | -0.834 |
neys | -0.770 |
Nether | -0.726 |
pton | -0.719 |
Token | : |
Token ID | 25 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
Canad | +0.683 |
Veh | +0.641 |
oward | +0.636 |
�� | +0.609 |
Crate | +0.601 |
Neg logit contributions | |
Jinn | -0.674 |
naire | -0.574 |
neys | -0.535 |
Nether | -0.502 |
pton | -0.498 |
Token | ' |
Token ID | 705 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Jinn | +0.405 |
naire | +0.354 |
neys | +0.334 |
Nether | +0.318 |
pton | +0.318 |
Neg logit contributions | |
Canad | -0.272 |
Veh | -0.249 |
oward | -0.246 |
�� | -0.231 |
Crate | -0.230 |
Token | Damn |
Token ID | 43343 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
Jinn | +0.252 |
naire | +0.218 |
neys | +0.205 |
Nether | +0.195 |
pton | +0.194 |
Neg logit contributions | |
Canad | -0.196 |
Veh | -0.181 |
oward | -0.179 |
�� | -0.169 |
Crate | -0.169 |
Token | right |
Token ID | 826 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Jinn | +0.425 |
naire | +0.367 |
neys | +0.344 |
Nether | +0.326 |
pton | +0.325 |
Neg logit contributions | |
Canad | -0.353 |
Veh | -0.327 |
oward | -0.324 |
Crate | -0.306 |
�� | -0.305 |
Token | ' |
Token ID | 6 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Canad | +0.351 |
Veh | +0.327 |
oward | +0.324 |
�� | +0.309 |
Crate | +0.306 |
Neg logit contributions | |
Jinn | -0.415 |
naire | -0.356 |
neys | -0.333 |
Nether | -0.316 |
pton | -0.314 |
Token | I |
Token ID | 314 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Canad | +1.751 |
oward | +1.646 |
Veh | +1.615 |
�� | +1.563 |
Crate | +1.503 |
Neg logit contributions | |
Jinn | -2.431 |
naire | -2.091 |
neys | -1.953 |
Nether | -1.914 |
pton | -1.891 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Canad | +0.923 |
Veh | +0.866 |
oward | +0.854 |
�� | +0.820 |
Crate | +0.815 |
Neg logit contributions | |
Jinn | -1.079 |
naire | -0.921 |
neys | -0.870 |
pton | -0.823 |
Nether | -0.818 |
Token | make |
Token ID | 787 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Canad | +1.599 |
Veh | +1.486 |
oward | +1.478 |
�� | +1.441 |
Crate | +1.384 |
Neg logit contributions | |
Jinn | -1.733 |
naire | -1.509 |
neys | -1.421 |
pton | -1.346 |
Nether | -1.314 |
Token | the |
Token ID | 262 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Jinn | +0.234 |
naire | +0.200 |
neys | +0.187 |
Nether | +0.177 |
pton | +0.176 |
Neg logit contributions | |
Canad | -0.212 |
Veh | -0.197 |
oward | -0.195 |
�� | -0.185 |
Crate | -0.185 |
Token | large |
Token ID | 1588 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Canad | +0.676 |
oward | +0.629 |
Veh | +0.629 |
�� | +0.596 |
Crate | +0.595 |
Neg logit contributions | |
Jinn | -0.741 |
naire | -0.633 |
neys | -0.596 |
Nether | -0.564 |
pton | -0.557 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Canad | +1.217 |
Veh | +1.138 |
oward | +1.131 |
�� | +1.094 |
Crate | +1.063 |
Neg logit contributions | |
Jinn | -1.243 |
naire | -1.070 |
neys | -0.988 |
Nether | -0.932 |
pton | -0.923 |
Token | : |
Token ID | 25 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Canad | +0.621 |
Veh | +0.582 |
oward | +0.578 |
�� | +0.553 |
Crate | +0.547 |
Neg logit contributions | |
Jinn | -0.617 |
naire | -0.525 |
neys | -0.489 |
Nether | -0.460 |
pton | -0.456 |
Token | ' |
Token ID | 705 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Jinn | +0.621 |
naire | +0.546 |
neys | +0.515 |
Nether | +0.490 |
pton | +0.490 |
Neg logit contributions | |
Canad | -0.403 |
Veh | -0.369 |
oward | -0.364 |
�� | -0.340 |
Crate | -0.340 |
Token | Damn |
Token ID | 43343 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Canad | +0.201 |
Veh | +0.185 |
oward | +0.183 |
�� | +0.175 |
Crate | +0.172 |
Neg logit contributions | |
Jinn | -0.255 |
naire | -0.220 |
neys | -0.208 |
Nether | -0.197 |
pton | -0.196 |
Token | right |
Token ID | 826 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Jinn | +0.364 |
naire | +0.315 |
neys | +0.296 |
Nether | +0.281 |
pton | +0.281 |
Neg logit contributions | |
Canad | -0.285 |
Veh | -0.263 |
oward | -0.261 |
Crate | -0.246 |
�� | -0.245 |
Token | ' |
Token ID | 6 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Canad | +0.496 |
Veh | +0.462 |
oward | +0.458 |
�� | +0.439 |
Crate | +0.434 |
Neg logit contributions | |
Jinn | -0.550 |
naire | -0.470 |
neys | -0.438 |
Nether | -0.415 |
pton | -0.413 |
Token | I |
Token ID | 314 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Canad | +1.687 |
oward | +1.569 |
Veh | +1.551 |
�� | +1.505 |
Crate | +1.435 |
Neg logit contributions | |
Jinn | -2.494 |
naire | -2.151 |
neys | -2.011 |
Nether | -1.975 |
pton | -1.956 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Canad | +1.071 |
Veh | +1.003 |
oward | +0.988 |
�� | +0.953 |
Crate | +0.943 |
Neg logit contributions | |
Jinn | -1.249 |
naire | -1.065 |
neys | -1.006 |
pton | -0.953 |
Nether | -0.947 |
Token | make |
Token ID | 787 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Canad | +1.381 |
Veh | +1.283 |
oward | +1.275 |
�� | +1.243 |
Crate | +1.196 |
Neg logit contributions | |
Jinn | -1.518 |
naire | -1.317 |
neys | -1.240 |
pton | -1.175 |
Nether | -1.153 |
Token | the |
Token ID | 262 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Jinn | +0.195 |
naire | +0.168 |
neys | +0.157 |
Nether | +0.148 |
pton | +0.148 |
Neg logit contributions | |
Canad | -0.171 |
Veh | -0.158 |
oward | -0.157 |
�� | -0.149 |
Crate | -0.148 |
Token | large |
Token ID | 1588 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Canad | +0.761 |
oward | +0.709 |
Veh | +0.708 |
�� | +0.672 |
Crate | +0.671 |
Neg logit contributions | |
Jinn | -0.817 |
naire | -0.696 |
neys | -0.656 |
Nether | -0.619 |
pton | -0.612 |
Token | birth |
Token ID | 4082 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
Jinn | +0.327 |
naire | +0.283 |
neys | +0.265 |
Nether | +0.251 |
pton | +0.251 |
Neg logit contributions | |
Canad | -0.260 |
Veh | -0.240 |
oward | -0.238 |
�� | -0.224 |
Crate | -0.224 |
Token | rate |
Token ID | 2494 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Jinn | +0.928 |
naire | +0.806 |
neys | +0.758 |
Nether | +0.715 |
pton | +0.715 |
Neg logit contributions | |
Canad | -0.734 |
Veh | -0.684 |
oward | -0.677 |
Crate | -0.638 |
�� | -0.637 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Canad | +0.331 |
Veh | +0.308 |
oward | +0.305 |
�� | +0.290 |
Crate | +0.287 |
Neg logit contributions | |
Jinn | -0.406 |
naire | -0.350 |
neys | -0.327 |
Nether | -0.312 |
pton | -0.310 |
Token | America |
Token ID | 2253 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Canad | +1.015 |
Veh | +0.945 |
oward | +0.938 |
�� | +0.900 |
Crate | +0.885 |
Neg logit contributions | |
Jinn | -1.148 |
naire | -0.983 |
neys | -0.912 |
Nether | -0.869 |
pton | -0.866 |
Token | needs |
Token ID | 2476 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Jinn | +0.158 |
naire | +0.136 |
neys | +0.127 |
Nether | +0.121 |
pton | +0.120 |
Neg logit contributions | |
Canad | -0.131 |
Veh | -0.121 |
oward | -0.120 |
�� | -0.114 |
Crate | -0.113 |
Token | future |
Token ID | 2003 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Canad | +2.024 |
Veh | +1.888 |
oward | +1.865 |
lov | +1.813 |
�� | +1.799 |
Neg logit contributions | |
Jinn | -1.994 |
naire | -1.672 |
neys | -1.552 |
pton | -1.499 |
Nether | -1.485 |
Token | migrants |
Token ID | 12783 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Canad | +1.727 |
oward | +1.607 |
Veh | +1.596 |
�� | +1.519 |
Crate | +1.482 |
Neg logit contributions | |
Jinn | -2.478 |
naire | -2.083 |
neys | -1.976 |
Nether | -1.921 |
pton | -1.919 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Canad | +1.534 |
Veh | +1.454 |
oward | +1.436 |
�� | +1.413 |
� | +1.339 |
Neg logit contributions | |
Jinn | -1.886 |
naire | -1.610 |
neys | -1.525 |
Nether | -1.446 |
pton | -1.414 |
Token | ways |
Token ID | 2842 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Canad | +0.847 |
Veh | +0.791 |
oward | +0.788 |
�� | +0.755 |
Crate | +0.735 |
Neg logit contributions | |
Jinn | -1.035 |
naire | -0.885 |
neys | -0.827 |
pton | -0.797 |
Nether | -0.793 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Canad | +0.466 |
Veh | +0.436 |
oward | +0.433 |
�� | +0.415 |
Crate | +0.408 |
Neg logit contributions | |
Jinn | -0.479 |
naire | -0.409 |
neys | -0.382 |
Nether | -0.359 |
pton | -0.359 |
Token | looms |
Token ID | 46234 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Canad | +1.314 |
oward | +1.211 |
Veh | +1.207 |
�� | +1.155 |
Crate | +1.104 |
Neg logit contributions | |
Jinn | -1.962 |
naire | -1.737 |
neys | -1.641 |
Nether | -1.566 |
pton | -1.556 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
Jinn | +0.245 |
naire | +0.206 |
neys | +0.191 |
Nether | +0.180 |
pton | +0.179 |
Neg logit contributions | |
Canad | -0.264 |
Veh | -0.247 |
oward | -0.245 |
�� | -0.234 |
Crate | -0.234 |
Token | I |
Token ID | 314 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
Canad | +0.200 |
Veh | +0.184 |
oward | +0.183 |
�� | +0.173 |
Crate | +0.172 |
Neg logit contributions | |
Jinn | -0.260 |
naire | -0.225 |
neys | -0.212 |
Nether | -0.202 |
pton | -0.201 |
Token | think |
Token ID | 892 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
Canad | +0.136 |
Veh | +0.126 |
oward | +0.125 |
�� | +0.119 |
Crate | +0.118 |
Neg logit contributions | |
Jinn | -0.158 |
naire | -0.136 |
neys | -0.128 |
Nether | -0.121 |
pton | -0.121 |
Token | for |
Token ID | 329 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
Jinn | +0.088 |
naire | +0.076 |
neys | +0.071 |
Nether | +0.067 |
pton | +0.067 |
Neg logit contributions | |
Canad | -0.077 |
Veh | -0.071 |
oward | -0.071 |
�� | -0.067 |
Crate | -0.067 |
Token | quite |
Token ID | 2407 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Jinn | +0.053 |
naire | +0.046 |
neys | +0.044 |
Nether | +0.042 |
pton | +0.042 |
Neg logit contributions | |
Canad | -0.031 |
Veh | -0.028 |
oward | -0.028 |
�� | -0.026 |
Crate | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Canad | +0.963 |
Veh | +0.897 |
oward | +0.888 |
�� | +0.865 |
Crate | +0.844 |
Neg logit contributions | |
Jinn | -0.938 |
naire | -0.798 |
neys | -0.734 |
Nether | -0.697 |
pton | -0.692 |
Token | while |
Token ID | 981 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Canad | +1.537 |
Veh | +1.375 |
oward | +1.360 |
�� | +1.318 |
Lavrov | +1.285 |
Neg logit contributions | |
Jinn | -2.583 |
naire | -2.293 |
neys | -2.136 |
Nether | -2.070 |
pton | -2.060 |
Token | will |
Token ID | 481 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
Jinn | +0.385 |
naire | +0.324 |
neys | +0.300 |
Nether | +0.281 |
pton | +0.280 |
Neg logit contributions | |
Canad | -0.427 |
Veh | -0.400 |
oward | -0.397 |
Crate | -0.378 |
�� | -0.377 |
Token | always |
Token ID | 1464 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Jinn | +0.547 |
naire | +0.466 |
neys | +0.435 |
Nether | +0.411 |
pton | +0.408 |
Neg logit contributions | |
Canad | -0.509 |
Veh | -0.474 |
oward | -0.470 |
Crate | -0.446 |
�� | -0.444 |
Token | be |
Token ID | 307 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
Jinn | +0.371 |
naire | +0.328 |
neys | +0.311 |
Nether | +0.298 |
pton | +0.297 |
Neg logit contributions | |
Canad | -0.200 |
Veh | -0.181 |
oward | -0.179 |
Crate | -0.166 |
�� | -0.166 |
Token | visible |
Token ID | 7424 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
Canad | +0.267 |
Veh | +0.247 |
oward | +0.245 |
�� | +0.234 |
Crate | +0.232 |
Neg logit contributions | |
Jinn | -0.309 |
naire | -0.265 |
neys | -0.248 |
Nether | -0.235 |
pton | -0.234 |
Token | x |
Token ID | 2124 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Canad | +0.330 |
Veh | +0.308 |
oward | +0.306 |
�� | +0.294 |
Crate | +0.289 |
Neg logit contributions | |
Jinn | -0.327 |
naire | -0.277 |
neys | -0.257 |
Nether | -0.242 |
pton | -0.242 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
Jinn | +0.070 |
naire | +0.061 |
neys | +0.057 |
Nether | +0.054 |
pton | +0.054 |
Neg logit contributions | |
Canad | -0.060 |
Veh | -0.055 |
oward | -0.055 |
�� | -0.052 |
Crate | -0.052 |
Token | x |
Token ID | 87 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Canad | +0.116 |
Veh | +0.108 |
oward | +0.107 |
�� | +0.103 |
Crate | +0.102 |
Neg logit contributions | |
Jinn | -0.113 |
naire | -0.096 |
neys | -0.089 |
pton | -0.084 |
Nether | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
Canad | +0.021 |
Veh | +0.019 |
oward | +0.019 |
�� | +0.018 |
Crate | +0.018 |
Neg logit contributions | |
Jinn | -0.024 |
naire | -0.021 |
neys | -0.020 |
Nether | -0.019 |
pton | -0.018 |
Token | x |
Token ID | 87 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
Canad | +0.295 |
Veh | +0.275 |
oward | +0.272 |
�� | +0.264 |
Crate | +0.259 |
Neg logit contributions | |
Jinn | -0.285 |
naire | -0.242 |
neys | -0.225 |
pton | -0.212 |
Nether | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Canad | +0.442 |
Veh | +0.411 |
oward | +0.407 |
�� | +0.395 |
Crate | +0.384 |
Neg logit contributions | |
Jinn | -0.508 |
naire | -0.437 |
neys | -0.407 |
Nether | -0.387 |
pton | -0.386 |
Token | 154 |
Token ID | 21526 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Canad | +1.570 |
Veh | +1.426 |
oward | +1.389 |
�� | +1.328 |
Lavrov | +1.313 |
Neg logit contributions | |
Jinn | -2.566 |
naire | -2.288 |
neys | -2.123 |
pton | -2.050 |
Nether | -2.049 |
Token | 109 |
Token ID | 16003 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Canad | +0.588 |
Veh | +0.538 |
oward | +0.537 |
�� | +0.513 |
Crate | +0.498 |
Neg logit contributions | |
Jinn | -0.913 |
naire | -0.797 |
neys | -0.753 |
Nether | -0.722 |
pton | -0.716 |
Token | 77 |
Token ID | 3324 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Canad | +0.166 |
Veh | +0.156 |
oward | +0.154 |
�� | +0.149 |
Crate | +0.147 |
Neg logit contributions | |
Jinn | -0.155 |
naire | -0.131 |
neys | -0.121 |
Nether | -0.114 |
pton | -0.113 |
Token | 39 |
Token ID | 2670 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Jinn | +0.149 |
naire | +0.126 |
neys | +0.117 |
Nether | +0.110 |
pton | +0.109 |
Neg logit contributions | |
Canad | -0.160 |
Veh | -0.150 |
oward | -0.149 |
�� | -0.142 |
Crate | -0.142 |
Token | x |
Token ID | 2124 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
Canad | +0.281 |
Veh | +0.262 |
oward | +0.261 |
�� | +0.251 |
Crate | +0.247 |
Neg logit contributions | |
Jinn | -0.279 |
naire | -0.236 |
neys | -0.220 |
Nether | -0.207 |
pton | -0.207 |
Token | Trump |
Token ID | 1301 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
Canad | +1.061 |
Veh | +0.965 |
oward | +0.958 |
�� | +0.931 |
Crate | +0.899 |
Neg logit contributions | |
Jinn | -1.575 |
naire | -1.361 |
neys | -1.293 |
Nether | -1.236 |
pton | -1.236 |
Token | House |
Token ID | 18102 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
Canad | +0.375 |
Veh | +0.347 |
oward | +0.343 |
�� | +0.328 |
Crate | +0.325 |
Neg logit contributions | |
Jinn | -0.461 |
naire | -0.398 |
neys | -0.374 |
pton | -0.354 |
Nether | -0.354 |
Token | committee |
Token ID | 5583 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Canad | +0.461 |
Veh | +0.429 |
oward | +0.427 |
�� | +0.406 |
Crate | +0.404 |
Neg logit contributions | |
Jinn | -0.471 |
naire | -0.398 |
neys | -0.372 |
pton | -0.353 |
Nether | -0.352 |
Token | believes |
Token ID | 5804 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Canad | +0.732 |
Veh | +0.690 |
oward | +0.686 |
Crate | +0.653 |
�� | +0.652 |
Neg logit contributions | |
Jinn | -0.651 |
naire | -0.547 |
neys | -0.504 |
Nether | -0.478 |
pton | -0.473 |
Token | it |
Token ID | 340 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Canad | +0.336 |
oward | +0.309 |
Veh | +0.308 |
�� | +0.290 |
Crate | +0.287 |
Neg logit contributions | |
Jinn | -0.478 |
naire | -0.418 |
neys | -0.393 |
Nether | -0.377 |
pton | -0.372 |
Token | has |
Token ID | 468 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Canad | +1.794 |
oward | +1.711 |
Veh | +1.690 |
�� | +1.638 |
Crate | +1.586 |
Neg logit contributions | |
Jinn | -1.686 |
naire | -1.417 |
neys | -1.309 |
Nether | -1.245 |
pton | -1.240 |
Token | evidence |
Token ID | 2370 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Canad | +1.541 |
Veh | +1.424 |
oward | +1.421 |
�� | +1.357 |
Crate | +1.305 |
Neg logit contributions | |
Jinn | -2.554 |
naire | -2.229 |
neys | -2.086 |
Nether | -2.061 |
pton | -2.014 |
Token | Trump |
Token ID | 1301 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Canad | +1.311 |
Veh | +1.218 |
oward | +1.208 |
�� | +1.172 |
Crate | +1.138 |
Neg logit contributions | |
Jinn | -1.483 |
naire | -1.253 |
neys | -1.188 |
pton | -1.134 |
Nether | -1.125 |
Token | requested |
Token ID | 9167 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Canad | +0.467 |
Veh | +0.432 |
oward | +0.430 |
�� | +0.409 |
Crate | +0.406 |
Neg logit contributions | |
Jinn | -0.549 |
naire | -0.469 |
neys | -0.438 |
Nether | -0.416 |
pton | -0.415 |
Token | putting |
Token ID | 5137 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Canad | +1.383 |
Veh | +1.287 |
oward | +1.279 |
�� | +1.213 |
Scand | +1.184 |
Neg logit contributions | |
Jinn | -1.759 |
naire | -1.526 |
neys | -1.434 |
Nether | -1.338 |
pton | -1.333 |
Token | ally |
Token ID | 12525 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
Canad | +0.569 |
Veh | +0.520 |
oward | +0.505 |
�� | +0.471 |
Crate | +0.461 |
Neg logit contributions | |
Jinn | -1.275 |
naire | -1.135 |
neys | -1.077 |
pton | -1.040 |
Nether | -1.035 |
Token | with |
Token ID | 351 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Canad | +0.216 |
Veh | +0.201 |
oward | +0.199 |
�� | +0.189 |
Crate | +0.188 |
Neg logit contributions | |
Jinn | -0.242 |
naire | -0.207 |
neys | -0.194 |
Nether | -0.183 |
pton | -0.183 |
Token | next |
Token ID | 1306 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
Canad | +0.294 |
Veh | +0.272 |
oward | +0.271 |
�� | +0.257 |
Crate | +0.255 |
Neg logit contributions | |
Jinn | -0.358 |
naire | -0.308 |
neys | -0.288 |
Nether | -0.274 |
pton | -0.273 |
Token | - |
Token ID | 12 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
Canad | +0.349 |
Veh | +0.324 |
oward | +0.321 |
�� | +0.305 |
Crate | +0.304 |
Neg logit contributions | |
Jinn | -0.395 |
naire | -0.338 |
neys | -0.317 |
Nether | -0.300 |
pton | -0.299 |
Token | generation |
Token ID | 20158 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
Jinn | +0.037 |
naire | +0.032 |
neys | +0.030 |
Nether | +0.029 |
pton | +0.029 |
Neg logit contributions | |
Canad | -0.025 |
Veh | -0.023 |
oward | -0.022 |
�� | -0.021 |
Crate | -0.021 |
Token | BF |
Token ID | 41646 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
Canad | +0.425 |
Veh | +0.392 |
oward | +0.391 |
�� | +0.370 |
Crate | +0.366 |
Neg logit contributions | |
Jinn | -0.545 |
naire | -0.470 |
neys | -0.441 |
Nether | -0.421 |
pton | -0.420 |
Token | Good |
Token ID | 10248 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Canad | +0.880 |
Veh | +0.821 |
oward | +0.819 |
�� | +0.789 |
Lavrov | +0.777 |
Neg logit contributions | |
Jinn | -0.808 |
naire | -0.679 |
neys | -0.629 |
Nether | -0.594 |
pton | -0.592 |
Token | rich |
Token ID | 7527 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Canad | +1.891 |
Veh | +1.745 |
oward | +1.729 |
�� | +1.705 |
Lavrov | +1.647 |
Neg logit contributions | |
Jinn | -2.152 |
naire | -1.865 |
neys | -1.750 |
Nether | -1.636 |
pton | -1.630 |
Token | All |
Token ID | 1439 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Canad | +0.219 |
Veh | +0.202 |
oward | +0.201 |
�� | +0.191 |
Crate | +0.189 |
Neg logit contributions | |
Jinn | -0.272 |
naire | -0.234 |
neys | -0.220 |
Nether | -0.209 |
pton | -0.208 |
Token | - |
Token ID | 12 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Jinn | +0.108 |
naire | +0.092 |
neys | +0.086 |
Nether | +0.082 |
pton | +0.081 |
Neg logit contributions | |
Canad | -0.094 |
Veh | -0.087 |
oward | -0.087 |
�� | -0.082 |
Crate | -0.082 |
Token | Ter |
Token ID | 15156 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Canad | +0.104 |
Veh | +0.098 |
oward | +0.097 |
�� | +0.093 |
Crate | +0.092 |
Neg logit contributions | |
Jinn | -0.099 |
naire | -0.084 |
neys | -0.078 |
Nether | -0.073 |
pton | -0.073 |
Token | rain |
Token ID | 3201 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Canad | +0.791 |
Veh | +0.722 |
oward | +0.719 |
�� | +0.693 |
Lavrov | +0.672 |
Neg logit contributions | |
Jinn | -1.138 |
naire | -0.993 |
neys | -0.938 |
pton | -0.894 |
Nether | -0.890 |
Token | low |
Token ID | 1877 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
Canad | +1.719 |
oward | +1.590 |
Veh | +1.589 |
�� | +1.522 |
Crate | +1.480 |
Neg logit contributions | |
Jinn | -2.049 |
naire | -1.730 |
neys | -1.632 |
Nether | -1.559 |
pton | -1.521 |
Token | birth |
Token ID | 4082 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
Jinn | +0.327 |
naire | +0.283 |
neys | +0.265 |
Nether | +0.251 |
pton | +0.251 |
Neg logit contributions | |
Canad | -0.260 |
Veh | -0.240 |
oward | -0.238 |
�� | -0.224 |
Crate | -0.224 |
Token | rate |
Token ID | 2494 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Jinn | +0.928 |
naire | +0.806 |
neys | +0.758 |
Nether | +0.715 |
pton | +0.715 |
Neg logit contributions | |
Canad | -0.734 |
Veh | -0.684 |
oward | -0.677 |
Crate | -0.638 |
�� | -0.637 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Canad | +0.331 |
Veh | +0.308 |
oward | +0.305 |
�� | +0.290 |
Crate | +0.287 |
Neg logit contributions | |
Jinn | -0.406 |
naire | -0.350 |
neys | -0.327 |
Nether | -0.312 |
pton | -0.310 |
Token | America |
Token ID | 2253 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Canad | +1.015 |
Veh | +0.945 |
oward | +0.938 |
�� | +0.900 |
Crate | +0.885 |
Neg logit contributions | |
Jinn | -1.148 |
naire | -0.983 |
neys | -0.912 |
Nether | -0.869 |
pton | -0.866 |
Token | needs |
Token ID | 2476 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Jinn | +0.158 |
naire | +0.136 |
neys | +0.127 |
Nether | +0.121 |
pton | +0.120 |
Neg logit contributions | |
Canad | -0.131 |
Veh | -0.121 |
oward | -0.120 |
�� | -0.114 |
Crate | -0.113 |
Token | future |
Token ID | 2003 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Canad | +2.024 |
Veh | +1.888 |
oward | +1.865 |
lov | +1.813 |
�� | +1.799 |
Neg logit contributions | |
Jinn | -1.994 |
naire | -1.672 |
neys | -1.552 |
pton | -1.499 |
Nether | -1.485 |
Token | migrants |
Token ID | 12783 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Canad | +1.727 |
oward | +1.607 |
Veh | +1.596 |
�� | +1.519 |
Crate | +1.482 |
Neg logit contributions | |
Jinn | -2.478 |
naire | -2.083 |
neys | -1.976 |
Nether | -1.921 |
pton | -1.919 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Canad | +1.534 |
Veh | +1.454 |
oward | +1.436 |
�� | +1.413 |
� | +1.339 |
Neg logit contributions | |
Jinn | -1.886 |
naire | -1.610 |
neys | -1.525 |
Nether | -1.446 |
pton | -1.414 |
Token | ways |
Token ID | 2842 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Canad | +0.847 |
Veh | +0.791 |
oward | +0.788 |
�� | +0.755 |
Crate | +0.735 |
Neg logit contributions | |
Jinn | -1.035 |
naire | -0.885 |
neys | -0.827 |
pton | -0.797 |
Nether | -0.793 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Canad | +0.466 |
Veh | +0.436 |
oward | +0.433 |
�� | +0.415 |
Crate | +0.408 |
Neg logit contributions | |
Jinn | -0.479 |
naire | -0.409 |
neys | -0.382 |
Nether | -0.359 |
pton | -0.359 |
Token | profile |
Token ID | 7034 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Canad | +0.100 |
Veh | +0.092 |
oward | +0.092 |
�� | +0.087 |
Crate | +0.086 |
Neg logit contributions | |
Jinn | -0.123 |
naire | -0.106 |
neys | -0.099 |
Nether | -0.094 |
pton | -0.094 |
Token | here |
Token ID | 994 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Jinn | +0.329 |
naire | +0.279 |
neys | +0.259 |
Nether | +0.244 |
pton | +0.243 |
Neg logit contributions | |
Canad | -0.334 |
Veh | -0.312 |
oward | -0.310 |
�� | -0.294 |
Crate | -0.294 |
Token | ). |
Token ID | 737 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Jinn | +0.224 |
naire | +0.189 |
neys | +0.176 |
Nether | +0.165 |
pton | +0.165 |
Neg logit contributions | |
Canad | -0.231 |
Veh | -0.216 |
oward | -0.214 |
�� | -0.204 |
Crate | -0.204 |
Token | Talking |
Token ID | 33445 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
Jinn | +0.016 |
naire | +0.014 |
neys | +0.013 |
Nether | +0.012 |
pton | +0.012 |
Neg logit contributions | |
Canad | -0.012 |
Veh | -0.011 |
oward | -0.011 |
�� | -0.010 |
Crate | -0.010 |
Token | Points |
Token ID | 11045 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Jinn | +0.355 |
naire | +0.300 |
neys | +0.279 |
Nether | +0.263 |
pton | +0.262 |
Neg logit contributions | |
Canad | -0.363 |
Veh | -0.339 |
oward | -0.337 |
�� | -0.320 |
Crate | -0.320 |
Token | Mem |
Token ID | 4942 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Jinn | +1.057 |
naire | +0.913 |
neys | +0.862 |
pton | +0.811 |
Nether | +0.810 |
Neg logit contributions | |
Canad | -0.819 |
Veh | -0.755 |
oward | -0.750 |
Crate | -0.707 |
Lavrov | -0.705 |
Token | o |
Token ID | 78 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Jinn | +2.946 |
naire | +2.500 |
neys | +2.385 |
Nether | +2.250 |
pton | +2.231 |
Neg logit contributions | |
Canad | -2.157 |
Veh | -1.948 |
oward | -1.940 |
Crate | -1.814 |
Lavrov | -1.803 |
Token | includes |
Token ID | 3407 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
Jinn | +0.638 |
naire | +0.548 |
neys | +0.513 |
Nether | +0.485 |
pton | +0.484 |
Neg logit contributions | |
Canad | -0.544 |
Veh | -0.504 |
oward | -0.499 |
Crate | -0.472 |
�� | -0.472 |
Token | some |
Token ID | 617 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
Canad | +0.075 |
Veh | +0.069 |
oward | +0.069 |
�� | +0.066 |
Crate | +0.065 |
Neg logit contributions | |
Jinn | -0.082 |
naire | -0.070 |
neys | -0.066 |
Nether | -0.062 |
pton | -0.062 |
Token | of |
Token ID | 286 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
Jinn | +0.072 |
naire | +0.062 |
neys | +0.058 |
Nether | +0.055 |
pton | +0.055 |
Neg logit contributions | |
Canad | -0.059 |
Veh | -0.055 |
oward | -0.054 |
�� | -0.051 |
Crate | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Jinn | +0.127 |
naire | +0.108 |
neys | +0.100 |
Nether | +0.095 |
pton | +0.094 |
Neg logit contributions | |
Canad | -0.124 |
Veh | -0.116 |
oward | -0.115 |
�� | -0.109 |
Crate | -0.109 |
Token | by |
Token ID | 416 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Jinn | +0.279 |
naire | +0.230 |
neys | +0.210 |
Nether | +0.196 |
pton | +0.195 |
Neg logit contributions | |
Canad | -0.371 |
Veh | -0.349 |
oward | -0.347 |
�� | -0.333 |
Crate | -0.332 |
Token | column |
Token ID | 5721 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Jinn | +0.540 |
naire | +0.467 |
neys | +0.435 |
Nether | +0.410 |
pton | +0.408 |
Neg logit contributions | |
Canad | -0.476 |
Veh | -0.440 |
oward | -0.436 |
�� | -0.413 |
Crate | -0.412 |
Token | ists |
Token ID | 1023 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Canad | +0.343 |
Veh | +0.317 |
oward | +0.315 |
�� | +0.298 |
Crate | +0.296 |
Neg logit contributions | |
Jinn | -0.429 |
naire | -0.371 |
neys | -0.348 |
Nether | -0.332 |
pton | -0.330 |
Token | are |
Token ID | 389 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Canad | +0.203 |
Veh | +0.188 |
oward | +0.187 |
�� | +0.176 |
Crate | +0.175 |
Neg logit contributions | |
Jinn | -0.266 |
naire | -0.231 |
neys | -0.217 |
pton | -0.207 |
Nether | -0.206 |
Token | their |
Token ID | 511 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
Jinn | +1.720 |
naire | +1.501 |
neys | +1.403 |
Nether | +1.322 |
pton | +1.299 |
Neg logit contributions | |
Canad | -1.384 |
Veh | -1.277 |
oward | -1.247 |
Crate | -1.191 |
�� | -1.185 |
Token | own |
Token ID | 898 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Jinn | +0.637 |
naire | +0.549 |
neys | +0.515 |
Nether | +0.488 |
pton | +0.485 |
Neg logit contributions | |
Canad | -0.532 |
Veh | -0.491 |
oward | -0.486 |
Crate | -0.461 |
�� | -0.460 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Jinn | +2.669 |
naire | +2.316 |
neys | +2.202 |
Nether | +2.051 |
pton | +2.048 |
Neg logit contributions | |
Canad | -2.000 |
Veh | -1.839 |
oward | -1.773 |
Lavrov | -1.719 |
Crate | -1.714 |
Token | do |
Token ID | 466 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Jinn | +1.274 |
naire | +1.121 |
neys | +1.058 |
Nether | +1.014 |
pton | +1.001 |
Neg logit contributions | |
Canad | -0.755 |
Veh | -0.685 |
oward | -0.668 |
Lavrov | -0.629 |
�� | -0.629 |
Token | not |
Token ID | 407 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Jinn | +0.906 |
naire | +0.780 |
neys | +0.734 |
Nether | +0.693 |
pton | +0.689 |
Neg logit contributions | |
Canad | -0.746 |
Veh | -0.691 |
oward | -0.681 |
Crate | -0.648 |
Lavrov | -0.645 |
Token | represent |
Token ID | 2380 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
Jinn | +1.680 |
naire | +1.443 |
neys | +1.360 |
Nether | +1.293 |
pton | +1.282 |
Neg logit contributions | |
Canad | -1.327 |
Veh | -1.210 |
oward | -1.197 |
Crate | -1.133 |
Lavrov | -1.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Jinn | +0.654 |
naire | +0.560 |
neys | +0.522 |
Nether | +0.492 |
pton | +0.490 |
Neg logit contributions | |
Canad | -0.618 |
Veh | -0.574 |
oward | -0.567 |
Crate | -0.539 |
�� | -0.538 |
Token | " |
Token ID | 366 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
Jinn | +0.180 |
naire | +0.154 |
neys | +0.144 |
Nether | +0.136 |
pton | +0.136 |
Neg logit contributions | |
Canad | -0.164 |
Veh | -0.152 |
oward | -0.151 |
�� | -0.143 |
Crate | -0.143 |
Token | 25 |
Token ID | 1495 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Canad | +0.441 |
Veh | +0.414 |
oward | +0.411 |
�� | +0.397 |
Crate | +0.393 |
Neg logit contributions | |
Jinn | -0.367 |
naire | -0.306 |
neys | -0.282 |
Nether | -0.264 |
pton | -0.263 |
Token | 56 |
Token ID | 3980 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
Canad | +0.359 |
Veh | +0.336 |
oward | +0.333 |
�� | +0.321 |
Crate | +0.317 |
Neg logit contributions | |
Jinn | -0.336 |
naire | -0.284 |
neys | -0.263 |
Nether | -0.247 |
pton | -0.247 |
Token | "] |
Token ID | 8973 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
Canad | +0.672 |
Veh | +0.629 |
oward | +0.626 |
�� | +0.600 |
Crate | +0.598 |
Neg logit contributions | |
Jinn | -0.594 |
naire | -0.500 |
neys | -0.458 |
Nether | -0.433 |
pton | -0.431 |
Token | [ |
Token ID | 685 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Jinn | +0.233 |
naire | +0.200 |
neys | +0.187 |
Nether | +0.177 |
pton | +0.176 |
Neg logit contributions | |
Canad | -0.208 |
Veh | -0.194 |
oward | -0.192 |
Crate | -0.182 |
�� | -0.182 |
Token | Black |
Token ID | 9915 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
Jinn | +0.777 |
naire | +0.633 |
neys | +0.579 |
Nether | +0.527 |
pton | +0.524 |
Neg logit contributions | |
Canad | -1.127 |
Veh | -1.060 |
oward | -1.050 |
Crate | -1.011 |
Lavrov | -1.004 |
Token | E |
Token ID | 36 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Jinn | +2.706 |
naire | +2.337 |
neys | +2.194 |
Nether | +2.089 |
pton | +2.083 |
Neg logit contributions | |
Canad | -1.874 |
oward | -1.687 |
Veh | -1.679 |
Crate | -1.563 |
Lavrov | -1.561 |
Token | lo |
Token ID | 5439 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
Canad | +0.107 |
Veh | +0.096 |
oward | +0.094 |
�� | +0.087 |
Crate | +0.086 |
Neg logit contributions | |
Jinn | -0.250 |
naire | -0.223 |
neys | -0.213 |
pton | -0.205 |
Nether | -0.204 |
Token | " |
Token ID | 366 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
Jinn | +0.017 |
naire | +0.014 |
neys | +0.013 |
Nether | +0.013 |
pton | +0.013 |
Neg logit contributions | |
Canad | -0.015 |
Veh | -0.014 |
oward | -0.014 |
�� | -0.014 |
Crate | -0.013 |
Token | 25 |
Token ID | 1495 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Canad | +0.267 |
Veh | +0.251 |
oward | +0.250 |
�� | +0.241 |
Crate | +0.238 |
Neg logit contributions | |
Jinn | -0.212 |
naire | -0.176 |
neys | -0.162 |
Nether | -0.151 |
pton | -0.150 |
Token | 67 |
Token ID | 3134 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
Jinn | +0.167 |
naire | +0.141 |
neys | +0.131 |
Nether | +0.123 |
pton | +0.122 |
Neg logit contributions | |
Canad | -0.177 |
Veh | -0.166 |
oward | -0.164 |
�� | -0.157 |
Crate | -0.156 |
Token | views |
Token ID | 5009 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Jinn | +1.690 |
naire | +1.449 |
neys | +1.363 |
Nether | +1.273 |
pton | +1.260 |
Neg logit contributions | |
Canad | -1.559 |
Veh | -1.451 |
oward | -1.434 |
Crate | -1.364 |
Lavrov | -1.360 |
Token | of |
Token ID | 286 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Jinn | +0.322 |
naire | +0.275 |
neys | +0.256 |
Nether | +0.242 |
pton | +0.241 |
Neg logit contributions | |
Canad | -0.304 |
Veh | -0.283 |
oward | -0.281 |
Crate | -0.266 |
�� | -0.266 |
Token | Town |
Token ID | 8329 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Jinn | +0.798 |
naire | +0.689 |
neys | +0.642 |
Nether | +0.607 |
pton | +0.606 |
Neg logit contributions | |
Canad | -0.678 |
Veh | -0.624 |
oward | -0.619 |
Crate | -0.585 |
�� | -0.583 |
Token | hall |
Token ID | 18323 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Jinn | +0.358 |
naire | +0.302 |
neys | +0.280 |
Nether | +0.263 |
pton | +0.262 |
Neg logit contributions | |
Canad | -0.381 |
Veh | -0.356 |
oward | -0.354 |
Crate | -0.336 |
�� | -0.336 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Jinn | +2.331 |
naire | +2.019 |
neys | +1.931 |
Nether | +1.808 |
pton | +1.777 |
Neg logit contributions | |
Canad | -1.758 |
Veh | -1.612 |
oward | -1.567 |
Crate | -1.501 |
Lavrov | -1.492 |
Token | com |
Token ID | 785 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Jinn | +0.375 |
naire | +0.320 |
neys | +0.298 |
Nether | +0.281 |
pton | +0.280 |
Neg logit contributions | |
Canad | -0.357 |
Veh | -0.332 |
oward | -0.329 |
Crate | -0.312 |
�� | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Jinn | +2.458 |
naire | +2.133 |
neys | +2.019 |
Nether | +1.895 |
pton | +1.859 |
Neg logit contributions | |
Canad | -1.809 |
Veh | -1.677 |
oward | -1.631 |
Crate | -1.576 |
Lavrov | -1.568 |
Token |
|
Token ID | 198 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Canad | +0.042 |
Veh | +0.039 |
oward | +0.039 |
�� | +0.037 |
Crate | +0.037 |
Neg logit contributions | |
Jinn | -0.046 |
naire | -0.040 |
neys | -0.037 |
Nether | -0.035 |
pton | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
Jinn | +0.066 |
naire | +0.056 |
neys | +0.053 |
Nether | +0.050 |
pton | +0.050 |
Neg logit contributions | |
Canad | -0.059 |
Veh | -0.055 |
oward | -0.054 |
�� | -0.052 |
Crate | -0.051 |
Token | Bernie |
Token ID | 33433 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
Jinn | +0.052 |
naire | +0.045 |
neys | +0.042 |
Nether | +0.040 |
pton | +0.040 |
Neg logit contributions | |
Canad | -0.045 |
Veh | -0.042 |
oward | -0.042 |
�� | -0.040 |
Crate | -0.039 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Canad | +0.563 |
Veh | +0.519 |
oward | +0.516 |
�� | +0.488 |
Crate | +0.482 |
Neg logit contributions | |
Jinn | -0.795 |
naire | -0.690 |
neys | -0.652 |
Nether | -0.622 |
pton | -0.619 |
Token | rate |
Token ID | 2494 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
Jinn | +0.188 |
naire | +0.161 |
neys | +0.151 |
Nether | +0.143 |
pton | +0.142 |
Neg logit contributions | |
Canad | -0.163 |
Veh | -0.151 |
oward | -0.150 |
�� | -0.142 |
Crate | -0.142 |
Token | last |
Token ID | 938 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Canad | +0.005 |
Veh | +0.005 |
oward | +0.005 |
�� | +0.004 |
Crate | +0.004 |
Neg logit contributions | |
Jinn | -0.006 |
naire | -0.005 |
neys | -0.005 |
Nether | -0.005 |
pton | -0.005 |
Token | year |
Token ID | 614 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Canad | +0.319 |
Veh | +0.279 |
oward | +0.274 |
�� | +0.249 |
Crate | +0.248 |
Neg logit contributions | |
Jinn | -0.866 |
naire | -0.777 |
neys | -0.741 |
Nether | -0.714 |
pton | -0.712 |
Token | per |
Token ID | 583 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Canad | +0.272 |
Veh | +0.252 |
oward | +0.250 |
�� | +0.237 |
Crate | +0.236 |
Neg logit contributions | |
Jinn | -0.324 |
naire | -0.280 |
neys | -0.262 |
Nether | -0.248 |
pton | -0.248 |
Token | Football |
Token ID | 9957 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Canad | +0.508 |
Veh | +0.470 |
oward | +0.467 |
�� | +0.443 |
Crate | +0.440 |
Neg logit contributions | |
Jinn | -0.617 |
naire | -0.531 |
neys | -0.498 |
Nether | -0.474 |
pton | -0.471 |
Token | Outs |
Token ID | 46580 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Jinn | +0.426 |
naire | +0.353 |
neys | +0.324 |
Nether | +0.302 |
pton | +0.301 |
Neg logit contributions | |
Canad | -0.537 |
Veh | -0.505 |
oward | -0.501 |
Crate | -0.480 |
�� | -0.478 |
Token | iders |
Token ID | 4157 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
Jinn | +1.521 |
naire | +1.190 |
neys | +1.071 |
Nether | +0.986 |
pton | +0.973 |
Neg logit contributions | |
Canad | -2.656 |
oward | -2.521 |
Veh | -2.502 |
Lavrov | -2.392 |
Crate | -2.390 |
Token | ( |
Token ID | 357 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Jinn | +0.445 |
naire | +0.382 |
neys | +0.359 |
Nether | +0.340 |
pton | +0.339 |
Neg logit contributions | |
Canad | -0.372 |
Veh | -0.345 |
oward | -0.342 |
�� | -0.324 |
Crate | -0.323 |
Token | 56 |
Token ID | 3980 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
Jinn | +0.349 |
naire | +0.297 |
neys | +0.276 |
Nether | +0.260 |
pton | +0.259 |
Neg logit contributions | |
Canad | -0.342 |
Veh | -0.319 |
oward | -0.317 |
�� | -0.301 |
Crate | -0.301 |
Token | percent |
Token ID | 1411 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Jinn | +0.906 |
naire | +0.778 |
neys | +0.728 |
Nether | +0.690 |
pton | +0.687 |
Neg logit contributions | |
Canad | -0.769 |
Veh | -0.715 |
oward | -0.710 |
�� | -0.669 |
Crate | -0.668 |
Token | ). |
Token ID | 737 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
Jinn | +1.139 |
naire | +0.963 |
neys | +0.896 |
Nether | +0.842 |
pton | +0.840 |
Neg logit contributions | |
Canad | -1.153 |
Veh | -1.079 |
oward | -1.073 |
Crate | -1.016 |
�� | -1.014 |
Token | ov |
Token ID | 709 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Jinn | +0.259 |
naire | +0.226 |
neys | +0.213 |
Nether | +0.203 |
pton | +0.203 |
Neg logit contributions | |
Canad | -0.180 |
Veh | -0.165 |
oward | -0.164 |
�� | -0.154 |
Crate | -0.153 |
Token | , |
Token ID | 11 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Canad | +0.298 |
Veh | +0.275 |
oward | +0.273 |
�� | +0.259 |
Crate | +0.258 |
Neg logit contributions | |
Jinn | -0.373 |
naire | -0.322 |
neys | -0.302 |
Nether | -0.287 |
pton | -0.286 |
Token | Mikhail |
Token ID | 42040 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Canad | +0.171 |
Veh | +0.158 |
oward | +0.157 |
�� | +0.149 |
Crate | +0.148 |
Neg logit contributions | |
Jinn | -0.216 |
naire | -0.187 |
neys | -0.175 |
Nether | -0.167 |
pton | -0.166 |
Token | Al |
Token ID | 978 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
Canad | +0.280 |
Veh | +0.262 |
oward | +0.260 |
�� | +0.249 |
Crate | +0.248 |
Neg logit contributions | |
Jinn | -0.255 |
naire | -0.215 |
neys | -0.199 |
Nether | -0.187 |
pton | -0.186 |
Token | "] |
Token ID | 8973 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Jinn | +0.765 |
naire | +0.659 |
neys | +0.618 |
Nether | +0.586 |
pton | +0.583 |
Neg logit contributions | |
Canad | -0.618 |
Veh | -0.573 |
oward | -0.568 |
Crate | -0.534 |
�� | -0.533 |
Token | [ |
Token ID | 685 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Jinn | +0.261 |
naire | +0.223 |
neys | +0.209 |
Nether | +0.197 |
pton | +0.197 |
Neg logit contributions | |
Canad | -0.232 |
Veh | -0.216 |
oward | -0.214 |
Crate | -0.203 |
�� | -0.202 |
Token | Result |
Token ID | 23004 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
Jinn | +2.537 |
naire | +2.226 |
neys | +2.100 |
Nether | +2.009 |
pton | +1.980 |
Neg logit contributions | |
Canad | -1.620 |
Veh | -1.486 |
oward | -1.466 |
Crate | -1.376 |
Lavrov | -1.365 |
Token | " |
Token ID | 366 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
Canad | +0.395 |
Veh | +0.368 |
oward | +0.364 |
�� | +0.350 |
Crate | +0.345 |
Neg logit contributions | |
Jinn | -0.422 |
naire | -0.361 |
neys | -0.336 |
Nether | -0.317 |
pton | -0.315 |
Token | 1 |
Token ID | 16 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Canad | +0.731 |
Veh | +0.686 |
oward | +0.681 |
�� | +0.661 |
Crate | +0.651 |
Neg logit contributions | |
Jinn | -0.567 |
naire | -0.469 |
neys | -0.428 |
Nether | -0.400 |
pton | -0.397 |
Token | / |
Token ID | 14 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
Canad | +0.464 |
Veh | +0.429 |
oward | +0.427 |
�� | +0.408 |
Crate | +0.402 |
Neg logit contributions | |
Jinn | -0.541 |
naire | -0.465 |
neys | -0.433 |
Nether | -0.412 |
pton | -0.411 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
Jinn | +0.006 |
naire | +0.004 |
neys | +0.004 |
Nether | +0.004 |
pton | +0.004 |
Neg logit contributions | |
Canad | -0.008 |
Veh | -0.008 |
oward | -0.008 |
�� | -0.008 |
Crate | -0.008 |
Token | 01 |
Token ID | 5534 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Jinn | +0.667 |
naire | +0.567 |
neys | +0.528 |
pton | +0.496 |
Nether | +0.494 |
Neg logit contributions | |
Canad | -0.672 |
Veh | -0.628 |
oward | -0.620 |
Crate | -0.592 |
Lavrov | -0.589 |
Token | : |
Token ID | 25 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Jinn | +0.251 |
naire | +0.214 |
neys | +0.199 |
Nether | +0.188 |
pton | +0.187 |
Neg logit contributions | |
Canad | -0.242 |
Veh | -0.226 |
oward | -0.224 |
Crate | -0.213 |
�� | -0.212 |
Token | 44 |
Token ID | 2598 |
Feature activation | -1.81e-01 |
Pos logit contributions | |
Jinn | +0.106 |
naire | +0.089 |
neys | +0.082 |
Nether | +0.077 |
pton | +0.077 |
Neg logit contributions | |
Canad | -0.118 |
Veh | -0.110 |
oward | -0.109 |
�� | -0.105 |
Crate | -0.104 |
Token | : |
Token ID | 25 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
Jinn | +0.159 |
naire | +0.135 |
neys | +0.126 |
Nether | +0.119 |
pton | +0.118 |
Neg logit contributions | |
Canad | -0.154 |
Veh | -0.143 |
oward | -0.142 |
�� | -0.135 |
Crate | -0.135 |
Token | 24 |
Token ID | 1731 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Jinn | +0.050 |
naire | +0.042 |
neys | +0.039 |
Nether | +0.037 |
pton | +0.037 |
Neg logit contributions | |
Canad | -0.055 |
Veh | -0.052 |
oward | -0.052 |
�� | -0.049 |
Crate | -0.049 |
Token | # |
Token ID | 1303 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Jinn | +0.317 |
naire | +0.273 |
neys | +0.255 |
Nether | +0.241 |
pton | +0.241 |
Neg logit contributions | |
Canad | -0.272 |
Veh | -0.252 |
oward | -0.250 |
Crate | -0.237 |
�� | -0.236 |
Token | 19 |
Token ID | 1129 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Jinn | +1.576 |
naire | +1.240 |
neys | +1.125 |
Nether | +1.034 |
pton | +1.007 |
Neg logit contributions | |
Canad | -2.528 |
Veh | -2.412 |
oward | -2.405 |
Crate | -2.309 |
Lavrov | -2.294 |
Token | edit |
Token ID | 4370 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Canad | +0.113 |
Veh | +0.103 |
oward | +0.102 |
�� | +0.095 |
Crate | +0.095 |
Neg logit contributions | |
Jinn | -0.199 |
naire | -0.175 |
neys | -0.166 |
Nether | -0.159 |
pton | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Jinn | +0.346 |
naire | +0.295 |
neys | +0.275 |
Nether | +0.260 |
pton | +0.259 |
Neg logit contributions | |
Canad | -0.321 |
Veh | -0.298 |
oward | -0.296 |
�� | -0.281 |
Crate | -0.281 |
Token | n |
Token ID | 299 |
Feature activation | -6.34e-01 |
Pos logit contributions | |
Jinn | +0.324 |
naire | +0.281 |
neys | +0.264 |
Nether | +0.250 |
pton | +0.250 |
Neg logit contributions | |
Canad | -0.249 |
Veh | -0.230 |
oward | -0.228 |
�� | -0.215 |
Crate | -0.215 |
Token | vm |
Token ID | 14761 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
Jinn | +0.559 |
naire | +0.475 |
neys | +0.443 |
Nether | +0.418 |
pton | +0.416 |
Neg logit contributions | |
Canad | -0.533 |
Veh | -0.496 |
oward | -0.493 |
Crate | -0.467 |
�� | -0.467 |
Token | hy |
Token ID | 2537 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Jinn | +0.035 |
naire | +0.030 |
neys | +0.028 |
Nether | +0.026 |
pton | +0.026 |
Neg logit contributions | |
Canad | -0.031 |
Veh | -0.029 |
oward | -0.029 |
�� | -0.027 |
Crate | -0.027 |
Token | men |
Token ID | 3653 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Jinn | +0.445 |
naire | +0.389 |
neys | +0.366 |
Nether | +0.350 |
pton | +0.348 |
Neg logit contributions | |
Canad | -0.298 |
Veh | -0.273 |
oward | -0.271 |
�� | -0.254 |
Crate | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
Canad | +0.171 |
Veh | +0.159 |
oward | +0.158 |
�� | +0.150 |
Crate | +0.149 |
Neg logit contributions | |
Jinn | -0.197 |
naire | -0.169 |
neys | -0.158 |
Nether | -0.150 |
pton | -0.149 |
Token |
|
Token ID | 198 |
Feature activation | +6.43e-03 |
Pos logit contributions | |
Canad | +0.064 |
Veh | +0.059 |
oward | +0.059 |
�� | +0.056 |
Crate | +0.055 |
Neg logit contributions | |
Jinn | -0.078 |
naire | -0.067 |
neys | -0.063 |
Nether | -0.060 |
pton | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
Canad | +0.005 |
Veh | +0.005 |
oward | +0.005 |
�� | +0.005 |
Crate | +0.005 |
Neg logit contributions | |
Jinn | -0.006 |
naire | -0.005 |
neys | -0.005 |
Nether | -0.004 |
pton | -0.004 |
Token | [ |
Token ID | 58 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Canad | +0.016 |
Veh | +0.015 |
oward | +0.015 |
�� | +0.015 |
Crate | +0.015 |
Neg logit contributions | |
Jinn | -0.012 |
naire | -0.010 |
neys | -0.009 |
Nether | -0.009 |
pton | -0.009 |
Token | 23 |
Token ID | 1954 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Jinn | +1.264 |
naire | +0.933 |
neys | +0.808 |
Nether | +0.724 |
pton | +0.693 |
Neg logit contributions | |
Canad | -2.832 |
oward | -2.694 |
Veh | -2.676 |
Lavrov | -2.595 |
Crate | -2.594 |
Token | ] |
Token ID | 60 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Canad | +0.249 |
Veh | +0.228 |
oward | +0.226 |
�� | +0.217 |
Crate | +0.211 |
Neg logit contributions | |
Jinn | -0.376 |
naire | -0.329 |
neys | -0.310 |
Nether | -0.296 |
pton | -0.295 |
Token | Similarly |
Token ID | 15298 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Canad | +0.174 |
Veh | +0.160 |
oward | +0.159 |
�� | +0.151 |
Crate | +0.149 |
Neg logit contributions | |
Jinn | -0.229 |
naire | -0.198 |
neys | -0.186 |
Nether | -0.178 |
pton | -0.177 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Canad | +0.096 |
Veh | +0.089 |
oward | +0.088 |
�� | +0.084 |
Crate | +0.083 |
Neg logit contributions | |
Jinn | -0.118 |
naire | -0.102 |
neys | -0.095 |
Nether | -0.091 |
pton | -0.090 |
Token | Levi |
Token ID | 20196 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
Canad | +0.166 |
Veh | +0.154 |
oward | +0.153 |
�� | +0.145 |
Crate | +0.144 |
Neg logit contributions | |
Jinn | -0.189 |
naire | -0.161 |
neys | -0.151 |
Nether | -0.143 |
pton | -0.143 |
Token | represent |
Token ID | 2380 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
Jinn | +1.680 |
naire | +1.443 |
neys | +1.360 |
Nether | +1.293 |
pton | +1.282 |
Neg logit contributions | |
Canad | -1.327 |
Veh | -1.210 |
oward | -1.197 |
Crate | -1.133 |
Lavrov | -1.128 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Jinn | +0.654 |
naire | +0.560 |
neys | +0.522 |
Nether | +0.492 |
pton | +0.490 |
Neg logit contributions | |
Canad | -0.618 |
Veh | -0.574 |
oward | -0.567 |
Crate | -0.539 |
�� | -0.538 |
Token | views |
Token ID | 5009 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Jinn | +1.690 |
naire | +1.449 |
neys | +1.363 |
Nether | +1.273 |
pton | +1.260 |
Neg logit contributions | |
Canad | -1.559 |
Veh | -1.451 |
oward | -1.434 |
Crate | -1.364 |
Lavrov | -1.360 |
Token | of |
Token ID | 286 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Jinn | +0.322 |
naire | +0.275 |
neys | +0.256 |
Nether | +0.242 |
pton | +0.241 |
Neg logit contributions | |
Canad | -0.304 |
Veh | -0.283 |
oward | -0.281 |
Crate | -0.266 |
�� | -0.266 |
Token | Town |
Token ID | 8329 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Jinn | +0.798 |
naire | +0.689 |
neys | +0.642 |
Nether | +0.607 |
pton | +0.606 |
Neg logit contributions | |
Canad | -0.678 |
Veh | -0.624 |
oward | -0.619 |
Crate | -0.585 |
�� | -0.583 |
Token | hall |
Token ID | 18323 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Jinn | +0.358 |
naire | +0.302 |
neys | +0.280 |
Nether | +0.263 |
pton | +0.262 |
Neg logit contributions | |
Canad | -0.381 |
Veh | -0.356 |
oward | -0.354 |
Crate | -0.336 |
�� | -0.336 |
Token | . |
Token ID | 13 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
Jinn | +2.331 |
naire | +2.019 |
neys | +1.931 |
Nether | +1.808 |
pton | +1.777 |
Neg logit contributions | |
Canad | -1.758 |
Veh | -1.612 |
oward | -1.567 |
Crate | -1.501 |
Lavrov | -1.492 |
Token | com |
Token ID | 785 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
Jinn | +0.375 |
naire | +0.320 |
neys | +0.298 |
Nether | +0.281 |
pton | +0.280 |
Neg logit contributions | |
Canad | -0.357 |
Veh | -0.332 |
oward | -0.329 |
Crate | -0.312 |
�� | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
Jinn | +2.458 |
naire | +2.133 |
neys | +2.019 |
Nether | +1.895 |
pton | +1.859 |
Neg logit contributions | |
Canad | -1.809 |
Veh | -1.677 |
oward | -1.631 |
Crate | -1.576 |
Lavrov | -1.568 |
Token |
|
Token ID | 198 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
Canad | +0.042 |
Veh | +0.039 |
oward | +0.039 |
�� | +0.037 |
Crate | +0.037 |
Neg logit contributions | |
Jinn | -0.046 |
naire | -0.040 |
neys | -0.037 |
Nether | -0.035 |
pton | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
Jinn | +0.066 |
naire | +0.056 |
neys | +0.053 |
Nether | +0.050 |
pton | +0.050 |
Neg logit contributions | |
Canad | -0.059 |
Veh | -0.055 |
oward | -0.054 |
�� | -0.052 |
Crate | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
Jinn | +0.182 |
naire | +0.156 |
neys | +0.146 |
Nether | +0.138 |
pton | +0.137 |
Neg logit contributions | |
Canad | -0.160 |
Veh | -0.149 |
oward | -0.147 |
�� | -0.140 |
Crate | -0.139 |
Token | air |
Token ID | 1633 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
Jinn | +0.043 |
naire | +0.035 |
neys | +0.032 |
Nether | +0.030 |
pton | +0.030 |
Neg logit contributions | |
Canad | -0.056 |
Veh | -0.053 |
oward | -0.053 |
�� | -0.051 |
Crate | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
Canad | +0.222 |
Veh | +0.206 |
oward | +0.204 |
�� | +0.194 |
Crate | +0.193 |
Neg logit contributions | |
Jinn | -0.269 |
naire | -0.231 |
neys | -0.217 |
Nether | -0.206 |
pton | -0.205 |
Token | Per |
Token ID | 2448 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
Jinn | +0.027 |
naire | +0.023 |
neys | +0.022 |
Nether | +0.021 |
pton | +0.021 |
Neg logit contributions | |
Canad | -0.020 |
Veh | -0.018 |
oward | -0.018 |
�� | -0.017 |
Crate | -0.017 |
Token | Football |
Token ID | 9957 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Canad | +0.213 |
Veh | +0.198 |
oward | +0.196 |
�� | +0.186 |
Crate | +0.185 |
Neg logit contributions | |
Jinn | -0.255 |
naire | -0.220 |
neys | -0.206 |
Nether | -0.195 |
pton | -0.195 |
Token | Outs |
Token ID | 46580 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Jinn | +0.234 |
naire | +0.194 |
neys | +0.178 |
Nether | +0.166 |
pton | +0.165 |
Neg logit contributions | |
Canad | -0.296 |
Veh | -0.278 |
oward | -0.276 |
�� | -0.264 |
Crate | -0.264 |
Token | iders |
Token ID | 4157 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Jinn | +1.457 |
naire | +1.141 |
neys | +1.028 |
Nether | +0.941 |
pton | +0.934 |
Neg logit contributions | |
Canad | -2.561 |
oward | -2.421 |
Veh | -2.414 |
Lavrov | -2.307 |
Crate | -2.304 |
Token | chart |
Token ID | 8262 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Jinn | +0.540 |
naire | +0.466 |
neys | +0.437 |
Nether | +0.415 |
pton | +0.414 |
Neg logit contributions | |
Canad | -0.432 |
Veh | -0.399 |
oward | -0.395 |
�� | -0.374 |
Crate | -0.373 |
Token | ing |
Token ID | 278 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
Jinn | +0.480 |
naire | +0.412 |
neys | +0.387 |
Nether | +0.366 |
pton | +0.366 |
Neg logit contributions | |
Canad | -0.406 |
Veh | -0.376 |
oward | -0.373 |
�� | -0.353 |
Crate | -0.353 |
Token | , |
Token ID | 11 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Jinn | +0.611 |
naire | +0.524 |
neys | +0.490 |
pton | +0.463 |
Nether | +0.463 |
Neg logit contributions | |
Canad | -0.537 |
Veh | -0.498 |
oward | -0.493 |
Crate | -0.468 |
�� | -0.467 |
Token | the |
Token ID | 262 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Jinn | +0.497 |
naire | +0.426 |
neys | +0.398 |
Nether | +0.376 |
pton | +0.375 |
Neg logit contributions | |
Canad | -0.445 |
Veh | -0.413 |
oward | -0.409 |
Crate | -0.388 |
�� | -0.388 |
Token | |
Token ID | 3907 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Jinn | +0.929 |
naire | +0.771 |
neys | +0.712 |
Nether | +0.661 |
pton | +0.658 |
Neg logit contributions | |
Canad | -1.143 |
Veh | -1.072 |
oward | -1.065 |
Crate | -1.020 |
Lavrov | -1.014 |
Token | tion |
Token ID | 5378 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
Jinn | +0.545 |
naire | +0.469 |
neys | +0.440 |
Nether | +0.419 |
pton | +0.416 |
Neg logit contributions | |
Canad | -0.429 |
Veh | -0.396 |
oward | -0.393 |
Crate | -0.371 |
�� | -0.370 |
Token | last |
Token ID | 938 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
Jinn | +0.423 |
naire | +0.361 |
neys | +0.337 |
Nether | +0.319 |
pton | +0.318 |
Neg logit contributions | |
Canad | -0.391 |
Veh | -0.363 |
oward | -0.360 |
Crate | -0.341 |
�� | -0.341 |
Token | Jan |
Token ID | 2365 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Canad | +0.396 |
Veh | +0.361 |
oward | +0.357 |
�� | +0.336 |
Crate | +0.332 |
Neg logit contributions | |
Jinn | -0.677 |
naire | -0.595 |
neys | -0.563 |
Nether | -0.540 |
pton | -0.537 |
Token | u |
Token ID | 84 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Jinn | +0.429 |
naire | +0.370 |
neys | +0.347 |
Nether | +0.329 |
pton | +0.327 |
Neg logit contributions | |
Canad | -0.357 |
Veh | -0.331 |
oward | -0.328 |
Crate | -0.310 |
�� | -0.310 |
Token | |
Token ID | 3907 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Jinn | +0.745 |
naire | +0.616 |
neys | +0.567 |
Nether | +0.530 |
pton | +0.527 |
Neg logit contributions | |
Canad | -0.922 |
Veh | -0.864 |
oward | -0.859 |
Crate | -0.822 |
Lavrov | -0.817 |
Token | ary |
Token ID | 560 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
Jinn | +2.067 |
naire | +1.687 |
neys | +1.592 |
Nether | +1.520 |
pton | +1.492 |
Neg logit contributions | |
Canad | -1.978 |
oward | -1.817 |
Veh | -1.796 |
Crate | -1.738 |
lov | -1.721 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Canad | +0.025 |
Veh | +0.023 |
oward | +0.023 |
�� | +0.021 |
Crate | +0.021 |
Neg logit contributions | |
Jinn | -0.028 |
naire | -0.024 |
neys | -0.023 |
Nether | -0.021 |
pton | -0.021 |
Token | � |
Token ID | 564 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
Canad | +0.142 |
Veh | +0.131 |
oward | +0.130 |
�� | +0.124 |
Crate | +0.122 |
Neg logit contributions | |
Jinn | -0.187 |
naire | -0.162 |
neys | -0.152 |
Nether | -0.145 |
pton | -0.144 |
Token | � |
Token ID | 250 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Canad | +0.388 |
Veh | +0.349 |
oward | +0.345 |
�� | +0.318 |
Crate | +0.317 |
Neg logit contributions | |
Jinn | -0.752 |
naire | -0.666 |
neys | -0.632 |
Nether | -0.606 |
pton | -0.605 |
Token | Bar |
Token ID | 10374 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
Canad | +0.082 |
Veh | +0.076 |
oward | +0.075 |
�� | +0.071 |
Crate | +0.071 |
Neg logit contributions | |
Jinn | -0.099 |
naire | -0.085 |
neys | -0.080 |
Nether | -0.076 |
pton | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Jinn | +0.216 |
naire | +0.185 |
neys | +0.173 |
Nether | +0.164 |
pton | +0.163 |
Neg logit contributions | |
Canad | -0.192 |
Veh | -0.179 |
oward | -0.177 |
�� | -0.168 |
Crate | -0.168 |
Token | Please |
Token ID | 5492 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Jinn | +0.143 |
naire | +0.122 |
neys | +0.114 |
Nether | +0.108 |
pton | +0.107 |
Neg logit contributions | |
Canad | -0.132 |
Veh | -0.123 |
oward | -0.122 |
�� | -0.116 |
Crate | -0.116 |
Token | help |
Token ID | 1037 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
Canad | +0.147 |
Veh | +0.134 |
oward | +0.133 |
�� | +0.125 |
Crate | +0.124 |
Neg logit contributions | |
Jinn | -0.225 |
naire | -0.196 |
neys | -0.185 |
Nether | -0.177 |
pton | -0.177 |
Token | support |
Token ID | 1104 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Jinn | +0.348 |
naire | +0.307 |
neys | +0.290 |
Nether | +0.278 |
pton | +0.277 |
Neg logit contributions | |
Canad | -0.201 |
Veh | -0.183 |
oward | -0.181 |
�� | -0.168 |
Crate | -0.168 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Jinn | +0.569 |
naire | +0.487 |
neys | +0.452 |
pton | +0.426 |
Nether | +0.425 |
Neg logit contributions | |
Canad | -0.537 |
Veh | -0.499 |
oward | -0.494 |
Crate | -0.471 |
�� | -0.469 |
Token | mission |
Token ID | 4365 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Jinn | +1.042 |
naire | +0.888 |
neys | +0.815 |
pton | +0.756 |
Nether | +0.749 |
Neg logit contributions | |
Canad | -1.203 |
Veh | -1.118 |
oward | -1.100 |
Crate | -1.064 |
Scand | -1.048 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Jinn | +2.157 |
naire | +1.833 |
neys | +1.711 |
pton | +1.630 |
Nether | +1.621 |
Neg logit contributions | |
Canad | -1.823 |
Veh | -1.685 |
oward | -1.678 |
Crate | -1.625 |
Lavrov | -1.586 |
Token | New |
Token ID | 968 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Jinn | +1.277 |
naire | +1.097 |
neys | +1.015 |
pton | +0.956 |
Nether | +0.943 |
Neg logit contributions | |
Canad | -1.253 |
Veh | -1.145 |
oward | -1.140 |
Crate | -1.089 |
�� | -1.078 |
Token | Advent |
Token ID | 33732 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Jinn | +0.897 |
naire | +0.751 |
neys | +0.695 |
pton | +0.651 |
Nether | +0.640 |
Neg logit contributions | |
Canad | -1.046 |
Veh | -0.978 |
oward | -0.968 |
Crate | -0.931 |
�� | -0.923 |
Token | and |
Token ID | 290 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Jinn | +0.155 |
naire | +0.133 |
neys | +0.124 |
Nether | +0.118 |
pton | +0.117 |
Neg logit contributions | |
Canad | -0.137 |
Veh | -0.127 |
oward | -0.126 |
�� | -0.120 |
Crate | -0.119 |
Token | get |
Token ID | 651 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
Canad | +0.873 |
Veh | +0.799 |
oward | +0.798 |
�� | +0.751 |
Lavrov | +0.737 |
Neg logit contributions | |
Jinn | -1.418 |
naire | -1.256 |
neys | -1.187 |
Nether | -1.138 |
pton | -1.122 |
Token | current |
Token ID | 1459 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Jinn | +0.063 |
naire | +0.054 |
neys | +0.051 |
Nether | +0.048 |
pton | +0.048 |
Neg logit contributions | |
Canad | -0.053 |
Veh | -0.049 |
oward | -0.049 |
�� | -0.046 |
Crate | -0.046 |
Token | best |
Token ID | 1266 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Jinn | +0.109 |
naire | +0.094 |
neys | +0.088 |
Nether | +0.084 |
pton | +0.083 |
Neg logit contributions | |
Canad | -0.091 |
Veh | -0.084 |
oward | -0.084 |
�� | -0.079 |
Crate | -0.079 |
Token | - |
Token ID | 12 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Jinn | +1.059 |
naire | +0.915 |
neys | +0.859 |
Nether | +0.815 |
pton | +0.813 |
Neg logit contributions | |
Canad | -0.831 |
Veh | -0.770 |
oward | -0.763 |
Crate | -0.716 |
�� | -0.714 |
Token | of |
Token ID | 1659 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Jinn | +0.495 |
naire | +0.422 |
neys | +0.394 |
Nether | +0.372 |
pton | +0.371 |
Neg logit contributions | |
Canad | -0.457 |
Veh | -0.426 |
oward | -0.423 |
�� | -0.400 |
Crate | -0.400 |
Token | - |
Token ID | 12 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Jinn | +0.527 |
naire | +0.453 |
neys | +0.424 |
Nether | +0.402 |
pton | +0.400 |
Neg logit contributions | |
Canad | -0.452 |
Veh | -0.419 |
oward | -0.416 |
�� | -0.393 |
Crate | -0.392 |
Token | bre |
Token ID | 4679 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Jinn | +0.437 |
naire | +0.372 |
neys | +0.347 |
Nether | +0.328 |
pton | +0.327 |
Neg logit contributions | |
Canad | -0.411 |
Veh | -0.383 |
oward | -0.380 |
�� | -0.360 |
Crate | -0.360 |
Token | ed |
Token ID | 276 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
Jinn | +1.859 |
naire | +1.534 |
neys | +1.422 |
Nether | +1.344 |
acle | +1.315 |
Neg logit contributions | |
Canad | -2.069 |
oward | -1.931 |
Veh | -1.927 |
Crate | -1.827 |
�� | -1.820 |
Token | C |
Token ID | 327 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Jinn | +0.681 |
naire | +0.585 |
neys | +0.547 |
Nether | +0.518 |
pton | +0.516 |
Neg logit contributions | |
Canad | -0.585 |
Veh | -0.543 |
oward | -0.538 |
Crate | -0.509 |
�� | -0.508 |
Token | UB |
Token ID | 10526 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Jinn | +0.363 |
naire | +0.306 |
neys | +0.284 |
Nether | +0.267 |
pton | +0.266 |
Neg logit contributions | |
Canad | -0.380 |
Veh | -0.355 |
oward | -0.353 |
�� | -0.336 |
Crate | -0.335 |
Token | IC |
Token ID | 2149 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
Jinn | +0.237 |
naire | +0.205 |
neys | +0.192 |
Nether | +0.182 |
pton | +0.182 |
Neg logit contributions | |
Canad | -0.192 |
Veh | -0.177 |
oward | -0.176 |
�� | -0.166 |
Crate | -0.166 |
Token | algorithm |
Token ID | 11862 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Jinn | +0.716 |
naire | +0.616 |
neys | +0.577 |
Nether | +0.546 |
pton | +0.544 |
Neg logit contributions | |
Canad | -0.603 |
Veh | -0.559 |
oward | -0.555 |
Crate | -0.524 |
�� | -0.523 |
Token | � |
Token ID | 447 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
Jinn | +1.712 |
naire | +1.448 |
neys | +1.332 |
Nether | +1.290 |
pton | +1.261 |
Neg logit contributions | |
Canad | -1.582 |
Veh | -1.451 |
oward | -1.450 |
Crate | -1.376 |
Lavrov | -1.371 |
Token | � |
Token ID | 247 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Jinn | +0.010 |
naire | +0.009 |
neys | +0.008 |
Nether | +0.008 |
pton | +0.008 |
Neg logit contributions | |
Canad | -0.004 |
Veh | -0.004 |
oward | -0.004 |
�� | -0.004 |
Crate | -0.004 |
Token | ve |
Token ID | 303 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Jinn | +0.791 |
naire | +0.698 |
neys | +0.661 |
Nether | +0.633 |
pton | +0.631 |
Neg logit contributions | |
Canad | -0.430 |
Veh | -0.390 |
oward | -0.385 |
Crate | -0.356 |
�� | -0.355 |
Token | written |
Token ID | 3194 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Canad | +0.285 |
Veh | +0.268 |
oward | +0.266 |
�� | +0.256 |
Crate | +0.255 |
Neg logit contributions | |
Jinn | -0.211 |
naire | -0.173 |
neys | -0.159 |
Nether | -0.147 |
pton | -0.147 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Jinn | +0.457 |
naire | +0.390 |
neys | +0.363 |
Nether | +0.344 |
pton | +0.342 |
Neg logit contributions | |
Canad | -0.432 |
Veh | -0.402 |
oward | -0.399 |
�� | -0.379 |
Crate | -0.378 |
Token | couple |
Token ID | 3155 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
Canad | +0.092 |
Veh | +0.084 |
oward | +0.083 |
�� | +0.078 |
Crate | +0.078 |
Neg logit contributions | |
Jinn | -0.146 |
naire | -0.128 |
neys | -0.121 |
Nether | -0.116 |
pton | -0.115 |
Token | of |
Token ID | 286 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Jinn | +2.101 |
naire | +1.841 |
neys | +1.723 |
Nether | +1.616 |
pton | +1.588 |
Neg logit contributions | |
Canad | -1.806 |
Veh | -1.661 |
oward | -1.647 |
Lavrov | -1.563 |
Crate | -1.562 |
Token | books |
Token ID | 3835 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Jinn | +0.984 |
naire | +0.871 |
neys | +0.823 |
Nether | +0.785 |
pton | +0.780 |
Neg logit contributions | |
Canad | -0.584 |
Veh | -0.530 |
oward | -0.525 |
Crate | -0.488 |
�� | -0.487 |
Token | , |
Token ID | 11 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
Jinn | +1.538 |
naire | +1.330 |
neys | +1.257 |
Nether | +1.198 |
pton | +1.190 |
Neg logit contributions | |
Canad | -1.132 |
oward | -1.036 |
Veh | -1.028 |
Crate | -0.976 |
Lavrov | -0.963 |
Token | which |
Token ID | 543 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Jinn | +0.308 |
naire | +0.263 |
neys | +0.246 |
Nether | +0.232 |
pton | +0.232 |
Neg logit contributions | |
Canad | -0.281 |
Veh | -0.262 |
oward | -0.259 |
�� | -0.246 |
Crate | -0.246 |
Token | you |
Token ID | 345 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Jinn | +0.358 |
naire | +0.309 |
neys | +0.289 |
Nether | +0.274 |
pton | +0.273 |
Neg logit contributions | |
Canad | -0.298 |
Veh | -0.276 |
oward | -0.274 |
�� | -0.259 |
Crate | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Jinn | +0.073 |
naire | +0.063 |
neys | +0.059 |
Nether | +0.055 |
pton | +0.055 |
Neg logit contributions | |
Canad | -0.063 |
Veh | -0.059 |
oward | -0.058 |
�� | -0.055 |
Crate | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
Jinn | +0.137 |
naire | +0.117 |
neys | +0.110 |
Nether | +0.104 |
pton | +0.103 |
Neg logit contributions | |
Canad | -0.119 |
Veh | -0.111 |
oward | -0.110 |
�� | -0.104 |
Crate | -0.104 |
Token | Cohn |
Token ID | 45005 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
Jinn | +0.318 |
naire | +0.274 |
neys | +0.256 |
Nether | +0.243 |
pton | +0.242 |
Neg logit contributions | |
Canad | -0.266 |
Veh | -0.247 |
oward | -0.245 |
�� | -0.231 |
Crate | -0.231 |
Token | prot |
Token ID | 1237 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Jinn | +0.066 |
naire | +0.057 |
neys | +0.053 |
Nether | +0.050 |
pton | +0.050 |
Neg logit contributions | |
Canad | -0.054 |
Veh | -0.050 |
oward | -0.050 |
�� | -0.047 |
Crate | -0.047 |
Token | é |
Token ID | 2634 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Jinn | +0.380 |
naire | +0.291 |
neys | +0.258 |
Nether | +0.232 |
pton | +0.229 |
Neg logit contributions | |
Canad | -0.765 |
Veh | -0.725 |
oward | -0.724 |
Crate | -0.694 |
�� | -0.694 |
Token | g |
Token ID | 70 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Jinn | +0.312 |
naire | +0.277 |
neys | +0.263 |
Nether | +0.252 |
pton | +0.251 |
Neg logit contributions | |
Canad | -0.156 |
Veh | -0.140 |
oward | -0.139 |
�� | -0.128 |
Crate | -0.128 |
Token | é |
Token ID | 2634 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Jinn | +1.369 |
naire | +1.031 |
neys | +0.953 |
Nether | +0.866 |
pton | +0.836 |
Neg logit contributions | |
Canad | -2.503 |
oward | -2.374 |
Veh | -2.320 |
Crate | -2.246 |
Lavrov | -2.245 |
Token | , |
Token ID | 11 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
Jinn | +0.011 |
naire | +0.010 |
neys | +0.009 |
Nether | +0.009 |
pton | +0.009 |
Neg logit contributions | |
Canad | -0.009 |
Veh | -0.008 |
oward | -0.008 |
�� | -0.008 |
Crate | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Canad | +0.058 |
Veh | +0.054 |
oward | +0.053 |
�� | +0.051 |
Crate | +0.050 |
Neg logit contributions | |
Jinn | -0.068 |
naire | -0.058 |
neys | -0.054 |
Nether | -0.052 |
pton | -0.051 |
Token | running |
Token ID | 2491 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Jinn | +0.143 |
naire | +0.124 |
neys | +0.116 |
Nether | +0.110 |
pton | +0.110 |
Neg logit contributions | |
Canad | -0.112 |
Veh | -0.103 |
oward | -0.102 |
�� | -0.097 |
Crate | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Canad | +0.218 |
Veh | +0.203 |
oward | +0.201 |
�� | +0.192 |
Crate | +0.191 |
Neg logit contributions | |
Jinn | -0.229 |
naire | -0.195 |
neys | -0.182 |
Nether | -0.172 |
pton | -0.171 |
Token | Fore |
Token ID | 4558 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Jinn | +1.779 |
naire | +1.513 |
neys | +1.414 |
pton | +1.318 |
Nether | +1.311 |
Neg logit contributions | |
Canad | -1.740 |
Veh | -1.610 |
oward | -1.584 |
Crate | -1.542 |
Lavrov | -1.511 |
Token | word |
Token ID | 4775 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Jinn | +0.585 |
naire | +0.513 |
neys | +0.484 |
Nether | +0.463 |
pton | +0.460 |
Neg logit contributions | |
Canad | -0.364 |
Veh | -0.332 |
oward | -0.330 |
�� | -0.307 |
Crate | -0.306 |
Token | by |
Token ID | 416 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Jinn | +1.344 |
naire | +1.103 |
neys | +1.033 |
Nether | +0.955 |
pton | +0.946 |
Neg logit contributions | |
Canad | -1.715 |
Veh | -1.596 |
oward | -1.595 |
Crate | -1.528 |
Lavrov | -1.508 |
Token | Patrick |
Token ID | 9925 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Canad | +1.880 |
Veh | +1.782 |
oward | +1.778 |
�� | +1.739 |
Lavrov | +1.717 |
Neg logit contributions | |
Jinn | -0.864 |
naire | -0.618 |
neys | -0.548 |
Nether | -0.499 |
pton | -0.498 |
Token | J |
Token ID | 449 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
Jinn | +1.431 |
naire | +1.240 |
neys | +1.130 |
pton | +1.066 |
Nether | +1.051 |
Neg logit contributions | |
Canad | -1.446 |
Veh | -1.354 |
oward | -1.334 |
Crate | -1.266 |
�� | -1.250 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Jinn | +0.500 |
naire | +0.432 |
neys | +0.404 |
Nether | +0.383 |
pton | +0.382 |
Neg logit contributions | |
Canad | -0.415 |
Veh | -0.384 |
oward | -0.381 |
Crate | -0.359 |
�� | -0.358 |
Token | Buchanan |
Token ID | 36358 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Jinn | +2.383 |
naire | +2.141 |
neys | +1.979 |
pton | +1.887 |
Nether | +1.865 |
Neg logit contributions | |
Canad | -1.479 |
Veh | -1.343 |
oward | -1.316 |
Crate | -1.241 |
Lavrov | -1.215 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Jinn | +1.277 |
naire | +1.107 |
neys | +1.037 |
Nether | +0.992 |
pton | +0.987 |
Neg logit contributions | |
Canad | -0.971 |
Veh | -0.891 |
oward | -0.879 |
Crate | -0.834 |
Lavrov | -0.827 |
Token | and |
Token ID | 290 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
Jinn | +1.090 |
naire | +0.947 |
neys | +0.881 |
Nether | +0.834 |
pton | +0.829 |
Neg logit contributions | |
Canad | -0.919 |
Veh | -0.854 |
oward | -0.839 |
Crate | -0.800 |
�� | -0.796 |
Token | critical |
Token ID | 4688 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Jinn | +0.834 |
naire | +0.711 |
neys | +0.654 |
Nether | +0.616 |
pton | +0.616 |
Neg logit contributions | |
Canad | -0.849 |
Veh | -0.792 |
oward | -0.783 |
Crate | -0.747 |
�� | -0.745 |
Token | essays |
Token ID | 27126 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Canad | +0.018 |
Veh | +0.017 |
oward | +0.017 |
�� | +0.016 |
Crate | +0.016 |
Neg logit contributions | |
Jinn | -0.020 |
naire | -0.017 |
neys | -0.016 |
Nether | -0.015 |
pton | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
Jinn | +0.907 |
naire | +0.780 |
neys | +0.730 |
Nether | +0.690 |
pton | +0.688 |
Neg logit contributions | |
Canad | -0.782 |
Veh | -0.723 |
oward | -0.718 |
Crate | -0.678 |
�� | -0.677 |
Token | music |
Token ID | 2647 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Jinn | +0.153 |
naire | +0.132 |
neys | +0.123 |
Nether | +0.117 |
pton | +0.116 |
Neg logit contributions | |
Canad | -0.131 |
Veh | -0.121 |
oward | -0.120 |
�� | -0.114 |
Crate | -0.114 |
Token | critic |
Token ID | 4014 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
Jinn | +0.345 |
naire | +0.297 |
neys | +0.278 |
Nether | +0.264 |
pton | +0.263 |
Neg logit contributions | |
Canad | -0.291 |
Veh | -0.270 |
oward | -0.267 |
�� | -0.253 |
Crate | -0.253 |
Token | Adam |
Token ID | 7244 |
Feature activation | -4.67e-02 |
Pos logit contributions | |
Jinn | +0.037 |
naire | +0.031 |
neys | +0.029 |
Nether | +0.028 |
pton | +0.028 |
Neg logit contributions | |
Canad | -0.033 |
Veh | -0.030 |
oward | -0.030 |
�� | -0.029 |
Crate | -0.028 |
Token | Ward |
Token ID | 12150 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
Jinn | +0.044 |
naire | +0.038 |
neys | +0.036 |
Nether | +0.034 |
pton | +0.034 |
Neg logit contributions | |
Canad | -0.036 |
Veh | -0.033 |
oward | -0.033 |
�� | -0.031 |
Crate | -0.031 |
Token | reminis |
Token ID | 21484 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Jinn | +0.592 |
naire | +0.504 |
neys | +0.471 |
Nether | +0.445 |
pton | +0.443 |
Neg logit contributions | |
Canad | -0.552 |
Veh | -0.512 |
oward | -0.509 |
Crate | -0.482 |
�� | -0.482 |
Token | ces |
Token ID | 728 |
Feature activation | -1.72e-03 |
Pos logit contributions | |
Jinn | +1.465 |
naire | +1.153 |
neys | +1.018 |
Nether | +0.955 |
pton | +0.942 |
Neg logit contributions | |
Canad | -2.373 |
oward | -2.239 |
Veh | -2.233 |
Crate | -2.130 |
Lavrov | -2.127 |
Token | about |
Token ID | 546 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
Jinn | +0.001 |
naire | +0.001 |
neys | +0.001 |
Nether | +0.001 |
pton | +0.001 |
Neg logit contributions | |
Canad | -0.002 |
Veh | -0.001 |
oward | -0.001 |
�� | -0.001 |
Crate | -0.001 |
Token | digital |
Token ID | 4875 |
Feature activation | +9.34e-02 |
Pos logit contributions | |
Canad | +0.027 |
Veh | +0.025 |
oward | +0.025 |
�� | +0.024 |
Crate | +0.024 |
Neg logit contributions | |
Jinn | -0.028 |
naire | -0.024 |
neys | -0.022 |
Nether | -0.021 |
pton | -0.021 |
Token | music |
Token ID | 2647 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Canad | +0.073 |
Veh | +0.068 |
oward | +0.067 |
�� | +0.063 |
Crate | +0.063 |
Neg logit contributions | |
Jinn | -0.088 |
naire | -0.076 |
neys | -0.071 |
Nether | -0.067 |
pton | -0.067 |
Token | files |
Token ID | 3696 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
Jinn | +0.147 |
naire | +0.127 |
neys | +0.119 |
Nether | +0.112 |
pton | +0.112 |
Neg logit contributions | |
Canad | -0.122 |
Veh | -0.113 |
oward | -0.112 |
�� | -0.106 |
Crate | -0.106 |
Token | Conservative |
Token ID | 11132 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Jinn | +0.568 |
naire | +0.503 |
neys | +0.476 |
pton | +0.456 |
Nether | +0.455 |
Neg logit contributions | |
Canad | -0.311 |
Veh | -0.281 |
oward | -0.276 |
Crate | -0.257 |
�� | -0.256 |
Token | Movement |
Token ID | 15477 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Jinn | +2.392 |
naire | +2.135 |
neys | +2.020 |
pton | +1.944 |
Nether | +1.911 |
Neg logit contributions | |
Canad | -1.320 |
Veh | -1.184 |
oward | -1.157 |
Crate | -1.091 |
� | -1.071 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Jinn | +1.463 |
naire | +1.253 |
neys | +1.185 |
Nether | +1.130 |
pton | +1.127 |
Neg logit contributions | |
Canad | -1.081 |
Veh | -0.989 |
oward | -0.976 |
Crate | -0.919 |
Lavrov | -0.914 |
Token | with |
Token ID | 351 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Jinn | +0.616 |
naire | +0.528 |
neys | +0.490 |
Nether | +0.464 |
pton | +0.464 |
Neg logit contributions | |
Canad | -0.555 |
Veh | -0.516 |
oward | -0.511 |
�� | -0.484 |
Crate | -0.483 |
Token | an |
Token ID | 281 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Jinn | +0.146 |
naire | +0.124 |
neys | +0.116 |
Nether | +0.109 |
pton | +0.109 |
Neg logit contributions | |
Canad | -0.141 |
Veh | -0.131 |
oward | -0.130 |
�� | -0.124 |
Crate | -0.123 |
Token | Introduction |
Token ID | 22395 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Jinn | +0.459 |
naire | +0.405 |
neys | +0.383 |
Nether | +0.366 |
pton | +0.366 |
Neg logit contributions | |
Canad | -0.263 |
Veh | -0.238 |
oward | -0.236 |
�� | -0.220 |
Crate | -0.219 |
Token | by |
Token ID | 416 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Jinn | +1.704 |
naire | +1.393 |
neys | +1.319 |
Nether | +1.210 |
pton | +1.197 |
Neg logit contributions | |
Canad | -2.110 |
oward | -1.968 |
Veh | -1.961 |
Crate | -1.876 |
� | -1.866 |
Token | Prof |
Token ID | 4415 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
Canad | +0.121 |
Veh | +0.109 |
oward | +0.108 |
�� | +0.100 |
Crate | +0.099 |
Neg logit contributions | |
Jinn | -0.226 |
naire | -0.199 |
neys | -0.190 |
Nether | -0.181 |
pton | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Jinn | +0.896 |
naire | +0.778 |
neys | +0.727 |
Nether | +0.689 |
pton | +0.688 |
Neg logit contributions | |
Canad | -0.725 |
Veh | -0.676 |
oward | -0.668 |
Crate | -0.627 |
�� | -0.625 |
Token | George |
Token ID | 4502 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
Jinn | +1.182 |
naire | +1.017 |
neys | +0.940 |
pton | +0.894 |
Nether | +0.887 |
Neg logit contributions | |
Canad | -1.102 |
Veh | -1.040 |
oward | -1.018 |
Crate | -0.975 |
Lavrov | -0.966 |
Token | W |
Token ID | 370 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
Jinn | +0.540 |
naire | +0.469 |
neys | +0.439 |
pton | +0.417 |
Nether | +0.416 |
Neg logit contributions | |
Canad | -0.414 |
Veh | -0.383 |
oward | -0.378 |
Crate | -0.356 |
�� | -0.356 |
Token | The |
Token ID | 383 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Jinn | +1.235 |
naire | +1.107 |
neys | +1.044 |
pton | +1.003 |
Nether | +0.999 |
Neg logit contributions | |
Canad | -0.590 |
Veh | -0.533 |
oward | -0.520 |
Crate | -0.476 |
Lavrov | -0.476 |
Token | Lost |
Token ID | 9164 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
Jinn | +0.572 |
naire | +0.495 |
neys | +0.460 |
Nether | +0.436 |
pton | +0.436 |
Neg logit contributions | |
Canad | -0.489 |
Veh | -0.454 |
oward | -0.448 |
Crate | -0.424 |
�� | -0.424 |
Token | Legacy |
Token ID | 14843 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Canad | +0.287 |
Veh | +0.270 |
oward | +0.269 |
�� | +0.259 |
Crate | +0.258 |
Neg logit contributions | |
Jinn | -0.206 |
naire | -0.168 |
neys | -0.154 |
Nether | -0.143 |
pton | -0.141 |
Token | of |
Token ID | 286 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Jinn | +0.244 |
naire | +0.208 |
neys | +0.194 |
Nether | +0.183 |
pton | +0.183 |
Neg logit contributions | |
Canad | -0.231 |
Veh | -0.215 |
oward | -0.214 |
�� | -0.203 |
Crate | -0.202 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Jinn | +0.379 |
naire | +0.324 |
neys | +0.302 |
Nether | +0.285 |
pton | +0.285 |
Neg logit contributions | |
Canad | -0.360 |
Veh | -0.335 |
oward | -0.333 |
�� | -0.315 |
Crate | -0.315 |
Token | Conservative |
Token ID | 11132 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Jinn | +0.568 |
naire | +0.503 |
neys | +0.476 |
pton | +0.456 |
Nether | +0.455 |
Neg logit contributions | |
Canad | -0.311 |
Veh | -0.281 |
oward | -0.276 |
Crate | -0.257 |
�� | -0.256 |
Token | Movement |
Token ID | 15477 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Jinn | +2.392 |
naire | +2.135 |
neys | +2.020 |
pton | +1.944 |
Nether | +1.911 |
Neg logit contributions | |
Canad | -1.320 |
Veh | -1.184 |
oward | -1.157 |
Crate | -1.091 |
� | -1.071 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
Jinn | +1.463 |
naire | +1.253 |
neys | +1.185 |
Nether | +1.130 |
pton | +1.127 |
Neg logit contributions | |
Canad | -1.081 |
Veh | -0.989 |
oward | -0.976 |
Crate | -0.919 |
Lavrov | -0.914 |
Token | with |
Token ID | 351 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Jinn | +0.616 |
naire | +0.528 |
neys | +0.490 |
Nether | +0.464 |
pton | +0.464 |
Neg logit contributions | |
Canad | -0.555 |
Veh | -0.516 |
oward | -0.511 |
�� | -0.484 |
Crate | -0.483 |
Token | an |
Token ID | 281 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Jinn | +0.146 |
naire | +0.124 |
neys | +0.116 |
Nether | +0.109 |
pton | +0.109 |
Neg logit contributions | |
Canad | -0.141 |
Veh | -0.131 |
oward | -0.130 |
�� | -0.124 |
Crate | -0.123 |
Token | Introduction |
Token ID | 22395 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Jinn | +0.459 |
naire | +0.405 |
neys | +0.383 |
Nether | +0.366 |
pton | +0.366 |
Neg logit contributions | |
Canad | -0.263 |
Veh | -0.238 |
oward | -0.236 |
�� | -0.220 |
Crate | -0.219 |
Token | terror |
Token ID | 3246 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
Canad | +0.159 |
Veh | +0.146 |
oward | +0.145 |
�� | +0.137 |
Crate | +0.136 |
Neg logit contributions | |
Jinn | -0.212 |
naire | -0.184 |
neys | -0.173 |
Nether | -0.165 |
pton | -0.164 |
Token | suspect |
Token ID | 4099 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Jinn | +0.003 |
naire | +0.002 |
neys | +0.002 |
Nether | +0.002 |
pton | +0.002 |
Neg logit contributions | |
Canad | -0.002 |
Veh | -0.002 |
oward | -0.002 |
�� | -0.002 |
Crate | -0.002 |
Token | Say |
Token ID | 13816 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
Jinn | +1.119 |
naire | +0.959 |
neys | +0.895 |
pton | +0.845 |
Nether | +0.843 |
Neg logit contributions | |
Canad | -0.997 |
Veh | -0.929 |
oward | -0.920 |
Crate | -0.871 |
Lavrov | -0.867 |
Token | full |
Token ID | 12853 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Jinn | +0.888 |
naire | +0.727 |
neys | +0.665 |
Nether | +0.613 |
pton | +0.609 |
Neg logit contributions | |
Canad | -1.240 |
Veh | -1.159 |
oward | -1.154 |
Crate | -1.109 |
Lavrov | -1.104 |
Token | o |
Token ID | 78 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
Canad | +0.864 |
Veh | +0.797 |
oward | +0.794 |
�� | +0.764 |
Lavrov | +0.746 |
Neg logit contributions | |
Jinn | -0.959 |
naire | -0.822 |
neys | -0.768 |
Nether | -0.724 |
pton | -0.717 |
Token | Sa |
Token ID | 10318 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Jinn | +0.916 |
naire | +0.800 |
neys | +0.757 |
Nether | +0.716 |
pton | +0.713 |
Neg logit contributions | |
Canad | -0.642 |
Veh | -0.593 |
oward | -0.581 |
Crate | -0.548 |
Lavrov | -0.545 |
Token | ip |
Token ID | 541 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Jinn | +2.258 |
naire | +1.982 |
neys | +1.866 |
Nether | +1.777 |
pton | +1.758 |
Neg logit contributions | |
Canad | -1.464 |
oward | -1.340 |
Veh | -1.326 |
Crate | -1.226 |
Lavrov | -1.226 |
Token | ov |
Token ID | 709 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Canad | +0.499 |
Veh | +0.426 |
oward | +0.420 |
�� | +0.392 |
Crate | +0.375 |
Neg logit contributions | |
Jinn | -1.643 |
naire | -1.483 |
neys | -1.414 |
Nether | -1.358 |
pton | -1.357 |
Token | may |
Token ID | 743 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
Canad | +0.431 |
Veh | +0.400 |
oward | +0.397 |
�� | +0.377 |
Crate | +0.374 |
Neg logit contributions | |
Jinn | -0.515 |
naire | -0.443 |
neys | -0.415 |
Nether | -0.393 |
pton | -0.393 |
Token | have |
Token ID | 423 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
Canad | +0.051 |
Veh | +0.047 |
oward | +0.047 |
�� | +0.044 |
Crate | +0.044 |
Neg logit contributions | |
Jinn | -0.062 |
naire | -0.054 |
neys | -0.050 |
Nether | -0.048 |
pton | -0.047 |
Token | sponsored |
Token ID | 15901 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
Canad | +0.070 |
Veh | +0.064 |
oward | +0.064 |
�� | +0.060 |
Crate | +0.060 |
Neg logit contributions | |
Jinn | -0.090 |
naire | -0.078 |
neys | -0.073 |
Nether | -0.069 |
pton | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Jinn | +0.002 |
naire | +0.001 |
neys | +0.001 |
Nether | +0.001 |
pton | +0.001 |
Neg logit contributions | |
Canad | -0.001 |
Veh | -0.001 |
oward | -0.001 |
�� | -0.001 |
Crate | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
Jinn | +0.275 |
naire | +0.238 |
neys | +0.224 |
Nether | +0.213 |
pton | +0.212 |
Neg logit contributions | |
Canad | -0.210 |
Veh | -0.194 |
oward | -0.192 |
�� | -0.181 |
Crate | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Jinn | +0.023 |
naire | +0.020 |
neys | +0.018 |
Nether | +0.017 |
pton | +0.017 |
Neg logit contributions | |
Canad | -0.021 |
Veh | -0.019 |
oward | -0.019 |
�� | -0.018 |
Crate | -0.018 |
Token | Now |
Token ID | 3844 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
Jinn | +0.197 |
naire | +0.168 |
neys | +0.157 |
Nether | +0.148 |
pton | +0.147 |
Neg logit contributions | |
Canad | -0.184 |
Veh | -0.171 |
oward | -0.169 |
�� | -0.161 |
Crate | -0.161 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Jinn | +0.006 |
naire | +0.005 |
neys | +0.005 |
Nether | +0.005 |
pton | +0.005 |
Neg logit contributions | |
Canad | -0.005 |
Veh | -0.005 |
oward | -0.005 |
�� | -0.004 |
Crate | -0.004 |
Token | : |
Token ID | 25 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Jinn | +0.110 |
naire | +0.094 |
neys | +0.087 |
Nether | +0.082 |
pton | +0.082 |
Neg logit contributions | |
Canad | -0.107 |
Veh | -0.100 |
oward | -0.099 |
�� | -0.094 |
Crate | -0.094 |
Token | Watch |
Token ID | 6305 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Canad | +1.581 |
Veh | +1.455 |
oward | +1.448 |
�� | +1.423 |
Lavrov | +1.311 |
Neg logit contributions | |
Jinn | -2.805 |
naire | -2.436 |
neys | -2.317 |
Nether | -2.233 |
pton | -2.214 |
Token | this |
Token ID | 428 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
Canad | +0.143 |
Veh | +0.132 |
oward | +0.132 |
�� | +0.125 |
Crate | +0.124 |
Neg logit contributions | |
Jinn | -0.158 |
naire | -0.135 |
neys | -0.127 |
Nether | -0.120 |
pton | -0.120 |
Token | : |
Token ID | 25 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
Canad | +0.734 |
Veh | +0.681 |
oward | +0.680 |
�� | +0.652 |
Crate | +0.642 |
Neg logit contributions | |
Jinn | -0.720 |
naire | -0.608 |
neys | -0.566 |
Nether | -0.537 |
pton | -0.534 |
Token | Top |
Token ID | 5849 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Jinn | +0.058 |
naire | +0.051 |
neys | +0.048 |
Nether | +0.045 |
pton | +0.045 |
Neg logit contributions | |
Canad | -0.045 |
Veh | -0.041 |
oward | -0.041 |
�� | -0.039 |
Crate | -0.039 |
Token | 5 |
Token ID | 642 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
Canad | +0.140 |
Veh | +0.129 |
oward | +0.129 |
�� | +0.122 |
Crate | +0.121 |
Neg logit contributions | |
Jinn | -0.179 |
naire | -0.155 |
neys | -0.145 |
Nether | -0.138 |
pton | -0.137 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
Canad | +1.091 |
Veh | +1.013 |
oward | +1.009 |
�� | +0.971 |
Crate | +0.945 |
Neg logit contributions | |
Jinn | -1.255 |
naire | -1.089 |
neys | -1.012 |
Nether | -0.958 |
pton | -0.949 |
Token | : |
Token ID | 25 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
Canad | +0.741 |
Veh | +0.696 |
oward | +0.691 |
�� | +0.662 |
Crate | +0.653 |
Neg logit contributions | |
Jinn | -0.732 |
naire | -0.624 |
neys | -0.582 |
Nether | -0.545 |
pton | -0.541 |
Token | ' |
Token ID | 705 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Jinn | +0.563 |
naire | +0.494 |
neys | +0.466 |
Nether | +0.443 |
pton | +0.442 |
Neg logit contributions | |
Canad | -0.375 |
Veh | -0.344 |
oward | -0.339 |
�� | -0.317 |
Crate | -0.317 |
Token | Damn |
Token ID | 43343 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
Canad | +0.132 |
Veh | +0.121 |
oward | +0.120 |
�� | +0.115 |
Crate | +0.113 |
Neg logit contributions | |
Jinn | -0.165 |
naire | -0.143 |
neys | -0.134 |
Nether | -0.127 |
pton | -0.127 |
Token | right |
Token ID | 826 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Jinn | +0.460 |
naire | +0.398 |
neys | +0.374 |
Nether | +0.355 |
pton | +0.354 |
Neg logit contributions | |
Canad | -0.362 |
Veh | -0.334 |
oward | -0.331 |
Crate | -0.312 |
�� | -0.311 |
Token | ' |
Token ID | 6 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Canad | +0.540 |
Veh | +0.503 |
oward | +0.498 |
�� | +0.477 |
Crate | +0.471 |
Neg logit contributions | |
Jinn | -0.633 |
naire | -0.542 |
neys | -0.506 |
Nether | -0.481 |
pton | -0.478 |
Token | I |
Token ID | 314 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Canad | +1.520 |
oward | +1.412 |
Veh | +1.399 |
�� | +1.350 |
Crate | +1.293 |
Neg logit contributions | |
Jinn | -2.264 |
naire | -1.950 |
neys | -1.831 |
Nether | -1.790 |
pton | -1.776 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
Canad | +1.037 |
Veh | +0.972 |
oward | +0.957 |
�� | +0.921 |
Crate | +0.914 |
Neg logit contributions | |
Jinn | -1.224 |
naire | -1.042 |
neys | -0.986 |
pton | -0.935 |
Nether | -0.927 |
Token | make |
Token ID | 787 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
Canad | +1.398 |
Veh | +1.300 |
oward | +1.290 |
�� | +1.259 |
Crate | +1.213 |
Neg logit contributions | |
Jinn | -1.534 |
naire | -1.330 |
neys | -1.255 |
pton | -1.190 |
Nether | -1.165 |
Token | the |
Token ID | 262 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Jinn | +0.216 |
naire | +0.185 |
neys | +0.172 |
Nether | +0.163 |
pton | +0.163 |
Neg logit contributions | |
Canad | -0.197 |
Veh | -0.183 |
oward | -0.181 |
�� | -0.172 |
Crate | -0.172 |
Token | large |
Token ID | 1588 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Canad | +0.690 |
oward | +0.641 |
Veh | +0.641 |
�� | +0.607 |
Crate | +0.605 |
Neg logit contributions | |
Jinn | -0.795 |
naire | -0.681 |
neys | -0.643 |
Nether | -0.609 |
pton | -0.602 |
Token | migrants |
Token ID | 12783 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Canad | +1.727 |
oward | +1.607 |
Veh | +1.596 |
�� | +1.519 |
Crate | +1.482 |
Neg logit contributions | |
Jinn | -2.478 |
naire | -2.083 |
neys | -1.976 |
Nether | -1.921 |
pton | -1.919 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Canad | +1.534 |
Veh | +1.454 |
oward | +1.436 |
�� | +1.413 |
� | +1.339 |
Neg logit contributions | |
Jinn | -1.886 |
naire | -1.610 |
neys | -1.525 |
Nether | -1.446 |
pton | -1.414 |
Token | ways |
Token ID | 2842 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
Canad | +0.847 |
Veh | +0.791 |
oward | +0.788 |
�� | +0.755 |
Crate | +0.735 |
Neg logit contributions | |
Jinn | -1.035 |
naire | -0.885 |
neys | -0.827 |
pton | -0.797 |
Nether | -0.793 |
Token | Hillary |
Token ID | 5073 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Canad | +0.466 |
Veh | +0.436 |
oward | +0.433 |
�� | +0.415 |
Crate | +0.408 |
Neg logit contributions | |
Jinn | -0.479 |
naire | -0.409 |
neys | -0.382 |
Nether | -0.359 |
pton | -0.359 |
Token | looms |
Token ID | 46234 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Canad | +1.314 |
oward | +1.211 |
Veh | +1.207 |
�� | +1.155 |
Crate | +1.104 |
Neg logit contributions | |
Jinn | -1.962 |
naire | -1.737 |
neys | -1.641 |
Nether | -1.566 |
pton | -1.556 |
Token | over |
Token ID | 625 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Canad | +1.448 |
Veh | +1.341 |
oward | +1.329 |
�� | +1.259 |
Crate | +1.234 |
Neg logit contributions | |
Jinn | -2.096 |
naire | -1.788 |
neys | -1.701 |
Nether | -1.645 |
pton | -1.623 |
Token | the |
Token ID | 262 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Canad | +2.123 |
oward | +2.025 |
Veh | +2.015 |
lov | +1.912 |
�� | +1.902 |
Neg logit contributions | |
Jinn | -2.248 |
naire | -1.907 |
neys | -1.811 |
pton | -1.751 |
Nether | -1.736 |
Token | 2020 |
Token ID | 12131 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Canad | +2.002 |
Veh | +1.904 |
oward | +1.880 |
�� | +1.800 |
lov | +1.781 |
Neg logit contributions | |
Jinn | -1.978 |
naire | -1.643 |
neys | -1.538 |
Nether | -1.504 |
pton | -1.484 |
Token | race |
Token ID | 3234 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Canad | +1.161 |
Veh | +1.067 |
oward | +1.057 |
�� | +1.008 |
Crate | +0.981 |
Neg logit contributions | |
Jinn | -1.580 |
naire | -1.360 |
neys | -1.284 |
pton | -1.237 |
Nether | -1.235 |
Token | Obama |
Token ID | 2486 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Canad | +0.718 |
oward | +0.663 |
Veh | +0.660 |
�� | +0.630 |
Crate | +0.607 |
Neg logit contributions | |
Jinn | -1.041 |
naire | -0.906 |
neys | -0.858 |
Nether | -0.818 |
pton | -0.804 |
Token | goes |
Token ID | 2925 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Canad | +1.014 |
Veh | +0.937 |
oward | +0.927 |
�� | +0.884 |
Crate | +0.871 |
Neg logit contributions | |
Jinn | -1.464 |
naire | -1.270 |
neys | -1.213 |
Nether | -1.145 |
pton | -1.141 |
Token | Sanders |
Token ID | 5831 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Canad | +1.217 |
Veh | +1.138 |
oward | +1.131 |
�� | +1.094 |
Crate | +1.063 |
Neg logit contributions | |
Jinn | -1.243 |
naire | -1.070 |
neys | -0.988 |
Nether | -0.932 |
pton | -0.923 |
Token | : |
Token ID | 25 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Canad | +0.621 |
Veh | +0.582 |
oward | +0.578 |
�� | +0.553 |
Crate | +0.547 |
Neg logit contributions | |
Jinn | -0.617 |
naire | -0.525 |
neys | -0.489 |
Nether | -0.460 |
pton | -0.456 |
Token | ' |
Token ID | 705 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Jinn | +0.621 |
naire | +0.546 |
neys | +0.515 |
Nether | +0.490 |
pton | +0.490 |
Neg logit contributions | |
Canad | -0.403 |
Veh | -0.369 |
oward | -0.364 |
�� | -0.340 |
Crate | -0.340 |
Token | Damn |
Token ID | 43343 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
Canad | +0.201 |
Veh | +0.185 |
oward | +0.183 |
�� | +0.175 |
Crate | +0.172 |
Neg logit contributions | |
Jinn | -0.255 |
naire | -0.220 |
neys | -0.208 |
Nether | -0.197 |
pton | -0.196 |
Token | right |
Token ID | 826 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
Jinn | +0.364 |
naire | +0.315 |
neys | +0.296 |
Nether | +0.281 |
pton | +0.281 |
Neg logit contributions | |
Canad | -0.285 |
Veh | -0.263 |
oward | -0.261 |
Crate | -0.246 |
�� | -0.245 |
Token | ' |
Token ID | 6 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Canad | +0.496 |
Veh | +0.462 |
oward | +0.458 |
�� | +0.439 |
Crate | +0.434 |
Neg logit contributions | |
Jinn | -0.550 |
naire | -0.470 |
neys | -0.438 |
Nether | -0.415 |
pton | -0.413 |
Token | I |
Token ID | 314 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Canad | +1.687 |
oward | +1.569 |
Veh | +1.551 |
�� | +1.505 |
Crate | +1.435 |
Neg logit contributions | |
Jinn | -2.494 |
naire | -2.151 |
neys | -2.011 |
Nether | -1.975 |
pton | -1.956 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Canad | +1.071 |
Veh | +1.003 |
oward | +0.988 |
�� | +0.953 |
Crate | +0.943 |
Neg logit contributions | |
Jinn | -1.249 |
naire | -1.065 |
neys | -1.006 |
pton | -0.953 |
Nether | -0.947 |
Token | make |
Token ID | 787 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Canad | +1.381 |
Veh | +1.283 |
oward | +1.275 |
�� | +1.243 |
Crate | +1.196 |
Neg logit contributions | |
Jinn | -1.518 |
naire | -1.317 |
neys | -1.240 |
pton | -1.175 |
Nether | -1.153 |
Token | the |
Token ID | 262 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Jinn | +0.195 |
naire | +0.168 |
neys | +0.157 |
Nether | +0.148 |
pton | +0.148 |
Neg logit contributions | |
Canad | -0.171 |
Veh | -0.158 |
oward | -0.157 |
�� | -0.149 |
Crate | -0.148 |
Token | large |
Token ID | 1588 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Canad | +0.761 |
oward | +0.709 |
Veh | +0.708 |
�� | +0.672 |
Crate | +0.671 |
Neg logit contributions | |
Jinn | -0.817 |
naire | -0.696 |
neys | -0.656 |
Nether | -0.619 |
pton | -0.612 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Canad | +0.460 |
Veh | +0.421 |
oward | +0.420 |
�� | +0.396 |
Crate | +0.389 |
Neg logit contributions | |
Jinn | -0.666 |
naire | -0.580 |
neys | -0.549 |
Nether | -0.525 |
pton | -0.524 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Canad | +1.149 |
oward | +1.076 |
Veh | +1.063 |
�� | +1.023 |
Lavrov | +1.011 |
Neg logit contributions | |
Jinn | -1.156 |
naire | -0.979 |
neys | -0.921 |
Nether | -0.875 |
pton | -0.859 |
Token | new |
Token ID | 649 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Canad | +0.742 |
oward | +0.682 |
Veh | +0.679 |
�� | +0.644 |
Lavrov | +0.634 |
Neg logit contributions | |
Jinn | -1.012 |
naire | -0.880 |
neys | -0.830 |
Nether | -0.797 |
pton | -0.792 |
Token | features |
Token ID | 3033 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Canad | +0.843 |
oward | +0.768 |
Veh | +0.759 |
�� | +0.720 |
� | +0.697 |
Neg logit contributions | |
Jinn | -1.451 |
naire | -1.279 |
neys | -1.221 |
Nether | -1.172 |
pton | -1.153 |
Token | ( |
Token ID | 357 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
Canad | +1.063 |
Veh | +0.988 |
oward | +0.986 |
�� | +0.943 |
Crate | +0.925 |
Neg logit contributions | |
Jinn | -1.194 |
naire | -1.020 |
neys | -0.955 |
Nether | -0.909 |
pton | -0.905 |
Token | including |
Token ID | 8201 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Canad | +0.049 |
Veh | +0.045 |
oward | +0.045 |
�� | +0.043 |
Crate | +0.043 |
Neg logit contributions | |
Jinn | -0.051 |
naire | -0.044 |
neys | -0.041 |
Nether | -0.038 |
pton | -0.038 |
Token | off |
Token ID | 572 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Canad | +1.488 |
Veh | +1.353 |
oward | +1.329 |
�� | +1.268 |
Lavrov | +1.212 |
Neg logit contributions | |
Jinn | -2.911 |
naire | -2.567 |
neys | -2.470 |
Nether | -2.423 |
pton | -2.396 |
Token | - |
Token ID | 12 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Canad | +0.190 |
Veh | +0.177 |
oward | +0.176 |
�� | +0.167 |
Crate | +0.166 |
Neg logit contributions | |
Jinn | -0.215 |
naire | -0.184 |
neys | -0.173 |
Nether | -0.163 |
pton | -0.162 |
Token | TV |
Token ID | 6849 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Canad | +0.436 |
Veh | +0.412 |
oward | +0.409 |
�� | +0.392 |
Lavrov | +0.389 |
Neg logit contributions | |
Jinn | -0.334 |
naire | -0.277 |
neys | -0.256 |
pton | -0.238 |
Nether | -0.236 |
Token | play |
Token ID | 711 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
Canad | +0.829 |
oward | +0.767 |
Veh | +0.760 |
�� | +0.727 |
Crate | +0.705 |
Neg logit contributions | |
Jinn | -1.228 |
naire | -1.069 |
neys | -1.028 |
Nether | -0.977 |
pton | -0.971 |
Token | ) |
Token ID | 8 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
Jinn | +0.084 |
naire | +0.071 |
neys | +0.066 |
Nether | +0.062 |
pton | +0.062 |
Neg logit contributions | |
Canad | -0.082 |
Veh | -0.077 |
oward | -0.076 |
�� | -0.073 |
Crate | -0.072 |
Token | mode |
Token ID | 4235 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Jinn | +0.241 |
naire | +0.210 |
neys | +0.198 |
Nether | +0.189 |
pton | +0.188 |
Neg logit contributions | |
Canad | -0.167 |
Veh | -0.153 |
oward | -0.152 |
�� | -0.143 |
Crate | -0.142 |
Token | with |
Token ID | 351 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
Jinn | +0.166 |
naire | +0.142 |
neys | +0.133 |
Nether | +0.126 |
pton | +0.126 |
Neg logit contributions | |
Canad | -0.142 |
Veh | -0.131 |
oward | -0.130 |
�� | -0.123 |
Crate | -0.123 |
Token | all |
Token ID | 477 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Canad | +0.047 |
Veh | +0.044 |
oward | +0.044 |
�� | +0.041 |
Crate | +0.041 |
Neg logit contributions | |
Jinn | -0.053 |
naire | -0.045 |
neys | -0.042 |
Nether | -0.040 |
pton | -0.040 |
Token | systems |
Token ID | 3341 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Canad | +0.119 |
Veh | +0.110 |
oward | +0.110 |
�� | +0.104 |
Crate | +0.103 |
Neg logit contributions | |
Jinn | -0.142 |
naire | -0.122 |
neys | -0.114 |
Nether | -0.108 |
pton | -0.108 |
Token | functioning |
Token ID | 15025 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
Canad | +0.175 |
Veh | +0.161 |
oward | +0.160 |
�� | +0.151 |
Crate | +0.151 |
Neg logit contributions | |
Jinn | -0.226 |
naire | -0.196 |
neys | -0.184 |
Nether | -0.175 |
pton | -0.174 |
Token | normally |
Token ID | 7685 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
Canad | +0.404 |
Veh | +0.374 |
oward | +0.371 |
�� | +0.351 |
Crate | +0.349 |
Neg logit contributions | |
Jinn | -0.530 |
naire | -0.458 |
neys | -0.429 |
Nether | -0.409 |
pton | -0.407 |
Token | . |
Token ID | 13 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
Canad | +0.474 |
Veh | +0.439 |
oward | +0.435 |
�� | +0.415 |
Crate | +0.412 |
Neg logit contributions | |
Jinn | -0.570 |
naire | -0.489 |
neys | -0.458 |
Nether | -0.435 |
pton | -0.433 |
Token | When |
Token ID | 1649 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
Canad | +0.022 |
Veh | +0.020 |
oward | +0.020 |
�� | +0.019 |
Crate | +0.018 |
Neg logit contributions | |
Jinn | -0.035 |
naire | -0.031 |
neys | -0.029 |
Nether | -0.028 |
pton | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
Canad | +0.071 |
Veh | +0.066 |
oward | +0.066 |
�� | +0.063 |
Crate | +0.062 |
Neg logit contributions | |
Jinn | -0.076 |
naire | -0.065 |
neys | -0.061 |
Nether | -0.057 |
pton | -0.057 |
Token | time |
Token ID | 640 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
Canad | +0.039 |
Veh | +0.036 |
oward | +0.036 |
�� | +0.034 |
Crate | +0.034 |
Neg logit contributions | |
Jinn | -0.048 |
naire | -0.042 |
neys | -0.039 |
Nether | -0.037 |
pton | -0.037 |
Token | came |
Token ID | 1625 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
Canad | +0.457 |
Veh | +0.424 |
oward | +0.420 |
�� | +0.400 |
Crate | +0.397 |
Neg logit contributions | |
Jinn | -0.544 |
naire | -0.467 |
neys | -0.436 |
Nether | -0.414 |
pton | -0.414 |
Token | taking |
Token ID | 2263 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
Canad | +0.270 |
Veh | +0.250 |
oward | +0.249 |
�� | +0.236 |
Crate | +0.234 |
Neg logit contributions | |
Jinn | -0.320 |
naire | -0.275 |
neys | -0.258 |
Nether | -0.244 |
pton | -0.243 |
Token | a |
Token ID | 257 |
Feature activation | -6.63e-02 |
Pos logit contributions | |
Canad | +0.524 |
Veh | +0.486 |
oward | +0.482 |
�� | +0.459 |
Crate | +0.455 |
Neg logit contributions | |
Jinn | -0.615 |
naire | -0.526 |
neys | -0.493 |
Nether | -0.469 |
pton | -0.464 |
Token | tougher |
Token ID | 20516 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Jinn | +0.064 |
naire | +0.055 |
neys | +0.052 |
Nether | +0.049 |
pton | +0.049 |
Neg logit contributions | |
Canad | -0.051 |
Veh | -0.047 |
oward | -0.046 |
�� | -0.044 |
Crate | -0.044 |
Token | stance |
Token ID | 12046 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Canad | +0.321 |
Veh | +0.298 |
oward | +0.296 |
�� | +0.282 |
Crate | +0.280 |
Neg logit contributions | |
Jinn | -0.373 |
naire | -0.321 |
neys | -0.300 |
Nether | -0.284 |
pton | -0.283 |
Token | against |
Token ID | 1028 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Canad | +0.221 |
Veh | +0.205 |
oward | +0.203 |
�� | +0.192 |
Crate | +0.191 |
Neg logit contributions | |
Jinn | -0.282 |
naire | -0.244 |
neys | -0.229 |
Nether | -0.218 |
pton | -0.217 |
Token | nudity |
Token ID | 42156 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
Canad | +0.229 |
Veh | +0.212 |
oward | +0.210 |
�� | +0.200 |
Crate | +0.198 |
Neg logit contributions | |
Jinn | -0.272 |
naire | -0.234 |
neys | -0.219 |
Nether | -0.208 |
pton | -0.207 |
Token | to |
Token ID | 284 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Canad | +0.751 |
Veh | +0.697 |
oward | +0.691 |
�� | +0.662 |
Crate | +0.655 |
Neg logit contributions | |
Jinn | -0.851 |
naire | -0.729 |
neys | -0.682 |
Nether | -0.648 |
pton | -0.642 |
Token | prevent |
Token ID | 2948 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Canad | +0.219 |
Veh | +0.201 |
oward | +0.200 |
�� | +0.188 |
Crate | +0.187 |
Neg logit contributions | |
Jinn | -0.319 |
naire | -0.278 |
neys | -0.262 |
Nether | -0.250 |
pton | -0.249 |
Token | their |
Token ID | 511 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Canad | +0.435 |
Veh | +0.400 |
oward | +0.398 |
�� | +0.378 |
Crate | +0.374 |
Neg logit contributions | |
Jinn | -0.576 |
naire | -0.499 |
neys | -0.470 |
Nether | -0.448 |
pton | -0.444 |
Token | services |
Token ID | 2594 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Canad | +0.504 |
Veh | +0.461 |
oward | +0.459 |
�� | +0.434 |
Crate | +0.428 |
Neg logit contributions | |
Jinn | -0.759 |
naire | -0.662 |
neys | -0.626 |
Nether | -0.598 |
pton | -0.594 |
Token | from |
Token ID | 422 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
Canad | +0.537 |
Veh | +0.498 |
oward | +0.494 |
�� | +0.470 |
Crate | +0.464 |
Neg logit contributions | |
Jinn | -0.668 |
naire | -0.575 |
neys | -0.541 |
Nether | -0.513 |
pton | -0.511 |
Token | FOR |
Token ID | 7473 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
Canad | +0.358 |
Veh | +0.330 |
oward | +0.328 |
�� | +0.310 |
Crate | +0.308 |
Neg logit contributions | |
Jinn | -0.451 |
naire | -0.389 |
neys | -0.365 |
Nether | -0.347 |
pton | -0.346 |
Token | T |
Token ID | 51 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Canad | +0.321 |
Veh | +0.298 |
oward | +0.296 |
�� | +0.282 |
Crate | +0.281 |
Neg logit contributions | |
Jinn | -0.339 |
naire | -0.289 |
neys | -0.269 |
Nether | -0.254 |
pton | -0.253 |
Token | . |
Token ID | 13 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
Canad | +0.315 |
Veh | +0.292 |
oward | +0.289 |
�� | +0.275 |
Crate | +0.273 |
Neg logit contributions | |
Jinn | -0.377 |
naire | -0.324 |
neys | -0.304 |
Nether | -0.288 |
pton | -0.287 |
Token | P |
Token ID | 350 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
Canad | +0.596 |
Veh | +0.545 |
oward | +0.545 |
�� | +0.516 |
Crate | +0.505 |
Neg logit contributions | |
Jinn | -0.904 |
naire | -0.788 |
neys | -0.744 |
Nether | -0.712 |
pton | -0.706 |
Token | hew |
Token ID | 6391 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Canad | +0.014 |
Veh | +0.013 |
oward | +0.013 |
�� | +0.013 |
Crate | +0.013 |
Neg logit contributions | |
Jinn | -0.017 |
naire | -0.015 |
neys | -0.014 |
Nether | -0.013 |
pton | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
Canad | +0.449 |
Veh | +0.416 |
oward | +0.414 |
�� | +0.393 |
Crate | +0.390 |
Neg logit contributions | |
Jinn | -0.540 |
naire | -0.465 |
neys | -0.437 |
Nether | -0.413 |
pton | -0.412 |
Token | I |
Token ID | 314 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
Canad | +0.382 |
Veh | +0.353 |
oward | +0.352 |
�� | +0.333 |
Crate | +0.330 |
Neg logit contributions | |
Jinn | -0.485 |
naire | -0.418 |
neys | -0.393 |
Nether | -0.373 |
pton | -0.371 |
Token | � |
Token ID | 447 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
Canad | +0.057 |
Veh | +0.053 |
oward | +0.052 |
�� | +0.049 |
Crate | +0.049 |
Neg logit contributions | |
Jinn | -0.070 |
naire | -0.060 |
neys | -0.056 |
Nether | -0.053 |
pton | -0.053 |
Token | � |
Token ID | 247 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Canad | +0.032 |
Veh | +0.028 |
oward | +0.028 |
�� | +0.026 |
Crate | +0.026 |
Neg logit contributions | |
Jinn | -0.077 |
naire | -0.068 |
neys | -0.065 |
Nether | -0.063 |
pton | -0.063 |
Token | ve |
Token ID | 303 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Canad | +0.099 |
Veh | +0.091 |
oward | +0.090 |
�� | +0.084 |
Crate | +0.084 |
Neg logit contributions | |
Jinn | -0.154 |
naire | -0.135 |
neys | -0.127 |
Nether | -0.121 |
pton | -0.121 |
Token | begun |
Token ID | 9258 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Canad | +0.260 |
Veh | +0.240 |
oward | +0.239 |
�� | +0.226 |
Crate | +0.224 |
Neg logit contributions | |
Jinn | -0.326 |
naire | -0.281 |
neys | -0.264 |
Nether | -0.250 |
pton | -0.250 |
Token | night |
Token ID | 1755 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Jinn | +1.059 |
naire | +0.892 |
neys | +0.831 |
pton | +0.775 |
Nether | +0.775 |
Neg logit contributions | |
Canad | -1.129 |
Veh | -1.056 |
oward | -1.047 |
Crate | -0.994 |
�� | -0.990 |
Token |
|
Token ID | 198 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
Canad | +0.329 |
Veh | +0.303 |
oward | +0.301 |
�� | +0.286 |
Crate | +0.284 |
Neg logit contributions | |
Jinn | -0.419 |
naire | -0.363 |
neys | -0.340 |
Nether | -0.324 |
pton | -0.323 |
Token |
|
Token ID | 198 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Jinn | +0.078 |
naire | +0.067 |
neys | +0.063 |
Nether | +0.059 |
pton | +0.059 |
Neg logit contributions | |
Canad | -0.070 |
Veh | -0.065 |
oward | -0.065 |
�� | -0.062 |
Crate | -0.061 |
Token | Most |
Token ID | 6943 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
Jinn | +0.194 |
naire | +0.164 |
neys | +0.152 |
Nether | +0.143 |
pton | +0.143 |
Neg logit contributions | |
Canad | -0.202 |
Veh | -0.188 |
oward | -0.187 |
�� | -0.178 |
Crate | -0.178 |
Token | capable |
Token ID | 6007 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Canad | +0.135 |
Veh | +0.124 |
oward | +0.124 |
�� | +0.117 |
Crate | +0.116 |
Neg logit contributions | |
Jinn | -0.177 |
naire | -0.153 |
neys | -0.144 |
Nether | -0.137 |
pton | -0.136 |
Token | : |
Token ID | 25 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
Canad | +0.757 |
Veh | +0.703 |
oward | +0.702 |
�� | +0.673 |
Crate | +0.663 |
Neg logit contributions | |
Jinn | -0.784 |
naire | -0.668 |
neys | -0.622 |
Nether | -0.587 |
pton | -0.586 |
Token | Red |
Token ID | 2297 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Canad | +0.509 |
oward | +0.467 |
Veh | +0.467 |
�� | +0.442 |
Crate | +0.435 |
Neg logit contributions | |
Jinn | -0.707 |
naire | -0.613 |
neys | -0.578 |
Nether | -0.552 |
pton | -0.549 |
Token | es |
Token ID | 274 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Canad | +0.390 |
Veh | +0.365 |
oward | +0.362 |
�� | +0.347 |
Crate | +0.345 |
Neg logit contributions | |
Jinn | -0.358 |
naire | -0.301 |
neys | -0.280 |
Nether | -0.263 |
pton | -0.262 |
Token | igned |
Token ID | 3916 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
Jinn | +0.776 |
naire | +0.613 |
neys | +0.547 |
Nether | +0.497 |
pton | +0.495 |
Neg logit contributions | |
Canad | -1.367 |
Veh | -1.296 |
oward | -1.289 |
Crate | -1.236 |
�� | -1.233 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Canad | +0.054 |
Veh | +0.050 |
oward | +0.049 |
�� | +0.047 |
Crate | +0.046 |
Neg logit contributions | |
Jinn | -0.071 |
naire | -0.062 |
neys | -0.058 |
Nether | -0.055 |
pton | -0.055 |
Token | larger |
Token ID | 4025 |
Feature activation | +9.93e-02 |
Pos logit contributions | |
Canad | +0.225 |
Veh | +0.208 |
oward | +0.207 |
�� | +0.195 |
Crate | +0.194 |
Neg logit contributions | |
Jinn | -0.287 |
naire | -0.248 |
neys | -0.233 |
Nether | -0.222 |
pton | -0.221 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
Canad | +0.361 |
Veh | +0.334 |
oward | +0.332 |
�� | +0.316 |
Crate | +0.314 |
Neg logit contributions | |
Jinn | -0.422 |
naire | -0.361 |
neys | -0.338 |
Nether | -0.321 |
pton | -0.319 |
Token | armed |
Token ID | 6936 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Jinn | +0.054 |
naire | +0.047 |
neys | +0.044 |
Nether | +0.042 |
pton | +0.042 |
Neg logit contributions | |
Canad | -0.040 |
Veh | -0.037 |
oward | -0.036 |
�� | -0.034 |
Crate | -0.034 |
Token | forces |
Token ID | 3386 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
Jinn | +0.337 |
naire | +0.297 |
neys | +0.281 |
Nether | +0.269 |
pton | +0.268 |
Neg logit contributions | |
Canad | -0.200 |
Veh | -0.182 |
oward | -0.180 |
�� | -0.168 |
Crate | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Jinn | +0.056 |
naire | +0.048 |
neys | +0.044 |
Nether | +0.042 |
pton | +0.042 |
Neg logit contributions | |
Canad | -0.052 |
Veh | -0.048 |
oward | -0.048 |
�� | -0.045 |
Crate | -0.045 |
Token | stay |
Token ID | 2652 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
Jinn | +0.249 |
naire | +0.217 |
neys | +0.205 |
Nether | +0.195 |
pton | +0.194 |
Neg logit contributions | |
Canad | -0.173 |
Veh | -0.159 |
oward | -0.158 |
�� | -0.148 |
Crate | -0.148 |
Token | in |
Token ID | 287 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
Jinn | +0.004 |
naire | +0.003 |
neys | +0.003 |
Nether | +0.003 |
pton | +0.003 |
Neg logit contributions | |
Canad | -0.003 |
Veh | -0.003 |
oward | -0.003 |
�� | -0.002 |
Crate | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Canad | +0.657 |
Veh | +0.610 |
oward | +0.607 |
�� | +0.579 |
Crate | +0.573 |
Neg logit contributions | |
Jinn | -0.730 |
naire | -0.622 |
neys | -0.579 |
Nether | -0.551 |
pton | -0.548 |
Token | barracks |
Token ID | 37658 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Jinn | +0.026 |
naire | +0.023 |
neys | +0.021 |
Nether | +0.020 |
pton | +0.020 |
Neg logit contributions | |
Canad | -0.020 |
Veh | -0.018 |
oward | -0.018 |
�� | -0.017 |
Crate | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
Jinn | +0.148 |
naire | +0.128 |
neys | +0.120 |
Nether | +0.113 |
pton | +0.113 |
Neg logit contributions | |
Canad | -0.122 |
Veh | -0.113 |
oward | -0.112 |
�� | -0.106 |
Crate | -0.106 |
Token | while |
Token ID | 981 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Canad | +0.120 |
Veh | +0.111 |
oward | +0.110 |
�� | +0.104 |
Crate | +0.103 |
Neg logit contributions | |
Jinn | -0.162 |
naire | -0.140 |
neys | -0.132 |
Nether | -0.126 |
pton | -0.125 |
Token | Ay |
Token ID | 13709 |
Feature activation | +6.80e-02 |
Pos logit contributions | |
Canad | +0.196 |
Veh | +0.182 |
oward | +0.181 |
�� | +0.172 |
Crate | +0.171 |
Neg logit contributions | |
Jinn | -0.215 |
naire | -0.183 |
neys | -0.171 |
Nether | -0.162 |
pton | -0.161 |
Token | Library |
Token ID | 23377 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
Jinn | +0.271 |
naire | +0.232 |
neys | +0.217 |
Nether | +0.205 |
pton | +0.205 |
Neg logit contributions | |
Canad | -0.243 |
Veh | -0.226 |
oward | -0.224 |
�� | -0.212 |
Crate | -0.212 |
Token | services |
Token ID | 2594 |
Feature activation | +7.91e-04 |
Pos logit contributions | |
Canad | +0.251 |
Veh | +0.231 |
oward | +0.230 |
�� | +0.217 |
Crate | +0.215 |
Neg logit contributions | |
Jinn | -0.339 |
naire | -0.294 |
neys | -0.277 |
Nether | -0.263 |
pton | -0.262 |
Token | platforms |
Token ID | 9554 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
Canad | +0.001 |
Veh | +0.001 |
oward | +0.001 |
�� | +0.001 |
Crate | +0.001 |
Neg logit contributions | |
Jinn | -0.001 |
naire | -0.001 |
neys | -0.001 |
Nether | -0.001 |
pton | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
Jinn | +0.072 |
naire | +0.062 |
neys | +0.058 |
Nether | +0.055 |
pton | +0.055 |
Neg logit contributions | |
Canad | -0.059 |
Veh | -0.054 |
oward | -0.054 |
�� | -0.051 |
Crate | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Jinn | +0.118 |
naire | +0.101 |
neys | +0.095 |
Nether | +0.090 |
pton | +0.089 |
Neg logit contributions | |
Canad | -0.106 |
Veh | -0.098 |
oward | -0.097 |
�� | -0.093 |
Crate | -0.092 |
Token | Recent |
Token ID | 26446 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
Jinn | +0.097 |
naire | +0.083 |
neys | +0.078 |
Nether | +0.074 |
pton | +0.074 |
Neg logit contributions | |
Canad | -0.086 |
Veh | -0.080 |
oward | -0.079 |
�� | -0.075 |
Crate | -0.075 |
Token | years |
Token ID | 812 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
Canad | +0.086 |
Veh | +0.079 |
oward | +0.078 |
�� | +0.074 |
Crate | +0.073 |
Neg logit contributions | |
Jinn | -0.124 |
naire | -0.108 |
neys | -0.102 |
Nether | -0.097 |
pton | -0.097 |
Token | have |
Token ID | 423 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Jinn | +0.166 |
naire | +0.142 |
neys | +0.133 |
Nether | +0.125 |
pton | +0.125 |
Neg logit contributions | |
Canad | -0.147 |
Veh | -0.137 |
oward | -0.136 |
�� | -0.129 |
Crate | -0.128 |
Token | seen |
Token ID | 1775 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
Canad | +0.139 |
Veh | +0.129 |
oward | +0.128 |
�� | +0.121 |
Crate | +0.120 |
Neg logit contributions | |
Jinn | -0.180 |
naire | -0.155 |
neys | -0.146 |
Nether | -0.139 |
pton | -0.138 |
Token | the |
Token ID | 262 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Canad | +0.275 |
Veh | +0.255 |
oward | +0.253 |
�� | +0.240 |
Crate | +0.238 |
Neg logit contributions | |
Jinn | -0.333 |
naire | -0.286 |
neys | -0.269 |
Nether | -0.255 |
pton | -0.254 |
Token | emergence |
Token ID | 22106 |
Feature activation | +7.30e-02 |
Pos logit contributions | |
Canad | +0.224 |
Veh | +0.206 |
oward | +0.204 |
�� | +0.193 |
Crate | +0.192 |
Neg logit contributions | |
Jinn | -0.318 |
naire | -0.277 |
neys | -0.261 |
Nether | -0.249 |
pton | -0.247 |
Token | powers |
Token ID | 5635 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
Canad | +0.049 |
Veh | +0.045 |
oward | +0.045 |
�� | +0.042 |
Crate | +0.042 |
Neg logit contributions | |
Jinn | -0.067 |
naire | -0.058 |
neys | -0.055 |
Nether | -0.052 |
pton | -0.052 |
Token | has |
Token ID | 468 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
Jinn | +0.032 |
naire | +0.028 |
neys | +0.026 |
Nether | +0.025 |
pton | +0.024 |
Neg logit contributions | |
Canad | -0.028 |
Veh | -0.026 |
oward | -0.026 |
�� | -0.024 |
Crate | -0.024 |
Token | been |
Token ID | 587 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Canad | +0.345 |
Veh | +0.320 |
oward | +0.317 |
�� | +0.301 |
Crate | +0.299 |
Neg logit contributions | |
Jinn | -0.431 |
naire | -0.371 |
neys | -0.348 |
Nether | -0.331 |
pton | -0.330 |
Token | a |
Token ID | 257 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Canad | +0.249 |
Veh | +0.231 |
oward | +0.229 |
�� | +0.218 |
Crate | +0.216 |
Neg logit contributions | |
Jinn | -0.292 |
naire | -0.250 |
neys | -0.235 |
Nether | -0.223 |
pton | -0.221 |
Token | topic |
Token ID | 7243 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
Canad | +0.183 |
Veh | +0.169 |
oward | +0.167 |
�� | +0.159 |
Crate | +0.158 |
Neg logit contributions | |
Jinn | -0.242 |
naire | -0.209 |
neys | -0.197 |
Nether | -0.188 |
pton | -0.187 |
Token | since |
Token ID | 1201 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
Canad | +0.755 |
Veh | +0.705 |
oward | +0.698 |
�� | +0.667 |
Crate | +0.664 |
Neg logit contributions | |
Jinn | -0.778 |
naire | -0.660 |
neys | -0.615 |
Nether | -0.581 |
pton | -0.577 |
Token | Ronald |
Token ID | 14430 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Canad | +0.046 |
Veh | +0.043 |
oward | +0.043 |
�� | +0.041 |
Crate | +0.040 |
Neg logit contributions | |
Jinn | -0.051 |
naire | -0.043 |
neys | -0.041 |
Nether | -0.038 |
pton | -0.038 |
Token | Reagan |
Token ID | 12823 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Canad | +0.300 |
Veh | +0.278 |
oward | +0.276 |
�� | +0.262 |
Crate | +0.260 |
Neg logit contributions | |
Jinn | -0.375 |
naire | -0.323 |
neys | -0.304 |
Nether | -0.289 |
pton | -0.288 |
Token | � |
Token ID | 447 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Canad | +0.496 |
Veh | +0.461 |
oward | +0.458 |
�� | +0.436 |
Crate | +0.433 |
Neg logit contributions | |
Jinn | -0.592 |
naire | -0.507 |
neys | -0.476 |
Nether | -0.450 |
pton | -0.450 |
Token | � |
Token ID | 247 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Canad | +0.113 |
Veh | +0.101 |
oward | +0.100 |
�� | +0.092 |
Crate | +0.092 |
Neg logit contributions | |
Jinn | -0.234 |
naire | -0.208 |
neys | -0.197 |
Nether | -0.189 |
pton | -0.189 |
Token | s |
Token ID | 82 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Canad | +0.317 |
Veh | +0.293 |
oward | +0.291 |
�� | +0.276 |
Crate | +0.275 |
Neg logit contributions | |
Jinn | -0.381 |
naire | -0.328 |
neys | -0.308 |
Nether | -0.292 |
pton | -0.291 |
Token | ($ |
Token ID | 7198 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Canad | +0.477 |
Veh | +0.442 |
oward | +0.437 |
�� | +0.416 |
Crate | +0.413 |
Neg logit contributions | |
Jinn | -0.575 |
naire | -0.495 |
neys | -0.464 |
Nether | -0.440 |
pton | -0.439 |
Token | Al |
Token ID | 2348 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
Jinn | +0.259 |
naire | +0.225 |
neys | +0.212 |
Nether | +0.202 |
pton | +0.201 |
Neg logit contributions | |
Canad | -0.187 |
Veh | -0.172 |
oward | -0.171 |
�� | -0.161 |
Crate | -0.160 |
Token | ign |
Token ID | 570 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
Jinn | +0.310 |
naire | +0.249 |
neys | +0.226 |
Nether | +0.208 |
pton | +0.206 |
Neg logit contributions | |
Canad | -0.491 |
Veh | -0.464 |
oward | -0.461 |
�� | -0.443 |
Crate | -0.442 |
Token | ) |
Token ID | 8 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
Jinn | +0.689 |
naire | +0.559 |
neys | +0.510 |
Nether | +0.472 |
pton | +0.468 |
Neg logit contributions | |
Canad | -0.998 |
Veh | -0.940 |
oward | -0.935 |
Crate | -0.897 |
�� | -0.894 |
Token | { |
Token ID | 1391 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Canad | +0.463 |
Veh | +0.425 |
oward | +0.421 |
�� | +0.399 |
Crate | +0.396 |
Neg logit contributions | |
Jinn | -0.636 |
naire | -0.553 |
neys | -0.520 |
Nether | -0.496 |
pton | -0.494 |
Token | Center |
Token ID | 3337 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Canad | +0.419 |
Veh | +0.387 |
oward | +0.384 |
�� | +0.364 |
Crate | +0.361 |
Neg logit contributions | |
Jinn | -0.536 |
naire | -0.463 |
neys | -0.435 |
Nether | -0.415 |
pton | -0.413 |
Token | { |
Token ID | 1391 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Canad | +0.053 |
Veh | +0.050 |
oward | +0.049 |
�� | +0.047 |
Crate | +0.046 |
Neg logit contributions | |
Jinn | -0.063 |
naire | -0.054 |
neys | -0.050 |
Nether | -0.048 |
pton | -0.048 |
Token | $ |
Token ID | 720 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
Canad | +0.170 |
Veh | +0.158 |
oward | +0.156 |
�� | +0.148 |
Crate | +0.148 |
Neg logit contributions | |
Jinn | -0.206 |
naire | -0.178 |
neys | -0.166 |
Nether | -0.158 |
pton | -0.158 |
Token | s |
Token ID | 82 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Canad | +0.134 |
Veh | +0.124 |
oward | +0.123 |
�� | +0.117 |
Crate | +0.116 |
Neg logit contributions | |
Jinn | -0.153 |
naire | -0.131 |
neys | -0.123 |
Nether | -0.116 |
pton | -0.116 |
Token | Format |
Token ID | 26227 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Jinn | +0.298 |
naire | +0.250 |
neys | +0.231 |
Nether | +0.217 |
pton | +0.216 |
Neg logit contributions | |
Canad | -0.333 |
Veh | -0.312 |
oward | -0.310 |
�� | -0.295 |
Crate | -0.295 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Canad | +0.181 |
Veh | +0.168 |
oward | +0.166 |
�� | +0.158 |
Crate | +0.157 |
Neg logit contributions | |
Jinn | -0.218 |
naire | -0.188 |
neys | -0.176 |
Nether | -0.167 |
pton | -0.167 |
Token | over |
Token ID | 2502 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
Canad | +0.246 |
Veh | +0.228 |
oward | +0.226 |
�� | +0.215 |
Crate | +0.213 |
Neg logit contributions | |
Jinn | -0.291 |
naire | -0.250 |
neys | -0.234 |
Nether | -0.222 |
pton | -0.221 |
Token | run |
Token ID | 5143 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
Canad | +0.503 |
Veh | +0.465 |
oward | +0.463 |
�� | +0.439 |
Crate | +0.435 |
Neg logit contributions | |
Jinn | -0.609 |
naire | -0.526 |
neys | -0.493 |
Nether | -0.468 |
pton | -0.467 |
Token | Cell |
Token ID | 12440 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Canad | +0.128 |
Veh | +0.118 |
oward | +0.118 |
�� | +0.111 |
Crate | +0.110 |
Neg logit contributions | |
Jinn | -0.167 |
naire | -0.145 |
neys | -0.136 |
Nether | -0.129 |
pton | -0.129 |
Token | Block |
Token ID | 9726 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Canad | +0.256 |
Veh | +0.236 |
oward | +0.235 |
�� | +0.223 |
Crate | +0.221 |
Neg logit contributions | |
Jinn | -0.310 |
naire | -0.267 |
neys | -0.251 |
Nether | -0.237 |
pton | -0.237 |
Token | D |
Token ID | 360 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Canad | +0.241 |
Veh | +0.223 |
oward | +0.221 |
�� | +0.210 |
Crate | +0.208 |
Neg logit contributions | |
Jinn | -0.295 |
naire | -0.255 |
neys | -0.239 |
Nether | -0.227 |
pton | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Jinn | +0.427 |
naire | +0.368 |
neys | +0.345 |
Nether | +0.327 |
pton | +0.326 |
Neg logit contributions | |
Canad | -0.357 |
Veh | -0.331 |
oward | -0.329 |
�� | -0.311 |
Crate | -0.310 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
Canad | +0.276 |
Veh | +0.256 |
oward | +0.255 |
�� | +0.242 |
Crate | +0.240 |
Neg logit contributions | |
Jinn | -0.311 |
naire | -0.266 |
neys | -0.249 |
Nether | -0.236 |
pton | -0.235 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
Canad | +0.080 |
Veh | +0.074 |
oward | +0.074 |
�� | +0.069 |
Crate | +0.069 |
Neg logit contributions | |
Jinn | -0.105 |
naire | -0.091 |
neys | -0.085 |
Nether | -0.081 |
pton | -0.081 |
Token | past |
Token ID | 1613 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Jinn | +0.096 |
naire | +0.083 |
neys | +0.077 |
Nether | +0.073 |
pton | +0.073 |
Neg logit contributions | |
Canad | -0.083 |
Veh | -0.077 |
oward | -0.076 |
�� | -0.073 |
Crate | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
Canad | +0.407 |
Veh | +0.378 |
oward | +0.376 |
�� | +0.358 |
Crate | +0.356 |
Neg logit contributions | |
Jinn | -0.439 |
naire | -0.374 |
neys | -0.349 |
Nether | -0.331 |
pton | -0.329 |
Token | two |
Token ID | 734 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
Canad | +0.356 |
Veh | +0.329 |
oward | +0.328 |
�� | +0.311 |
Crate | +0.308 |
Neg logit contributions | |
Jinn | -0.438 |
naire | -0.377 |
neys | -0.354 |
Nether | -0.337 |
pton | -0.334 |
Token | Michael |
Token ID | 3899 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Canad | +0.045 |
Veh | +0.042 |
oward | +0.041 |
�� | +0.039 |
Crate | +0.039 |
Neg logit contributions | |
Jinn | -0.050 |
naire | -0.043 |
neys | -0.040 |
Nether | -0.038 |
pton | -0.038 |
Token | Ign |
Token ID | 16583 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Canad | +0.160 |
Veh | +0.147 |
oward | +0.146 |
�� | +0.138 |
Crate | +0.137 |
Neg logit contributions | |
Jinn | -0.213 |
naire | -0.184 |
neys | -0.173 |
Nether | -0.165 |
pton | -0.165 |
Token | at |
Token ID | 265 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
Canad | +0.681 |
Veh | +0.642 |
oward | +0.631 |
�� | +0.618 |
Crate | +0.606 |
Neg logit contributions | |
Jinn | -0.562 |
naire | -0.472 |
neys | -0.433 |
pton | -0.407 |
Nether | -0.402 |
Token | ie |
Token ID | 494 |
Feature activation | -8.96e-01 |
Pos logit contributions | |
Canad | +0.285 |
Veh | +0.265 |
oward | +0.261 |
�� | +0.252 |
Crate | +0.248 |
Neg logit contributions | |
Jinn | -0.328 |
naire | -0.283 |
neys | -0.264 |
Nether | -0.249 |
pton | -0.249 |
Token | ff |
Token ID | 487 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
Jinn | +0.681 |
naire | +0.564 |
neys | +0.520 |
Nether | +0.486 |
pton | +0.479 |
Neg logit contributions | |
Canad | -0.860 |
Veh | -0.808 |
oward | -0.804 |
Crate | -0.766 |
Lavrov | -0.765 |
Token | , |
Token ID | 11 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
Jinn | +0.030 |
naire | +0.025 |
neys | +0.023 |
Nether | +0.022 |
pton | +0.022 |
Neg logit contributions | |
Canad | -0.030 |
Veh | -0.028 |
oward | -0.028 |
�� | -0.027 |
Crate | -0.027 |
Token | all |
Token ID | 477 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
Jinn | +0.049 |
naire | +0.042 |
neys | +0.039 |
Nether | +0.037 |
pton | +0.037 |
Neg logit contributions | |
Canad | -0.043 |
Veh | -0.040 |
oward | -0.040 |
�� | -0.038 |
Crate | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
Canad | +0.152 |
Veh | +0.142 |
oward | +0.141 |
�� | +0.134 |
Crate | +0.133 |
Neg logit contributions | |
Jinn | -0.163 |
naire | -0.139 |
neys | -0.130 |
Nether | -0.123 |
pton | -0.122 |
Token | whom |
Token ID | 4150 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
Jinn | +0.065 |
naire | +0.055 |
neys | +0.052 |
Nether | +0.049 |
pton | +0.049 |
Neg logit contributions | |
Canad | -0.065 |
Veh | -0.060 |
oward | -0.060 |
�� | -0.057 |
Crate | -0.057 |
Token | accuse |
Token ID | 24456 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Canad | +0.071 |
Veh | +0.066 |
oward | +0.065 |
�� | +0.062 |
Crate | +0.062 |
Neg logit contributions | |
Jinn | -0.087 |
naire | -0.075 |
neys | -0.071 |
Nether | -0.067 |
pton | -0.067 |
Token | him |
Token ID | 683 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
Canad | +0.254 |
Veh | +0.237 |
oward | +0.236 |
�� | +0.225 |
Crate | +0.224 |
Neg logit contributions | |
Jinn | -0.253 |
naire | -0.215 |
neys | -0.200 |
Nether | -0.188 |
pton | -0.188 |
Token | s |
Token ID | 82 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Jinn | +0.652 |
naire | +0.574 |
neys | +0.543 |
Nether | +0.519 |
pton | +0.518 |
Neg logit contributions | |
Canad | -0.386 |
Veh | -0.352 |
oward | -0.348 |
Crate | -0.324 |
�� | -0.323 |
Token | two |
Token ID | 734 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Jinn | +0.207 |
naire | +0.178 |
neys | +0.167 |
Nether | +0.158 |
pton | +0.158 |
Neg logit contributions | |
Canad | -0.173 |
Veh | -0.161 |
oward | -0.159 |
�� | -0.151 |
Crate | -0.150 |
Token | prominent |
Token ID | 9208 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Jinn | +0.243 |
naire | +0.209 |
neys | +0.196 |
Nether | +0.186 |
pton | +0.185 |
Neg logit contributions | |
Canad | -0.203 |
Veh | -0.188 |
oward | -0.186 |
�� | -0.177 |
Crate | -0.176 |
Token | Islamic |
Token ID | 5533 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Jinn | +0.336 |
naire | +0.290 |
neys | +0.272 |
Nether | +0.257 |
pton | +0.257 |
Neg logit contributions | |
Canad | -0.276 |
Veh | -0.256 |
oward | -0.253 |
�� | -0.240 |
Crate | -0.239 |
Token | hel |
Token ID | 932 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
Jinn | +0.104 |
naire | +0.090 |
neys | +0.085 |
Nether | +0.081 |
pton | +0.080 |
Neg logit contributions | |
Canad | -0.081 |
Veh | -0.075 |
oward | -0.074 |
�� | -0.070 |
Crate | -0.070 |
Token | pl |
Token ID | 489 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Jinn | +0.831 |
naire | +0.721 |
neys | +0.674 |
Nether | +0.640 |
pton | +0.634 |
Neg logit contributions | |
Canad | -0.673 |
Veh | -0.623 |
oward | -0.617 |
Crate | -0.581 |
�� | -0.580 |
Token | ines |
Token ID | 1127 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Jinn | +1.429 |
naire | +1.252 |
neys | +1.167 |
Nether | +1.118 |
pton | +1.109 |
Neg logit contributions | |
Canad | -1.007 |
Veh | -0.918 |
oward | -0.918 |
Lavrov | -0.857 |
Crate | -0.856 |
Token | are |
Token ID | 389 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
Jinn | +0.243 |
naire | +0.209 |
neys | +0.196 |
Nether | +0.186 |
pton | +0.185 |
Neg logit contributions | |
Canad | -0.203 |
Veh | -0.188 |
oward | -0.186 |
�� | -0.176 |
Crate | -0.176 |
Token | discouraging |
Token ID | 48001 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
Jinn | +0.093 |
naire | +0.080 |
neys | +0.075 |
Nether | +0.071 |
pton | +0.071 |
Neg logit contributions | |
Canad | -0.078 |
Veh | -0.072 |
oward | -0.072 |
�� | -0.068 |
Crate | -0.068 |
Token | young |
Token ID | 1862 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Jinn | +0.352 |
naire | +0.304 |
neys | +0.284 |
Nether | +0.269 |
pton | +0.269 |
Neg logit contributions | |
Canad | -0.295 |
Veh | -0.273 |
oward | -0.270 |
�� | -0.256 |
Crate | -0.255 |
Token | call |
Token ID | 869 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Jinn | +0.383 |
naire | +0.329 |
neys | +0.308 |
Nether | +0.291 |
pton | +0.291 |
Neg logit contributions | |
Canad | -0.332 |
Veh | -0.308 |
oward | -0.305 |
�� | -0.289 |
Crate | -0.289 |
Token | s |
Token ID | 82 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Canad | +0.155 |
Veh | +0.144 |
oward | +0.143 |
�� | +0.135 |
Crate | +0.134 |
Neg logit contributions | |
Jinn | -0.188 |
naire | -0.162 |
neys | -0.152 |
Nether | -0.144 |
pton | -0.143 |
Token | exchanges |
Token ID | 14525 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Jinn | +0.353 |
naire | +0.303 |
neys | +0.283 |
Nether | +0.269 |
pton | +0.268 |
Neg logit contributions | |
Canad | -0.303 |
Veh | -0.281 |
oward | -0.278 |
�� | -0.264 |
Crate | -0.263 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Jinn | +0.096 |
naire | +0.082 |
neys | +0.077 |
Nether | +0.073 |
pton | +0.073 |
Neg logit contributions | |
Canad | -0.082 |
Veh | -0.076 |
oward | -0.075 |
�� | -0.072 |
Crate | -0.071 |
Token | sharply |
Token ID | 18939 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
Canad | +0.071 |
Veh | +0.065 |
oward | +0.065 |
�� | +0.061 |
Crate | +0.060 |
Neg logit contributions | |
Jinn | -0.106 |
naire | -0.093 |
neys | -0.087 |
Nether | -0.083 |
pton | -0.083 |
Token | cut |
Token ID | 2005 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Jinn | +0.141 |
naire | +0.125 |
neys | +0.118 |
Nether | +0.113 |
pton | +0.113 |
Neg logit contributions | |
Canad | -0.075 |
Veh | -0.068 |
oward | -0.067 |
�� | -0.063 |
Crate | -0.062 |
Token | long |
Token ID | 890 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
Jinn | +0.570 |
naire | +0.493 |
neys | +0.464 |
Nether | +0.440 |
pton | +0.439 |
Neg logit contributions | |
Canad | -0.434 |
Veh | -0.400 |
oward | -0.397 |
Crate | -0.373 |
�� | -0.373 |
Token | - |
Token ID | 12 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
Jinn | +1.537 |
naire | +1.315 |
neys | +1.234 |
Nether | +1.171 |
pton | +1.171 |
Neg logit contributions | |
Canad | -1.255 |
Veh | -1.163 |
oward | -1.160 |
Crate | -1.086 |
�� | -1.084 |
Token | term |
Token ID | 4354 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Jinn | +0.853 |
naire | +0.730 |
neys | +0.682 |
Nether | +0.646 |
pton | +0.645 |
Neg logit contributions | |
Canad | -0.746 |
Veh | -0.692 |
oward | -0.689 |
Crate | -0.650 |
�� | -0.649 |
Token | Medicaid |
Token ID | 13594 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Jinn | +0.996 |
naire | +0.859 |
neys | +0.807 |
Nether | +0.763 |
pton | +0.761 |
Neg logit contributions | |
Canad | -0.805 |
Veh | -0.744 |
oward | -0.739 |
Crate | -0.696 |
�� | -0.692 |
Token | spending |
Token ID | 4581 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
Jinn | +0.137 |
naire | +0.119 |
neys | +0.112 |
Nether | +0.106 |
pton | +0.106 |
Neg logit contributions | |
Canad | -0.102 |
Veh | -0.094 |
oward | -0.094 |
�� | -0.088 |
Crate | -0.088 |
Token | while |
Token ID | 981 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
Canad | +0.058 |
Veh | +0.054 |
oward | +0.054 |
�� | +0.051 |
Crate | +0.051 |
Neg logit contributions | |
Jinn | -0.066 |
naire | -0.056 |
neys | -0.052 |
Nether | -0.050 |
pton | -0.050 |
Token | EUR |
Token ID | 27526 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
Canad | +0.005 |
Veh | +0.004 |
oward | +0.004 |
�� | +0.004 |
Crate | +0.004 |
Neg logit contributions | |
Jinn | -0.008 |
naire | -0.007 |
neys | -0.007 |
Nether | -0.006 |
pton | -0.006 |
Token | OP |
Token ID | 3185 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
Jinn | +0.261 |
naire | +0.221 |
neys | +0.205 |
Nether | +0.193 |
pton | +0.192 |
Neg logit contributions | |
Canad | -0.269 |
Veh | -0.251 |
oward | -0.249 |
�� | -0.237 |
Crate | -0.237 |
Token | P |
Token ID | 47 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
Canad | +0.167 |
Veh | +0.154 |
oward | +0.153 |
�� | +0.145 |
Crate | +0.143 |
Neg logit contributions | |
Jinn | -0.213 |
naire | -0.184 |
neys | -0.173 |
Nether | -0.165 |
pton | -0.164 |
Token | – |
Token ID | 784 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Canad | +0.164 |
Veh | +0.151 |
oward | +0.150 |
�� | +0.142 |
Crate | +0.141 |
Neg logit contributions | |
Jinn | -0.206 |
naire | -0.178 |
neys | -0.167 |
Nether | -0.159 |
pton | -0.158 |
Token | European |
Token ID | 3427 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Canad | +0.770 |
Veh | +0.722 |
oward | +0.720 |
�� | +0.685 |
Crate | +0.676 |
Neg logit contributions | |
Jinn | -0.759 |
naire | -0.642 |
neys | -0.593 |
Nether | -0.567 |
pton | -0.560 |
Token | Politics |
Token ID | 17554 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Canad | +0.030 |
Veh | +0.028 |
oward | +0.027 |
�� | +0.026 |
Crate | +0.025 |
Neg logit contributions | |
Jinn | -0.049 |
naire | -0.043 |
neys | -0.040 |
Nether | -0.039 |
pton | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Jinn | +1.276 |
naire | +1.093 |
neys | +1.034 |
Nether | +0.976 |
pton | +0.973 |
Neg logit contributions | |
Canad | -1.049 |
Veh | -0.969 |
oward | -0.963 |
Crate | -0.917 |
Lavrov | -0.907 |
Token | Policy |
Token ID | 7820 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Jinn | +0.333 |
naire | +0.285 |
neys | +0.266 |
Nether | +0.252 |
pton | +0.251 |
Neg logit contributions | |
Canad | -0.300 |
Veh | -0.279 |
oward | -0.276 |
�� | -0.262 |
Crate | -0.262 |
Token | or |
Token ID | 393 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Jinn | +1.332 |
naire | +1.148 |
neys | +1.086 |
Nether | +1.030 |
pton | +1.027 |
Neg logit contributions | |
Canad | -0.992 |
Veh | -0.911 |
oward | -0.906 |
Crate | -0.856 |
Lavrov | -0.853 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Canad | +0.544 |
Veh | +0.507 |
oward | +0.502 |
�� | +0.484 |
Crate | +0.476 |
Neg logit contributions | |
Jinn | -0.566 |
naire | -0.481 |
neys | -0.450 |
Nether | -0.426 |
pton | -0.421 |
Token | London |
Token ID | 3576 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Canad | +1.164 |
Veh | +1.098 |
oward | +1.097 |
�� | +1.054 |
Crate | +1.039 |
Neg logit contributions | |
Jinn | -0.892 |
naire | -0.728 |
neys | -0.671 |
Nether | -0.641 |
pton | -0.618 |
Token | everyone |
Token ID | 2506 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Jinn | +0.123 |
naire | +0.106 |
neys | +0.100 |
Nether | +0.095 |
pton | +0.094 |
Neg logit contributions | |
Canad | -0.100 |
Veh | -0.093 |
oward | -0.092 |
�� | -0.087 |
Crate | -0.087 |
Token | was |
Token ID | 373 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Jinn | +0.262 |
naire | +0.226 |
neys | +0.212 |
Nether | +0.201 |
pton | +0.200 |
Neg logit contributions | |
Canad | -0.218 |
Veh | -0.202 |
oward | -0.200 |
�� | -0.189 |
Crate | -0.189 |
Token | doing |
Token ID | 1804 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Jinn | +0.267 |
naire | +0.229 |
neys | +0.214 |
Nether | +0.203 |
pton | +0.202 |
Neg logit contributions | |
Canad | -0.234 |
Veh | -0.217 |
oward | -0.215 |
�� | -0.204 |
Crate | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
Jinn | +0.336 |
naire | +0.289 |
neys | +0.270 |
Nether | +0.255 |
pton | +0.255 |
Neg logit contributions | |
Canad | -0.291 |
Veh | -0.270 |
oward | -0.268 |
�� | -0.253 |
Crate | -0.253 |
Token | Glenn |
Token ID | 17551 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Jinn | +0.122 |
naire | +0.107 |
neys | +0.102 |
Nether | +0.097 |
pton | +0.097 |
Neg logit contributions | |
Canad | -0.068 |
Veh | -0.062 |
oward | -0.061 |
�� | -0.057 |
Crate | -0.056 |
Token | McGr |
Token ID | 41114 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
Jinn | +0.513 |
naire | +0.440 |
neys | +0.412 |
Nether | +0.388 |
pton | +0.388 |
Neg logit contributions | |
Canad | -0.458 |
Veh | -0.425 |
oward | -0.421 |
Crate | -0.399 |
�� | -0.398 |
Token | ath |
Token ID | 776 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
Jinn | +0.779 |
naire | +0.588 |
neys | +0.503 |
Nether | +0.443 |
pton | +0.437 |
Neg logit contributions | |
Canad | -1.873 |
oward | -1.802 |
Veh | -1.794 |
Crate | -1.723 |
Lavrov | -1.710 |
Token | had |
Token ID | 550 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
Jinn | +0.517 |
naire | +0.446 |
neys | +0.418 |
Nether | +0.396 |
pton | +0.395 |
Neg logit contributions | |
Canad | -0.429 |
Veh | -0.397 |
oward | -0.394 |
Crate | -0.372 |
�� | -0.371 |
Token | a |
Token ID | 257 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
Jinn | +0.517 |
naire | +0.444 |
neys | +0.416 |
Nether | +0.393 |
pton | +0.392 |
Neg logit contributions | |
Canad | -0.456 |
Veh | -0.423 |
oward | -0.419 |
�� | -0.397 |
Crate | -0.396 |
Token | slight |
Token ID | 3731 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Jinn | +0.401 |
naire | +0.348 |
neys | +0.327 |
Nether | +0.310 |
pton | +0.309 |
Neg logit contributions | |
Canad | -0.310 |
Veh | -0.286 |
oward | -0.283 |
�� | -0.267 |
Crate | -0.267 |
Token | bend |
Token ID | 19396 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
Jinn | +0.290 |
naire | +0.253 |
neys | +0.239 |
Nether | +0.228 |
pton | +0.227 |
Neg logit contributions | |
Canad | -0.191 |
Veh | -0.175 |
oward | -0.174 |
�� | -0.163 |
Crate | -0.162 |
Token | he |
Token ID | 339 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
Jinn | +0.220 |
naire | +0.187 |
neys | +0.175 |
Nether | +0.165 |
pton | +0.164 |
Neg logit contributions | |
Canad | -0.213 |
Veh | -0.199 |
oward | -0.197 |
�� | -0.187 |
Crate | -0.187 |
Token | plans |
Token ID | 3352 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
Jinn | +0.108 |
naire | +0.093 |
neys | +0.087 |
Nether | +0.082 |
pton | +0.082 |
Neg logit contributions | |
Canad | -0.092 |
Veh | -0.086 |
oward | -0.085 |
�� | -0.081 |
Crate | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Jinn | +0.137 |
naire | +0.117 |
neys | +0.109 |
Nether | +0.103 |
pton | +0.103 |
Neg logit contributions | |
Canad | -0.127 |
Veh | -0.118 |
oward | -0.117 |
�� | -0.111 |
Crate | -0.111 |
Token | soon |
Token ID | 2582 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Jinn | +0.457 |
naire | +0.399 |
neys | +0.376 |
Nether | +0.359 |
pton | +0.358 |
Neg logit contributions | |
Canad | -0.305 |
Veh | -0.279 |
oward | -0.277 |
�� | -0.259 |
Crate | -0.259 |
Token | make |
Token ID | 787 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Jinn | +0.277 |
naire | +0.243 |
neys | +0.230 |
Nether | +0.219 |
pton | +0.219 |
Neg logit contributions | |
Canad | -0.171 |
Veh | -0.156 |
oward | -0.154 |
�� | -0.144 |
Crate | -0.143 |
Token | an |
Token ID | 281 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Jinn | +0.521 |
naire | +0.443 |
neys | +0.412 |
Nether | +0.387 |
pton | +0.386 |
Neg logit contributions | |
Canad | -0.530 |
Veh | -0.493 |
oward | -0.489 |
�� | -0.465 |
Crate | -0.465 |
Token | application |
Token ID | 3586 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Jinn | +1.241 |
naire | +1.077 |
neys | +1.011 |
Nether | +0.959 |
pton | +0.956 |
Neg logit contributions | |
Canad | -0.983 |
Veh | -0.902 |
oward | -0.894 |
Lavrov | -0.842 |
�� | -0.839 |
Token | before |
Token ID | 878 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
Jinn | +0.225 |
naire | +0.193 |
neys | +0.180 |
Nether | +0.170 |
pton | +0.170 |
Neg logit contributions | |
Canad | -0.202 |
Veh | -0.188 |
oward | -0.186 |
�� | -0.177 |
Crate | -0.176 |
Token | a |
Token ID | 257 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Canad | +0.153 |
Veh | +0.143 |
oward | +0.142 |
�� | +0.135 |
Crate | +0.134 |
Neg logit contributions | |
Jinn | -0.167 |
naire | -0.142 |
neys | -0.133 |
Nether | -0.126 |
pton | -0.125 |
Token | youth |
Token ID | 6205 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Jinn | +0.347 |
naire | +0.300 |
neys | +0.282 |
Nether | +0.268 |
pton | +0.267 |
Neg logit contributions | |
Canad | -0.269 |
Veh | -0.248 |
oward | -0.246 |
�� | -0.232 |
Crate | -0.232 |
Token | court |
Token ID | 2184 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Canad | +0.154 |
Veh | +0.143 |
oward | +0.142 |
�� | +0.135 |
Crate | +0.135 |
Neg logit contributions | |
Jinn | -0.173 |
naire | -0.148 |
neys | -0.138 |
Nether | -0.131 |
pton | -0.130 |