Token | - |
Token ID | 12 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
recept | +0.822 |
acht | +0.803 |
xxxxxxxx | +0.773 |
phabet | +0.762 |
ieth | +0.745 |
Neg logit contributions | |
anamo | -0.968 |
DCS | -0.887 |
Salvador | -0.868 |
abul | -0.864 |
ⓘ | -0.861 |
Token | 40 |
Token ID | 1821 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
anamo | +0.096 |
DCS | +0.087 |
Salvador | +0.085 |
abul | +0.084 |
ⓘ | +0.084 |
Neg logit contributions | |
recept | -0.112 |
acht | -0.111 |
xxxxxxxx | -0.107 |
phabet | -0.106 |
ieth | -0.104 |
Token | ), |
Token ID | 828 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
recept | +0.180 |
acht | +0.176 |
xxxxxxxx | +0.168 |
phabet | +0.166 |
ieth | +0.161 |
Neg logit contributions | |
anamo | -0.254 |
DCS | -0.236 |
Salvador | -0.232 |
abul | -0.230 |
ⓘ | -0.229 |
Token | which |
Token ID | 543 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
recept | +0.305 |
acht | +0.296 |
xxxxxxxx | +0.284 |
phabet | +0.282 |
ieth | +0.275 |
Neg logit contributions | |
anamo | -0.377 |
DCS | -0.348 |
Salvador | -0.339 |
abul | -0.339 |
ⓘ | -0.335 |
Token | is |
Token ID | 318 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
anamo | +0.434 |
DCS | +0.405 |
Salvador | +0.397 |
abul | +0.395 |
ⓘ | +0.393 |
Neg logit contributions | |
recept | -0.279 |
acht | -0.273 |
xxxxxxxx | -0.258 |
phabet | -0.258 |
ieth | -0.249 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
anamo | +0.468 |
DCS | +0.434 |
Salvador | +0.424 |
abul | +0.422 |
ⓘ | +0.419 |
Neg logit contributions | |
recept | -0.384 |
acht | -0.377 |
xxxxxxxx | -0.360 |
phabet | -0.359 |
ieth | -0.349 |
Token | aten |
Token ID | 36686 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
anamo | +5.394 |
DCS | +5.088 |
abul | +5.052 |
sole | +4.952 |
raught | +4.932 |
Neg logit contributions | |
recept | -3.021 |
acht | -2.897 |
phabet | -2.821 |
xxxxxxxx | -2.721 |
ieth | -2.601 |
Token | ated |
Token ID | 515 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
anamo | +0.667 |
DCS | +0.607 |
Salvador | +0.591 |
abul | +0.586 |
ⓘ | +0.582 |
Neg logit contributions | |
recept | -0.806 |
acht | -0.794 |
xxxxxxxx | -0.764 |
phabet | -0.762 |
ieth | -0.745 |
Token | with |
Token ID | 351 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
anamo | +0.317 |
DCS | +0.294 |
Salvador | +0.288 |
abul | +0.287 |
ⓘ | +0.284 |
Neg logit contributions | |
recept | -0.237 |
acht | -0.232 |
xxxxxxxx | -0.221 |
phabet | -0.220 |
ieth | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
anamo | +0.131 |
DCS | +0.121 |
Salvador | +0.118 |
abul | +0.118 |
ⓘ | +0.117 |
Neg logit contributions | |
recept | -0.107 |
acht | -0.104 |
xxxxxxxx | -0.100 |
phabet | -0.099 |
ieth | -0.096 |
Token | 24 |
Token ID | 1987 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
recept | +0.183 |
acht | +0.179 |
xxxxxxxx | +0.173 |
phabet | +0.171 |
ieth | +0.168 |
Neg logit contributions | |
anamo | -0.159 |
DCS | -0.144 |
abul | -0.139 |
Salvador | -0.139 |
ⓘ | -0.137 |
Token | . |
Token ID | 13 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
anamo | +0.729 |
DCS | +0.676 |
Salvador | +0.661 |
abul | +0.658 |
ⓘ | +0.654 |
Neg logit contributions | |
recept | -0.558 |
acht | -0.548 |
xxxxxxxx | -0.520 |
phabet | -0.518 |
ieth | -0.504 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
anamo | +0.307 |
DCS | +0.285 |
Salvador | +0.279 |
abul | +0.276 |
ⓘ | +0.275 |
Neg logit contributions | |
recept | -0.250 |
acht | -0.245 |
xxxxxxxx | -0.233 |
phabet | -0.232 |
ieth | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
recept | +0.120 |
acht | +0.118 |
xxxxxxxx | +0.112 |
phabet | +0.111 |
ieth | +0.108 |
Neg logit contributions | |
anamo | -0.171 |
DCS | -0.159 |
Salvador | -0.156 |
abul | -0.155 |
ⓘ | -0.154 |
Token | H |
Token ID | 39 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
anamo | +0.022 |
DCS | +0.020 |
Salvador | +0.020 |
abul | +0.020 |
ⓘ | +0.020 |
Neg logit contributions | |
recept | -0.019 |
acht | -0.019 |
xxxxxxxx | -0.018 |
phabet | -0.018 |
ieth | -0.017 |
Token | app |
Token ID | 1324 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
anamo | +0.168 |
DCS | +0.155 |
Salvador | +0.152 |
abul | +0.150 |
ⓘ | +0.150 |
Neg logit contributions | |
recept | -0.156 |
acht | -0.154 |
xxxxxxxx | -0.146 |
phabet | -0.146 |
ieth | -0.143 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
anamo | +0.353 |
DCS | +0.333 |
Salvador | +0.327 |
abul | +0.325 |
ⓘ | +0.324 |
Neg logit contributions | |
recept | -0.152 |
acht | -0.148 |
xxxxxxxx | -0.137 |
phabet | -0.137 |
ieth | -0.132 |
Token | urs |
Token ID | 1834 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
anamo | +4.664 |
DCS | +4.400 |
abul | +4.279 |
Salvador | +4.212 |
sole | +4.169 |
Neg logit contributions | |
recept | -3.464 |
acht | -3.375 |
phabet | -3.252 |
xxxxxxxx | -3.184 |
ieth | -3.079 |
Token | : |
Token ID | 25 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
anamo | +1.124 |
DCS | +1.044 |
Salvador | +1.019 |
abul | +1.019 |
ⓘ | +1.008 |
Neg logit contributions | |
recept | -0.809 |
acht | -0.793 |
xxxxxxxx | -0.753 |
phabet | -0.748 |
ieth | -0.729 |
Token | " |
Token ID | 366 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
anamo | +0.983 |
DCS | +0.905 |
Salvador | +0.883 |
abul | +0.880 |
ⓘ | +0.872 |
Neg logit contributions | |
recept | -0.909 |
acht | -0.893 |
xxxxxxxx | -0.853 |
phabet | -0.850 |
ieth | -0.829 |
Token | The |
Token ID | 464 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
anamo | +0.310 |
DCS | +0.282 |
Salvador | +0.279 |
abul | +0.278 |
ⓘ | +0.276 |
Neg logit contributions | |
recept | -0.247 |
acht | -0.244 |
xxxxxxxx | -0.235 |
phabet | -0.229 |
ieth | -0.225 |
Token | semi |
Token ID | 10663 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
recept | +0.418 |
acht | +0.406 |
xxxxxxxx | +0.387 |
phabet | +0.385 |
ieth | +0.376 |
Neg logit contributions | |
anamo | -0.489 |
DCS | -0.450 |
abul | -0.440 |
Salvador | -0.437 |
ⓘ | -0.434 |
Token | bone |
Token ID | 9970 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
anamo | +1.001 |
DCS | +0.931 |
Salvador | +0.920 |
abul | +0.908 |
ⓘ | +0.905 |
Neg logit contributions | |
recept | -0.775 |
acht | -0.768 |
phabet | -0.728 |
xxxxxxxx | -0.727 |
ieth | -0.704 |
Token | region |
Token ID | 3814 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
recept | +0.248 |
acht | +0.243 |
xxxxxxxx | +0.231 |
phabet | +0.230 |
ieth | +0.223 |
Neg logit contributions | |
anamo | -0.344 |
DCS | -0.320 |
Salvador | -0.313 |
abul | -0.311 |
ⓘ | -0.310 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
recept | +0.778 |
acht | +0.759 |
xxxxxxxx | +0.721 |
phabet | +0.710 |
ieth | +0.697 |
Neg logit contributions | |
anamo | -1.141 |
DCS | -1.055 |
abul | -1.029 |
Salvador | -1.029 |
ⓘ | -1.018 |
Token | we |
Token ID | 356 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
recept | +0.149 |
acht | +0.146 |
xxxxxxxx | +0.139 |
phabet | +0.138 |
ieth | +0.134 |
Neg logit contributions | |
anamo | -0.194 |
DCS | -0.179 |
Salvador | -0.175 |
abul | -0.175 |
ⓘ | -0.173 |
Token | obtained |
Token ID | 6492 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
anamo | +0.621 |
DCS | +0.579 |
Salvador | +0.567 |
abul | +0.564 |
ⓘ | +0.560 |
Neg logit contributions | |
recept | -0.402 |
acht | -0.393 |
xxxxxxxx | -0.372 |
phabet | -0.369 |
ieth | -0.359 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
recept | +0.921 |
acht | +0.894 |
xxxxxxxx | +0.855 |
phabet | +0.844 |
ieth | +0.834 |
Neg logit contributions | |
anamo | -1.109 |
DCS | -1.009 |
abul | -0.983 |
Salvador | -0.973 |
ⓘ | -0.963 |
Token | ord |
Token ID | 585 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
anamo | +4.025 |
DCS | +3.787 |
abul | +3.738 |
Salvador | +3.636 |
sole | +3.614 |
Neg logit contributions | |
recept | -3.771 |
acht | -3.709 |
phabet | -3.536 |
xxxxxxxx | -3.504 |
ieth | -3.385 |
Token | ant |
Token ID | 415 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
recept | +0.716 |
acht | +0.696 |
xxxxxxxx | +0.655 |
phabet | +0.651 |
ieth | +0.632 |
Neg logit contributions | |
anamo | -1.276 |
DCS | -1.196 |
Salvador | -1.172 |
ⓘ | -1.161 |
abul | -1.159 |
Token | C |
Token ID | 327 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
recept | +0.182 |
acht | +0.177 |
xxxxxxxx | +0.169 |
phabet | +0.168 |
ieth | +0.164 |
Neg logit contributions | |
anamo | -0.228 |
DCS | -0.211 |
abul | -0.205 |
Salvador | -0.205 |
ⓘ | -0.202 |
Token | - |
Token ID | 12 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
recept | +0.143 |
acht | +0.140 |
xxxxxxxx | +0.133 |
phabet | +0.132 |
ieth | +0.128 |
Neg logit contributions | |
anamo | -0.209 |
DCS | -0.195 |
Salvador | -0.191 |
abul | -0.190 |
ⓘ | -0.189 |
Token | 14 |
Token ID | 1415 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
recept | +0.067 |
acht | +0.066 |
xxxxxxxx | +0.063 |
phabet | +0.063 |
ieth | +0.061 |
Neg logit contributions | |
anamo | -0.068 |
DCS | -0.063 |
Salvador | -0.062 |
abul | -0.061 |
ⓘ | -0.061 |
Token | together |
Token ID | 1978 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
recept | +0.129 |
acht | +0.126 |
xxxxxxxx | +0.120 |
phabet | +0.119 |
ieth | +0.116 |
Neg logit contributions | |
anamo | -0.182 |
DCS | -0.169 |
Salvador | -0.166 |
abul | -0.165 |
ⓘ | -0.164 |
Token | with |
Token ID | 351 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
anamo | +0.231 |
DCS | +0.212 |
Salvador | +0.207 |
abul | +0.206 |
ⓘ | +0.204 |
Neg logit contributions | |
recept | -0.185 |
acht | -0.182 |
xxxxxxxx | -0.173 |
phabet | -0.170 |
ieth | -0.167 |
Token | many |
Token ID | 867 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
recept | +0.270 |
acht | +0.264 |
xxxxxxxx | +0.252 |
phabet | +0.251 |
ieth | +0.245 |
Neg logit contributions | |
anamo | -0.312 |
DCS | -0.287 |
Salvador | -0.281 |
abul | -0.279 |
ⓘ | -0.277 |
Token | other |
Token ID | 584 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
anamo | +0.268 |
DCS | +0.245 |
Salvador | +0.238 |
abul | +0.237 |
ⓘ | +0.235 |
Neg logit contributions | |
recept | -0.307 |
acht | -0.302 |
xxxxxxxx | -0.290 |
phabet | -0.289 |
ieth | -0.283 |
Token | remarkable |
Token ID | 11004 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
recept | +0.237 |
acht | +0.231 |
xxxxxxxx | +0.221 |
phabet | +0.220 |
ieth | +0.215 |
Neg logit contributions | |
anamo | -0.280 |
DCS | -0.258 |
Salvador | -0.251 |
abul | -0.251 |
ⓘ | -0.248 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
recept | +0.710 |
acht | +0.689 |
xxxxxxxx | +0.661 |
phabet | +0.655 |
ieth | +0.642 |
Neg logit contributions | |
anamo | -0.863 |
DCS | -0.795 |
Salvador | -0.772 |
abul | -0.771 |
ⓘ | -0.763 |
Token | ord |
Token ID | 585 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
anamo | +3.718 |
DCS | +3.494 |
abul | +3.480 |
Salvador | +3.319 |
sole | +3.318 |
Neg logit contributions | |
recept | -3.951 |
acht | -3.828 |
xxxxxxxx | -3.668 |
phabet | -3.651 |
ieth | -3.554 |
Token | ances |
Token ID | 1817 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
recept | +0.710 |
acht | +0.694 |
xxxxxxxx | +0.651 |
phabet | +0.648 |
ieth | +0.630 |
Neg logit contributions | |
anamo | -1.230 |
DCS | -1.153 |
Salvador | -1.133 |
ⓘ | -1.121 |
abul | -1.118 |
Token | between |
Token ID | 1022 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
anamo | +0.132 |
DCS | +0.123 |
Salvador | +0.120 |
abul | +0.119 |
ⓘ | +0.118 |
Neg logit contributions | |
recept | -0.099 |
acht | -0.097 |
xxxxxxxx | -0.093 |
phabet | -0.092 |
ieth | -0.090 |
Token | samples |
Token ID | 8405 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
anamo | +0.239 |
DCS | +0.222 |
Salvador | +0.217 |
abul | +0.216 |
ⓘ | +0.215 |
Neg logit contributions | |
recept | -0.193 |
acht | -0.190 |
xxxxxxxx | -0.181 |
phabet | -0.180 |
ieth | -0.175 |
Token | from |
Token ID | 422 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
anamo | +0.099 |
DCS | +0.092 |
Salvador | +0.090 |
abul | +0.090 |
ⓘ | +0.089 |
Neg logit contributions | |
recept | -0.072 |
acht | -0.071 |
xxxxxxxx | -0.067 |
phabet | -0.067 |
ieth | -0.065 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
recept | +0.021 |
acht | +0.021 |
xxxxxxxx | +0.020 |
phabet | +0.020 |
ieth | +0.019 |
Neg logit contributions | |
anamo | -0.019 |
DCS | -0.017 |
abul | -0.017 |
Salvador | -0.017 |
ⓘ | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
anamo | +0.238 |
DCS | +0.221 |
Salvador | +0.216 |
abul | +0.215 |
ⓘ | +0.213 |
Neg logit contributions | |
recept | -0.182 |
acht | -0.179 |
xxxxxxxx | -0.170 |
phabet | -0.169 |
ieth | -0.164 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
anamo | +0.160 |
DCS | +0.149 |
Salvador | +0.146 |
abul | +0.145 |
ⓘ | +0.144 |
Neg logit contributions | |
recept | -0.116 |
acht | -0.113 |
xxxxxxxx | -0.108 |
phabet | -0.107 |
ieth | -0.104 |
Token | as |
Token ID | 355 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
anamo | +0.173 |
DCS | +0.161 |
Salvador | +0.157 |
abul | +0.157 |
ⓘ | +0.155 |
Neg logit contributions | |
recept | -0.126 |
acht | -0.124 |
xxxxxxxx | -0.117 |
phabet | -0.117 |
ieth | -0.114 |
Token | a |
Token ID | 257 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
anamo | +0.295 |
DCS | +0.274 |
Salvador | +0.270 |
abul | +0.267 |
ⓘ | +0.266 |
Neg logit contributions | |
recept | -0.226 |
acht | -0.223 |
xxxxxxxx | -0.212 |
phabet | -0.212 |
ieth | -0.205 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
anamo | +0.114 |
DCS | +0.105 |
abul | +0.102 |
Salvador | +0.102 |
ⓘ | +0.101 |
Neg logit contributions | |
recept | -0.107 |
acht | -0.105 |
xxxxxxxx | -0.100 |
phabet | -0.099 |
ieth | -0.097 |
Token | ier |
Token ID | 959 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
anamo | +5.546 |
DCS | +5.330 |
abul | +5.238 |
Salvador | +5.185 |
sole | +5.115 |
Neg logit contributions | |
recept | -1.977 |
acht | -1.878 |
xxxxxxxx | -1.764 |
phabet | -1.762 |
ieth | -1.642 |
Token | ge |
Token ID | 469 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
recept | +1.795 |
acht | +1.750 |
xxxxxxxx | +1.664 |
phabet | +1.651 |
ieth | +1.618 |
Neg logit contributions | |
anamo | -2.080 |
DCS | -1.884 |
abul | -1.840 |
Salvador | -1.839 |
ⓘ | -1.826 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
recept | +0.315 |
acht | +0.306 |
xxxxxxxx | +0.290 |
phabet | +0.287 |
ieth | +0.281 |
Neg logit contributions | |
anamo | -0.430 |
DCS | -0.397 |
abul | -0.388 |
Salvador | -0.385 |
ⓘ | -0.384 |
Token | or |
Token ID | 393 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
anamo | +0.173 |
DCS | +0.160 |
Salvador | +0.156 |
abul | +0.156 |
ⓘ | +0.155 |
Neg logit contributions | |
recept | -0.142 |
acht | -0.139 |
xxxxxxxx | -0.132 |
phabet | -0.132 |
ieth | -0.128 |
Token | VIP |
Token ID | 24791 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
recept | +0.074 |
acht | +0.073 |
xxxxxxxx | +0.069 |
phabet | +0.069 |
ieth | +0.067 |
Neg logit contributions | |
anamo | -0.088 |
DCS | -0.082 |
Salvador | -0.080 |
abul | -0.080 |
ⓘ | -0.079 |
Token | sent |
Token ID | 1908 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
recept | +0.231 |
acht | +0.226 |
xxxxxxxx | +0.214 |
phabet | +0.211 |
ieth | +0.206 |
Neg logit contributions | |
anamo | -0.331 |
DCS | -0.308 |
abul | -0.300 |
Salvador | -0.300 |
ⓘ | -0.298 |
Token | him |
Token ID | 683 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
recept | +0.296 |
acht | +0.291 |
xxxxxxxx | +0.278 |
phabet | +0.277 |
ieth | +0.270 |
Neg logit contributions | |
anamo | -0.312 |
DCS | -0.288 |
Salvador | -0.279 |
abul | -0.279 |
ⓘ | -0.276 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
anamo | +0.631 |
DCS | +0.587 |
Salvador | +0.575 |
abul | +0.571 |
ⓘ | +0.568 |
Neg logit contributions | |
recept | -0.485 |
acht | -0.476 |
xxxxxxxx | -0.453 |
phabet | -0.452 |
ieth | -0.439 |
Token | handwritten |
Token ID | 45916 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
anamo | +0.135 |
DCS | +0.124 |
Salvador | +0.121 |
abul | +0.120 |
ⓘ | +0.119 |
Neg logit contributions | |
recept | -0.123 |
acht | -0.121 |
xxxxxxxx | -0.115 |
phabet | -0.115 |
ieth | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
anamo | +0.330 |
DCS | +0.303 |
abul | +0.295 |
Salvador | +0.295 |
ⓘ | +0.292 |
Neg logit contributions | |
recept | -0.289 |
acht | -0.281 |
xxxxxxxx | -0.268 |
phabet | -0.266 |
ieth | -0.261 |
Token | conc |
Token ID | 1673 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
anamo | +0.022 |
DCS | +0.020 |
Salvador | +0.020 |
abul | +0.020 |
ⓘ | +0.019 |
Neg logit contributions | |
recept | -0.020 |
acht | -0.020 |
xxxxxxxx | -0.019 |
phabet | -0.019 |
ieth | -0.018 |
Token | ili |
Token ID | 2403 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
anamo | +4.292 |
DCS | +4.063 |
abul | +3.996 |
Salvador | +3.878 |
sole | +3.870 |
Neg logit contributions | |
recept | -3.138 |
acht | -3.055 |
phabet | -2.935 |
xxxxxxxx | -2.881 |
ieth | -2.778 |
Token | atory |
Token ID | 2870 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
recept | +0.549 |
acht | +0.543 |
xxxxxxxx | +0.519 |
phabet | +0.513 |
ieth | +0.496 |
Neg logit contributions | |
anamo | -0.685 |
DCS | -0.635 |
Salvador | -0.622 |
ⓘ | -0.613 |
abul | -0.611 |
Token | note |
Token ID | 3465 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
recept | +0.485 |
acht | +0.473 |
xxxxxxxx | +0.452 |
phabet | +0.448 |
ieth | +0.439 |
Neg logit contributions | |
anamo | -0.537 |
DCS | -0.491 |
abul | -0.478 |
Salvador | -0.477 |
ⓘ | -0.473 |
Token | . |
Token ID | 13 |
Feature activation | +9.43e-02 |
Pos logit contributions | |
anamo | +1.541 |
DCS | +1.437 |
Salvador | +1.413 |
abul | +1.398 |
ⓘ | +1.392 |
Neg logit contributions | |
recept | -1.215 |
acht | -1.199 |
phabet | -1.146 |
xxxxxxxx | -1.144 |
ieth | -1.108 |
Token | The |
Token ID | 383 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
anamo | +0.079 |
DCS | +0.073 |
abul | +0.071 |
Salvador | +0.071 |
ⓘ | +0.070 |
Neg logit contributions | |
recept | -0.062 |
acht | -0.061 |
xxxxxxxx | -0.058 |
phabet | -0.057 |
ieth | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
recept | +0.122 |
acht | +0.119 |
xxxxxxxx | +0.113 |
phabet | +0.112 |
ieth | +0.109 |
Neg logit contributions | |
anamo | -0.183 |
DCS | -0.171 |
Salvador | -0.167 |
abul | -0.166 |
ⓘ | -0.165 |
Token |
|
Token ID | 198 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
recept | +0.018 |
acht | +0.018 |
xxxxxxxx | +0.017 |
phabet | +0.017 |
ieth | +0.016 |
Neg logit contributions | |
anamo | -0.024 |
DCS | -0.023 |
Salvador | -0.022 |
abul | -0.022 |
ⓘ | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
recept | +0.056 |
acht | +0.055 |
xxxxxxxx | +0.052 |
phabet | +0.052 |
ieth | +0.051 |
Neg logit contributions | |
anamo | -0.080 |
DCS | -0.074 |
Salvador | -0.073 |
abul | -0.072 |
ⓘ | -0.072 |
Token | Despite |
Token ID | 8332 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
anamo | +0.138 |
DCS | +0.127 |
Salvador | +0.124 |
abul | +0.123 |
ⓘ | +0.122 |
Neg logit contributions | |
recept | -0.140 |
acht | -0.137 |
xxxxxxxx | -0.132 |
phabet | -0.131 |
ieth | -0.128 |
Token | her |
Token ID | 607 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
recept | +0.498 |
acht | +0.484 |
xxxxxxxx | +0.462 |
phabet | +0.460 |
ieth | +0.449 |
Neg logit contributions | |
anamo | -0.569 |
DCS | -0.525 |
abul | -0.510 |
Salvador | -0.510 |
ⓘ | -0.505 |
Token | conc |
Token ID | 1673 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
anamo | +0.151 |
DCS | +0.138 |
abul | +0.135 |
Salvador | +0.134 |
ⓘ | +0.133 |
Neg logit contributions | |
recept | -0.134 |
acht | -0.130 |
xxxxxxxx | -0.124 |
phabet | -0.123 |
ieth | -0.121 |
Token | ili |
Token ID | 2403 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
anamo | +3.826 |
DCS | +3.604 |
abul | +3.543 |
Salvador | +3.429 |
jured | +3.416 |
Neg logit contributions | |
recept | -3.231 |
acht | -3.178 |
phabet | -3.085 |
xxxxxxxx | -3.055 |
ieth | -2.898 |
Token | atory |
Token ID | 2870 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
recept | +0.333 |
acht | +0.327 |
xxxxxxxx | +0.312 |
phabet | +0.311 |
ieth | +0.303 |
Neg logit contributions | |
anamo | -0.385 |
DCS | -0.356 |
Salvador | -0.348 |
abul | -0.346 |
ⓘ | -0.344 |
Token | tone |
Token ID | 8216 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
recept | +0.555 |
acht | +0.538 |
xxxxxxxx | +0.513 |
phabet | +0.509 |
ieth | +0.501 |
Neg logit contributions | |
anamo | -0.568 |
DCS | -0.517 |
abul | -0.503 |
Salvador | -0.501 |
ⓘ | -0.496 |
Token | , |
Token ID | 11 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
anamo | +0.251 |
DCS | +0.233 |
Salvador | +0.229 |
abul | +0.227 |
ⓘ | +0.226 |
Neg logit contributions | |
recept | -0.195 |
acht | -0.192 |
xxxxxxxx | -0.183 |
phabet | -0.182 |
ieth | -0.177 |
Token | Merkel |
Token ID | 18263 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
anamo | +0.145 |
DCS | +0.133 |
Salvador | +0.129 |
abul | +0.129 |
ⓘ | +0.127 |
Neg logit contributions | |
recept | -0.154 |
acht | -0.151 |
xxxxxxxx | -0.145 |
phabet | -0.144 |
ieth | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
anamo | +0.451 |
DCS | +0.420 |
Salvador | +0.412 |
abul | +0.409 |
ⓘ | +0.407 |
Neg logit contributions | |
recept | -0.319 |
acht | -0.312 |
xxxxxxxx | -0.297 |
phabet | -0.296 |
ieth | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
recept | +0.275 |
acht | +0.269 |
phabet | +0.256 |
xxxxxxxx | +0.254 |
ieth | +0.247 |
Neg logit contributions | |
anamo | -0.376 |
DCS | -0.353 |
Salvador | -0.345 |
abul | -0.343 |
ⓘ | -0.342 |
Token | Power |
Token ID | 13434 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
recept | +0.142 |
acht | +0.140 |
xxxxxxxx | +0.133 |
phabet | +0.133 |
ieth | +0.129 |
Neg logit contributions | |
anamo | -0.146 |
DCS | -0.133 |
Salvador | -0.132 |
abul | -0.130 |
ⓘ | -0.129 |
Token | Point |
Token ID | 12727 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anamo | +0.449 |
DCS | +0.411 |
abul | +0.396 |
Salvador | +0.390 |
ⓘ | +0.390 |
Neg logit contributions | |
recept | -0.484 |
acht | -0.466 |
xxxxxxxx | -0.456 |
phabet | -0.448 |
ieth | -0.441 |
Token | slide |
Token ID | 10649 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
anamo | +1.356 |
DCS | +1.241 |
Salvador | +1.219 |
abul | +1.211 |
ⓘ | +1.207 |
Neg logit contributions | |
recept | -1.295 |
acht | -1.284 |
xxxxxxxx | -1.235 |
phabet | -1.234 |
ieth | -1.209 |
Token | PNG |
Token ID | 36182 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
anamo | +0.178 |
DCS | +0.141 |
Salvador | +0.131 |
abul | +0.129 |
ⓘ | +0.126 |
Neg logit contributions | |
recept | -0.727 |
acht | -0.719 |
xxxxxxxx | -0.701 |
phabet | -0.700 |
ieth | -0.689 |
Token | larger |
Token ID | 4025 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
anamo | +2.323 |
Salvador | +2.039 |
DCS | +1.962 |
PB | +1.947 |
ridden | +1.944 |
Neg logit contributions | |
recept | -4.500 |
xxxxxxxx | -4.456 |
acht | -4.394 |
ieth | -4.367 |
phabet | -4.288 |
Token | image |
Token ID | 2939 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
anamo | +1.257 |
DCS | +1.146 |
Salvador | +1.128 |
ⓘ | +1.107 |
abul | +1.103 |
Neg logit contributions | |
recept | -1.586 |
acht | -1.575 |
xxxxxxxx | -1.513 |
phabet | -1.507 |
ieth | -1.484 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
anamo | +0.566 |
DCS | +0.530 |
Salvador | +0.525 |
ⓘ | +0.525 |
abul | +0.514 |
Neg logit contributions | |
recept | -0.460 |
acht | -0.447 |
phabet | -0.435 |
xxxxxxxx | -0.422 |
ieth | -0.421 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
recept | +0.086 |
acht | +0.084 |
phabet | +0.080 |
xxxxxxxx | +0.080 |
ieth | +0.078 |
Neg logit contributions | |
anamo | -0.117 |
DCS | -0.110 |
Salvador | -0.108 |
abul | -0.107 |
ⓘ | -0.107 |
Token | larg |
Token ID | 15521 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
anamo | +0.007 |
DCS | +0.006 |
Salvador | +0.006 |
abul | +0.006 |
ⓘ | +0.005 |
Neg logit contributions | |
recept | -0.024 |
acht | -0.023 |
xxxxxxxx | -0.023 |
phabet | -0.023 |
ieth | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anamo | +1.066 |
DCS | +0.993 |
Salvador | +0.971 |
abul | +0.967 |
ⓘ | +0.961 |
Neg logit contributions | |
recept | -0.759 |
acht | -0.744 |
xxxxxxxx | -0.707 |
phabet | -0.703 |
ieth | -0.682 |
Token | to |
Token ID | 284 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
anamo | +0.156 |
DCS | +0.146 |
Salvador | +0.142 |
abul | +0.142 |
ⓘ | +0.141 |
Neg logit contributions | |
recept | -0.107 |
acht | -0.105 |
xxxxxxxx | -0.100 |
phabet | -0.099 |
ieth | -0.096 |
Token | San |
Token ID | 2986 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
anamo | +0.142 |
DCS | +0.130 |
abul | +0.126 |
Salvador | +0.125 |
ⓘ | +0.125 |
Neg logit contributions | |
recept | -0.158 |
acht | -0.156 |
xxxxxxxx | -0.150 |
phabet | -0.149 |
ieth | -0.145 |
Token | Francisco |
Token ID | 6033 |
Feature activation | -8.32e-01 |
Pos logit contributions | |
anamo | +0.702 |
DCS | +0.627 |
ⓘ | +0.592 |
abul | +0.589 |
sole | +0.584 |
Neg logit contributions | |
recept | -1.202 |
acht | -1.197 |
phabet | -1.155 |
xxxxxxxx | -1.155 |
ieth | -1.131 |
Token | ), |
Token ID | 828 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
recept | +0.496 |
acht | +0.487 |
xxxxxxxx | +0.461 |
phabet | +0.459 |
ieth | +0.443 |
Neg logit contributions | |
anamo | -0.738 |
DCS | -0.688 |
Salvador | -0.673 |
abul | -0.673 |
ⓘ | -0.670 |
Token | warning |
Token ID | 6509 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
recept | +0.386 |
acht | +0.377 |
xxxxxxxx | +0.361 |
phabet | +0.357 |
ieth | +0.347 |
Neg logit contributions | |
anamo | -0.467 |
DCS | -0.432 |
abul | -0.423 |
Salvador | -0.420 |
ⓘ | -0.419 |
Token | that |
Token ID | 326 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
anamo | +3.644 |
DCS | +3.358 |
Salvador | +3.332 |
abul | +3.248 |
ⓘ | +3.205 |
Neg logit contributions | |
recept | -3.293 |
acht | -3.217 |
phabet | -3.120 |
xxxxxxxx | -3.061 |
ieth | -3.021 |
Token | Kam |
Token ID | 12670 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
anamo | +0.675 |
DCS | +0.627 |
Salvador | +0.614 |
abul | +0.609 |
ⓘ | +0.605 |
Neg logit contributions | |
recept | -0.534 |
acht | -0.524 |
xxxxxxxx | -0.499 |
phabet | -0.498 |
ieth | -0.484 |
Token | al |
Token ID | 282 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
recept | +0.580 |
acht | +0.578 |
xxxxxxxx | +0.544 |
phabet | +0.539 |
ieth | +0.526 |
Neg logit contributions | |
anamo | -0.808 |
DCS | -0.753 |
Salvador | -0.736 |
ⓘ | -0.728 |
abul | -0.726 |
Token | was |
Token ID | 373 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
recept | +0.828 |
acht | +0.818 |
xxxxxxxx | +0.769 |
phabet | +0.760 |
ieth | +0.747 |
Neg logit contributions | |
anamo | -1.172 |
DCS | -1.092 |
abul | -1.063 |
Salvador | -1.052 |
ⓘ | -1.051 |
Token | " |
Token ID | 366 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
recept | +0.026 |
acht | +0.026 |
xxxxxxxx | +0.024 |
phabet | +0.024 |
ieth | +0.024 |
Neg logit contributions | |
anamo | -0.033 |
DCS | -0.031 |
abul | -0.030 |
Salvador | -0.030 |
ⓘ | -0.030 |
Token | "[ |
Token ID | 17912 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
recept | +0.882 |
acht | +0.865 |
xxxxxxxx | +0.825 |
phabet | +0.817 |
ieth | +0.804 |
Neg logit contributions | |
anamo | -0.939 |
DCS | -0.867 |
Salvador | -0.835 |
abul | -0.833 |
ⓘ | -0.826 |
Token | 41 |
Token ID | 3901 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
anamo | +1.279 |
DCS | +1.182 |
Salvador | +1.151 |
abul | +1.146 |
ⓘ | +1.135 |
Neg logit contributions | |
recept | -1.254 |
acht | -1.232 |
phabet | -1.178 |
xxxxxxxx | -1.177 |
ieth | -1.147 |
Token | ] |
Token ID | 60 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
recept | +0.471 |
acht | +0.464 |
xxxxxxxx | +0.446 |
phabet | +0.445 |
ieth | +0.434 |
Neg logit contributions | |
anamo | -0.423 |
DCS | -0.386 |
Salvador | -0.377 |
abul | -0.374 |
ⓘ | -0.371 |
Token | and |
Token ID | 290 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
anamo | +0.310 |
DCS | +0.288 |
abul | +0.279 |
Salvador | +0.278 |
ⓘ | +0.276 |
Neg logit contributions | |
recept | -0.245 |
acht | -0.238 |
xxxxxxxx | -0.228 |
phabet | -0.225 |
ieth | -0.219 |
Token | Peterson |
Token ID | 18914 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
anamo | +0.270 |
DCS | +0.252 |
abul | +0.244 |
Salvador | +0.242 |
ⓘ | +0.240 |
Neg logit contributions | |
recept | -0.215 |
acht | -0.209 |
xxxxxxxx | -0.200 |
phabet | -0.197 |
ieth | -0.193 |
Token | conc |
Token ID | 1673 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
anamo | +0.142 |
DCS | +0.132 |
Salvador | +0.128 |
abul | +0.128 |
ⓘ | +0.127 |
Neg logit contributions | |
recept | -0.100 |
acht | -0.097 |
xxxxxxxx | -0.092 |
phabet | -0.091 |
ieth | -0.090 |
Token | urs |
Token ID | 1834 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
anamo | +2.693 |
DCS | +2.429 |
abul | +2.339 |
Salvador | +2.287 |
sole | +2.272 |
Neg logit contributions | |
recept | -4.150 |
acht | -4.085 |
phabet | -4.020 |
xxxxxxxx | -3.939 |
ieth | -3.776 |
Token | that |
Token ID | 326 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
anamo | +0.827 |
DCS | +0.768 |
Salvador | +0.750 |
abul | +0.747 |
ⓘ | +0.741 |
Neg logit contributions | |
recept | -0.643 |
acht | -0.630 |
xxxxxxxx | -0.599 |
phabet | -0.595 |
ieth | -0.581 |
Token | the |
Token ID | 262 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
anamo | +0.198 |
DCS | +0.184 |
abul | +0.178 |
Salvador | +0.177 |
ⓘ | +0.176 |
Neg logit contributions | |
recept | -0.170 |
acht | -0.165 |
xxxxxxxx | -0.158 |
phabet | -0.156 |
ieth | -0.153 |
Token | Muslims |
Token ID | 7045 |
Feature activation | -6.72e-01 |
Pos logit contributions | |
recept | +0.090 |
acht | +0.088 |
xxxxxxxx | +0.084 |
phabet | +0.083 |
ieth | +0.081 |
Neg logit contributions | |
anamo | -0.094 |
DCS | -0.086 |
abul | -0.083 |
Salvador | -0.083 |
ⓘ | -0.082 |
Token | wanted |
Token ID | 2227 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
recept | +0.412 |
acht | +0.402 |
xxxxxxxx | +0.379 |
phabet | +0.375 |
ieth | +0.366 |
Neg logit contributions | |
anamo | -0.592 |
DCS | -0.552 |
abul | -0.537 |
Salvador | -0.536 |
ⓘ | -0.531 |
Token | seekers |
Token ID | 47971 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
anamo | +0.402 |
DCS | +0.367 |
Salvador | +0.356 |
ⓘ | +0.351 |
abul | +0.350 |
Neg logit contributions | |
recept | -0.493 |
acht | -0.488 |
xxxxxxxx | -0.469 |
phabet | -0.466 |
ieth | -0.457 |
Token | and |
Token ID | 290 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
anamo | +0.544 |
DCS | +0.507 |
Salvador | +0.495 |
abul | +0.493 |
ⓘ | +0.490 |
Neg logit contributions | |
recept | -0.381 |
acht | -0.373 |
xxxxxxxx | -0.354 |
phabet | -0.352 |
ieth | -0.342 |
Token | would |
Token ID | 561 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
anamo | +0.447 |
DCS | +0.413 |
abul | +0.403 |
Salvador | +0.402 |
ⓘ | +0.399 |
Neg logit contributions | |
recept | -0.356 |
acht | -0.346 |
xxxxxxxx | -0.329 |
phabet | -0.326 |
ieth | -0.319 |
Token | be |
Token ID | 307 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
anamo | +0.628 |
DCS | +0.581 |
Salvador | +0.569 |
abul | +0.566 |
ⓘ | +0.563 |
Neg logit contributions | |
recept | -0.471 |
acht | -0.461 |
xxxxxxxx | -0.438 |
phabet | -0.434 |
ieth | -0.423 |
Token | fully |
Token ID | 3938 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
anamo | +0.058 |
DCS | +0.054 |
abul | +0.053 |
Salvador | +0.053 |
ⓘ | +0.052 |
Neg logit contributions | |
recept | -0.047 |
acht | -0.046 |
xxxxxxxx | -0.043 |
phabet | -0.043 |
ieth | -0.042 |
Token | compens |
Token ID | 7144 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
anamo | +0.384 |
DCS | +0.358 |
Salvador | +0.351 |
abul | +0.349 |
ⓘ | +0.347 |
Neg logit contributions | |
recept | -0.251 |
acht | -0.246 |
xxxxxxxx | -0.233 |
phabet | -0.232 |
ieth | -0.225 |
Token | ating |
Token ID | 803 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
anamo | +2.792 |
DCS | +2.516 |
abul | +2.456 |
Salvador | +2.435 |
ⓘ | +2.404 |
Neg logit contributions | |
recept | -3.981 |
acht | -3.922 |
phabet | -3.788 |
xxxxxxxx | -3.767 |
ieth | -3.690 |
Token | those |
Token ID | 883 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
anamo | +1.392 |
DCS | +1.289 |
Salvador | +1.255 |
abul | +1.250 |
ⓘ | +1.245 |
Neg logit contributions | |
recept | -1.148 |
acht | -1.126 |
xxxxxxxx | -1.074 |
phabet | -1.069 |
ieth | -1.039 |
Token | injured |
Token ID | 6686 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
anamo | +0.203 |
DCS | +0.187 |
abul | +0.181 |
Salvador | +0.180 |
ⓘ | +0.180 |
Neg logit contributions | |
recept | -0.188 |
acht | -0.184 |
xxxxxxxx | -0.175 |
phabet | -0.173 |
ieth | -0.171 |
Token | in |
Token ID | 287 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
anamo | +1.720 |
DCS | +1.601 |
Salvador | +1.572 |
abul | +1.560 |
ⓘ | +1.551 |
Neg logit contributions | |
recept | -1.260 |
acht | -1.235 |
xxxxxxxx | -1.174 |
phabet | -1.172 |
ieth | -1.136 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
anamo | +0.333 |
DCS | +0.308 |
abul | +0.301 |
Salvador | +0.300 |
ⓘ | +0.299 |
Neg logit contributions | |
recept | -0.252 |
acht | -0.247 |
xxxxxxxx | -0.234 |
phabet | -0.232 |
ieth | -0.227 |
Token | against |
Token ID | 1028 |
Feature activation | +7.62e-03 |
Pos logit contributions | |
anamo | +0.299 |
DCS | +0.278 |
Salvador | +0.271 |
abul | +0.270 |
ⓘ | +0.268 |
Neg logit contributions | |
recept | -0.219 |
acht | -0.215 |
xxxxxxxx | -0.204 |
phabet | -0.203 |
ieth | -0.198 |
Token | Kul |
Token ID | 50024 |
Feature activation | +2.94e-03 |
Pos logit contributions | |
anamo | +0.006 |
DCS | +0.005 |
abul | +0.005 |
Salvador | +0.005 |
ⓘ | +0.005 |
Neg logit contributions | |
recept | -0.006 |
acht | -0.006 |
xxxxxxxx | -0.005 |
phabet | -0.005 |
ieth | -0.005 |
Token | ik |
Token ID | 1134 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
anamo | +0.002 |
DCS | +0.002 |
Salvador | +0.002 |
abul | +0.002 |
ⓘ | +0.002 |
Neg logit contributions | |
recept | -0.002 |
acht | -0.002 |
xxxxxxxx | -0.002 |
phabet | -0.002 |
ieth | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
recept | +0.271 |
acht | +0.269 |
xxxxxxxx | +0.255 |
phabet | +0.254 |
ieth | +0.250 |
Neg logit contributions | |
anamo | -0.266 |
DCS | -0.245 |
Salvador | -0.238 |
abul | -0.235 |
ⓘ | -0.234 |
Token | widely |
Token ID | 6768 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
anamo | +0.376 |
DCS | +0.347 |
Salvador | +0.339 |
abul | +0.338 |
ⓘ | +0.334 |
Neg logit contributions | |
recept | -0.316 |
acht | -0.309 |
xxxxxxxx | -0.295 |
phabet | -0.293 |
ieth | -0.286 |
Token | propag |
Token ID | 8928 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
anamo | +0.279 |
DCS | +0.257 |
Salvador | +0.251 |
abul | +0.250 |
ⓘ | +0.248 |
Neg logit contributions | |
recept | -0.231 |
acht | -0.225 |
xxxxxxxx | -0.215 |
phabet | -0.213 |
ieth | -0.209 |
Token | and |
Token ID | 392 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
anamo | +2.702 |
DCS | +2.468 |
abul | +2.457 |
sole | +2.384 |
jured | +2.362 |
Neg logit contributions | |
recept | -3.976 |
acht | -3.866 |
phabet | -3.854 |
xxxxxxxx | -3.759 |
ieth | -3.702 |
Token | ized |
Token ID | 1143 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
anamo | +1.140 |
DCS | +1.044 |
abul | +1.015 |
Salvador | +1.013 |
ⓘ | +1.004 |
Neg logit contributions | |
recept | -1.293 |
acht | -1.270 |
phabet | -1.230 |
xxxxxxxx | -1.225 |
ieth | -1.182 |
Token | , |
Token ID | 11 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
anamo | +0.857 |
DCS | +0.793 |
Salvador | +0.776 |
abul | +0.771 |
ⓘ | +0.766 |
Neg logit contributions | |
recept | -0.711 |
acht | -0.698 |
xxxxxxxx | -0.665 |
phabet | -0.663 |
ieth | -0.645 |
Token | which |
Token ID | 543 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
anamo | +0.382 |
DCS | +0.353 |
Salvador | +0.343 |
abul | +0.343 |
ⓘ | +0.339 |
Neg logit contributions | |
recept | -0.320 |
acht | -0.313 |
xxxxxxxx | -0.298 |
phabet | -0.296 |
ieth | -0.289 |
Token | created |
Token ID | 2727 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
anamo | +0.342 |
DCS | +0.317 |
abul | +0.309 |
Salvador | +0.308 |
ⓘ | +0.306 |
Neg logit contributions | |
recept | -0.243 |
acht | -0.237 |
xxxxxxxx | -0.224 |
phabet | -0.223 |
ieth | -0.217 |
Token | sun |
Token ID | 4252 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
recept | +0.018 |
acht | +0.017 |
xxxxxxxx | +0.016 |
phabet | +0.016 |
ieth | +0.016 |
Neg logit contributions | |
anamo | -0.022 |
DCS | -0.020 |
abul | -0.019 |
Salvador | -0.019 |
ⓘ | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
anamo | +1.947 |
DCS | +1.812 |
Salvador | +1.777 |
abul | +1.766 |
ⓘ | +1.755 |
Neg logit contributions | |
recept | -1.394 |
acht | -1.368 |
xxxxxxxx | -1.300 |
phabet | -1.298 |
ieth | -1.255 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
recept | +0.149 |
acht | +0.146 |
xxxxxxxx | +0.140 |
phabet | +0.139 |
ieth | +0.135 |
Neg logit contributions | |
anamo | -0.168 |
DCS | -0.154 |
abul | -0.150 |
Salvador | -0.150 |
ⓘ | -0.149 |
Token | moon |
Token ID | 8824 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
recept | +0.078 |
acht | +0.076 |
xxxxxxxx | +0.073 |
phabet | +0.073 |
ieth | +0.071 |
Neg logit contributions | |
anamo | -0.072 |
DCS | -0.066 |
abul | -0.064 |
Salvador | -0.063 |
ⓘ | -0.063 |
Token | are |
Token ID | 389 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
anamo | +1.268 |
DCS | +1.178 |
Salvador | +1.154 |
abul | +1.147 |
ⓘ | +1.140 |
Neg logit contributions | |
recept | -0.978 |
acht | -0.960 |
xxxxxxxx | -0.915 |
phabet | -0.912 |
ieth | -0.885 |
Token | tug |
Token ID | 27762 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
anamo | +0.157 |
DCS | +0.144 |
abul | +0.140 |
Salvador | +0.139 |
ⓘ | +0.138 |
Neg logit contributions | |
recept | -0.140 |
acht | -0.136 |
xxxxxxxx | -0.130 |
phabet | -0.128 |
ieth | -0.126 |
Token | ging |
Token ID | 2667 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
anamo | +3.537 |
DCS | +3.285 |
abul | +3.204 |
Salvador | +3.196 |
sole | +3.152 |
Neg logit contributions | |
acht | -3.133 |
recept | -3.118 |
xxxxxxxx | -2.972 |
phabet | -2.945 |
ieth | -2.888 |
Token | on |
Token ID | 319 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
anamo | +0.755 |
DCS | +0.700 |
abul | +0.682 |
Salvador | +0.681 |
ⓘ | +0.674 |
Neg logit contributions | |
recept | -0.577 |
acht | -0.563 |
xxxxxxxx | -0.536 |
phabet | -0.531 |
ieth | -0.518 |
Token | Earth |
Token ID | 3668 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
anamo | +0.237 |
DCS | +0.217 |
abul | +0.212 |
Salvador | +0.211 |
ⓘ | +0.210 |
Neg logit contributions | |
recept | -0.187 |
acht | -0.181 |
xxxxxxxx | -0.173 |
phabet | -0.170 |
ieth | -0.167 |
Token | 's |
Token ID | 338 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
anamo | +1.175 |
DCS | +1.093 |
Salvador | +1.070 |
abul | +1.065 |
ⓘ | +1.058 |
Neg logit contributions | |
recept | -0.843 |
acht | -0.826 |
xxxxxxxx | -0.784 |
phabet | -0.781 |
ieth | -0.758 |
Token | spin |
Token ID | 7906 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
recept | +0.015 |
acht | +0.014 |
xxxxxxxx | +0.014 |
phabet | +0.013 |
ieth | +0.013 |
Neg logit contributions | |
anamo | -0.017 |
DCS | -0.015 |
abul | -0.015 |
Salvador | -0.015 |
ⓘ | -0.014 |
Token | screen |
Token ID | 3159 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
anamo | +0.478 |
DCS | +0.440 |
Salvador | +0.430 |
abul | +0.427 |
ⓘ | +0.424 |
Neg logit contributions | |
recept | -0.471 |
acht | -0.463 |
xxxxxxxx | -0.444 |
phabet | -0.443 |
ieth | -0.431 |
Token | grab |
Token ID | 5552 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
anamo | +0.693 |
DCS | +0.628 |
Salvador | +0.608 |
abul | +0.605 |
ⓘ | +0.599 |
Neg logit contributions | |
recept | -0.934 |
acht | -0.921 |
xxxxxxxx | -0.886 |
phabet | -0.886 |
ieth | -0.866 |
Token | ] |
Token ID | 60 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
anamo | +0.893 |
DCS | +0.823 |
Salvador | +0.809 |
abul | +0.799 |
ⓘ | +0.794 |
Neg logit contributions | |
recept | -0.884 |
acht | -0.872 |
xxxxxxxx | -0.836 |
phabet | -0.834 |
ieth | -0.812 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
anamo | +0.788 |
DCS | +0.740 |
Salvador | +0.732 |
ⓘ | +0.720 |
abul | +0.715 |
Neg logit contributions | |
recept | -0.485 |
acht | -0.470 |
phabet | -0.441 |
xxxxxxxx | -0.440 |
ieth | -0.428 |
Token | ( |
Token ID | 7 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
recept | +1.191 |
acht | +1.183 |
xxxxxxxx | +1.145 |
phabet | +1.119 |
ieth | +1.095 |
Neg logit contributions | |
anamo | -1.315 |
DCS | -1.181 |
Salvador | -1.176 |
ⓘ | -1.160 |
abul | -1.159 |
Token | Updated |
Token ID | 17354 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
anamo | +0.156 |
DCS | +0.141 |
Salvador | +0.138 |
abul | +0.138 |
ⓘ | +0.137 |
Neg logit contributions | |
recept | -0.175 |
acht | -0.172 |
xxxxxxxx | -0.166 |
phabet | -0.165 |
ieth | -0.161 |
Token | below |
Token ID | 2174 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
anamo | +3.504 |
DCS | +3.249 |
Salvador | +3.220 |
ⓘ | +3.167 |
abul | +3.158 |
Neg logit contributions | |
recept | -3.163 |
acht | -3.117 |
xxxxxxxx | -2.979 |
phabet | -2.970 |
ieth | -2.899 |
Token | ) |
Token ID | 8 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
recept | +0.320 |
acht | +0.311 |
xxxxxxxx | +0.296 |
phabet | +0.294 |
ieth | +0.287 |
Neg logit contributions | |
anamo | -0.457 |
DCS | -0.425 |
abul | -0.413 |
ⓘ | -0.410 |
Salvador | -0.409 |
Token |
|
Token ID | 198 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
recept | +0.036 |
acht | +0.035 |
xxxxxxxx | +0.034 |
phabet | +0.034 |
ieth | +0.033 |
Neg logit contributions | |
anamo | -0.045 |
DCS | -0.042 |
abul | -0.041 |
Salvador | -0.041 |
ⓘ | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
anamo | +0.360 |
DCS | +0.334 |
Salvador | +0.327 |
abul | +0.326 |
ⓘ | +0.323 |
Neg logit contributions | |
recept | -0.246 |
acht | -0.242 |
xxxxxxxx | -0.230 |
phabet | -0.227 |
ieth | -0.221 |
Token | The |
Token ID | 464 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
anamo | +0.388 |
DCS | +0.356 |
Salvador | +0.350 |
abul | +0.347 |
ⓘ | +0.345 |
Neg logit contributions | |
recept | -0.344 |
acht | -0.339 |
xxxxxxxx | -0.325 |
phabet | -0.322 |
ieth | -0.314 |
Token | � |
Token ID | 447 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
recept | +0.119 |
acht | +0.118 |
xxxxxxxx | +0.114 |
phabet | +0.112 |
ieth | +0.110 |
Neg logit contributions | |
anamo | -0.118 |
DCS | -0.108 |
abul | -0.105 |
Salvador | -0.104 |
ⓘ | -0.104 |
Token | � |
Token ID | 251 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
anamo | +0.100 |
DCS | +0.092 |
Salvador | +0.091 |
abul | +0.090 |
ⓘ | +0.089 |
Neg logit contributions | |
recept | -0.080 |
acht | -0.078 |
xxxxxxxx | -0.074 |
phabet | -0.074 |
ieth | -0.072 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
anamo | +0.071 |
DCS | +0.066 |
Salvador | +0.065 |
abul | +0.065 |
ⓘ | +0.064 |
Neg logit contributions | |
recept | -0.050 |
acht | -0.049 |
xxxxxxxx | -0.047 |
phabet | -0.046 |
ieth | -0.045 |
Token | R |
Token ID | 49 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
recept | +1.200 |
acht | +1.192 |
xxxxxxxx | +1.154 |
phabet | +1.128 |
ieth | +1.104 |
Neg logit contributions | |
anamo | -1.326 |
DCS | -1.191 |
Salvador | -1.184 |
ⓘ | -1.169 |
abul | -1.168 |
Token | amon |
Token ID | 16487 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
recept | +0.129 |
acht | +0.127 |
xxxxxxxx | +0.121 |
phabet | +0.121 |
ieth | +0.117 |
Neg logit contributions | |
anamo | -0.146 |
DCS | -0.135 |
Salvador | -0.132 |
abul | -0.131 |
ⓘ | -0.130 |
Token | Hare |
Token ID | 42285 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
recept | +0.082 |
acht | +0.081 |
xxxxxxxx | +0.077 |
phabet | +0.077 |
ieth | +0.075 |
Neg logit contributions | |
anamo | -0.081 |
DCS | -0.075 |
Salvador | -0.072 |
abul | -0.072 |
ⓘ | -0.071 |
Token | wood |
Token ID | 3822 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
anamo | +3.830 |
DCS | +3.577 |
ⓘ | +3.522 |
Salvador | +3.516 |
abul | +3.484 |
Neg logit contributions | |
recept | -2.817 |
acht | -2.741 |
xxxxxxxx | -2.644 |
phabet | -2.634 |
ieth | -2.569 |
Token | met |
Token ID | 1138 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
anamo | +0.646 |
DCS | +0.601 |
Salvador | +0.588 |
abul | +0.585 |
ⓘ | +0.582 |
Neg logit contributions | |
recept | -0.468 |
acht | -0.459 |
xxxxxxxx | -0.436 |
phabet | -0.435 |
ieth | -0.422 |
Token | with |
Token ID | 351 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
recept | +1.720 |
acht | +1.700 |
xxxxxxxx | +1.620 |
phabet | +1.604 |
ieth | +1.580 |
Neg logit contributions | |
anamo | -1.701 |
DCS | -1.566 |
abul | -1.511 |
ⓘ | -1.510 |
Salvador | -1.492 |
Token | the |
Token ID | 262 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
anamo | +0.363 |
DCS | +0.333 |
abul | +0.324 |
Salvador | +0.323 |
ⓘ | +0.320 |
Neg logit contributions | |
recept | -0.359 |
acht | -0.352 |
xxxxxxxx | -0.336 |
phabet | -0.335 |
ieth | -0.327 |
Token | Carolina |
Token ID | 5913 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
anamo | +0.359 |
DCS | +0.328 |
abul | +0.320 |
Salvador | +0.319 |
ⓘ | +0.316 |
Neg logit contributions | |
recept | -0.366 |
acht | -0.359 |
xxxxxxxx | -0.343 |
phabet | -0.342 |
ieth | -0.334 |
Token | because |
Token ID | 780 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
anamo | +0.332 |
DCS | +0.307 |
Salvador | +0.299 |
abul | +0.299 |
ⓘ | +0.297 |
Neg logit contributions | |
recept | -0.256 |
acht | -0.251 |
xxxxxxxx | -0.239 |
phabet | -0.238 |
ieth | -0.230 |
Token | nothing |
Token ID | 2147 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
recept | +0.170 |
acht | +0.166 |
xxxxxxxx | +0.158 |
phabet | +0.157 |
ieth | +0.153 |
Neg logit contributions | |
anamo | -0.225 |
DCS | -0.208 |
abul | -0.203 |
Salvador | -0.202 |
ⓘ | -0.201 |
Token | says |
Token ID | 1139 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
anamo | +1.226 |
DCS | +1.141 |
Salvador | +1.117 |
abul | +1.112 |
ⓘ | +1.105 |
Neg logit contributions | |
recept | -0.845 |
acht | -0.827 |
xxxxxxxx | -0.785 |
phabet | -0.781 |
ieth | -0.759 |
Token | mad |
Token ID | 8805 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
recept | +0.423 |
acht | +0.413 |
xxxxxxxx | +0.395 |
phabet | +0.390 |
ieth | +0.384 |
Neg logit contributions | |
anamo | -0.473 |
DCS | -0.435 |
abul | -0.424 |
Salvador | -0.422 |
ⓘ | -0.419 |
Token | geek |
Token ID | 27314 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
recept | +0.389 |
acht | +0.381 |
xxxxxxxx | +0.363 |
phabet | +0.362 |
ieth | +0.353 |
Neg logit contributions | |
anamo | -0.436 |
DCS | -0.402 |
Salvador | -0.393 |
abul | -0.389 |
ⓘ | -0.387 |
Token | cred |
Token ID | 2600 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
recept | +1.264 |
acht | +1.229 |
phabet | +1.161 |
xxxxxxxx | +1.153 |
ieth | +1.131 |
Neg logit contributions | |
anamo | -1.797 |
DCS | -1.677 |
Salvador | -1.620 |
abul | -1.618 |
ⓘ | -1.614 |
Token | like |
Token ID | 588 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
anamo | +3.637 |
DCS | +3.387 |
Salvador | +3.312 |
abul | +3.308 |
ⓘ | +3.267 |
Neg logit contributions | |
recept | -3.013 |
acht | -2.951 |
xxxxxxxx | -2.841 |
phabet | -2.808 |
ieth | -2.728 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anamo | +0.299 |
DCS | +0.278 |
Salvador | +0.273 |
abul | +0.270 |
ⓘ | +0.268 |
Neg logit contributions | |
recept | -0.236 |
acht | -0.232 |
phabet | -0.221 |
xxxxxxxx | -0.221 |
ieth | -0.214 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
recept | +0.693 |
acht | +0.674 |
xxxxxxxx | +0.640 |
phabet | +0.630 |
ieth | +0.616 |
Neg logit contributions | |
anamo | -0.960 |
DCS | -0.889 |
abul | -0.866 |
Salvador | -0.863 |
ⓘ | -0.861 |
Token | TR |
Token ID | 7579 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
anamo | +0.082 |
DCS | +0.076 |
Salvador | +0.074 |
abul | +0.073 |
ⓘ | +0.073 |
Neg logit contributions | |
recept | -0.073 |
acht | -0.071 |
xxxxxxxx | -0.068 |
phabet | -0.068 |
ieth | -0.066 |
Token | ON |
Token ID | 1340 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
anamo | +1.017 |
DCS | +0.924 |
Salvador | +0.896 |
abul | +0.885 |
ⓘ | +0.875 |
Neg logit contributions | |
recept | -1.574 |
acht | -1.555 |
phabet | -1.504 |
xxxxxxxx | -1.494 |
ieth | -1.469 |
Token | lake |
Token ID | 13546 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
anamo | +0.449 |
DCS | +0.415 |
Salvador | +0.405 |
abul | +0.403 |
ⓘ | +0.400 |
Neg logit contributions | |
recept | -0.386 |
acht | -0.379 |
xxxxxxxx | -0.361 |
phabet | -0.360 |
ieth | -0.351 |
Token | near |
Token ID | 1474 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
anamo | +1.315 |
DCS | +1.221 |
Salvador | +1.194 |
abul | +1.186 |
ⓘ | +1.176 |
Neg logit contributions | |
recept | -0.985 |
acht | -0.964 |
xxxxxxxx | -0.915 |
phabet | -0.910 |
ieth | -0.887 |
Token | Da |
Token ID | 9637 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
recept | +0.166 |
acht | +0.163 |
xxxxxxxx | +0.156 |
phabet | +0.155 |
ieth | +0.152 |
Neg logit contributions | |
anamo | -0.150 |
DCS | -0.137 |
abul | -0.132 |
Salvador | -0.131 |
ⓘ | -0.129 |
Token | B |
Token ID | 347 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
anamo | +1.565 |
DCS | +1.453 |
Salvador | +1.418 |
abul | +1.410 |
ⓘ | +1.401 |
Neg logit contributions | |
recept | -1.244 |
acht | -1.225 |
xxxxxxxx | -1.165 |
phabet | -1.161 |
ieth | -1.130 |
Token | ao |
Token ID | 5488 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
anamo | +0.085 |
DCS | +0.079 |
Salvador | +0.078 |
abul | +0.077 |
ⓘ | +0.077 |
Neg logit contributions | |
recept | -0.067 |
acht | -0.067 |
xxxxxxxx | -0.063 |
phabet | -0.062 |
ieth | -0.061 |
Token | Shan |
Token ID | 14866 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
anamo | +0.212 |
DCS | +0.198 |
Salvador | +0.192 |
abul | +0.190 |
sole | +0.188 |
Neg logit contributions | |
recept | -0.172 |
acht | -0.171 |
xxxxxxxx | -0.161 |
phabet | -0.160 |
ieth | -0.157 |
Token | in |
Token ID | 287 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
anamo | +3.597 |
DCS | +3.327 |
abul | +3.264 |
ⓘ | +3.260 |
Salvador | +3.260 |
Neg logit contributions | |
recept | -3.058 |
acht | -2.981 |
phabet | -2.874 |
xxxxxxxx | -2.870 |
ieth | -2.781 |
Token | the |
Token ID | 262 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
anamo | +0.370 |
DCS | +0.333 |
abul | +0.319 |
Salvador | +0.317 |
HUD | +0.313 |
Neg logit contributions | |
recept | -0.430 |
acht | -0.420 |
xxxxxxxx | -0.403 |
phabet | -0.399 |
ieth | -0.391 |
Token | northern |
Token ID | 7840 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
anamo | +0.356 |
DCS | +0.318 |
abul | +0.304 |
Salvador | +0.299 |
HUD | +0.298 |
Neg logit contributions | |
recept | -0.474 |
acht | -0.460 |
xxxxxxxx | -0.445 |
phabet | -0.439 |
ieth | -0.433 |
Token | part |
Token ID | 636 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
anamo | +1.713 |
DCS | +1.553 |
Salvador | +1.503 |
abul | +1.496 |
ⓘ | +1.478 |
Neg logit contributions | |
recept | -2.125 |
acht | -2.089 |
xxxxxxxx | -2.006 |
phabet | -1.998 |
ieth | -1.961 |
Token | of |
Token ID | 286 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
recept | +0.390 |
acht | +0.382 |
xxxxxxxx | +0.359 |
phabet | +0.352 |
ieth | +0.344 |
Neg logit contributions | |
anamo | -0.745 |
DCS | -0.695 |
abul | -0.678 |
Salvador | -0.678 |
ⓘ | -0.669 |
Token | you |
Token ID | 345 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
recept | +0.587 |
acht | +0.573 |
xxxxxxxx | +0.542 |
phabet | +0.539 |
ieth | +0.523 |
Neg logit contributions | |
anamo | -0.879 |
DCS | -0.818 |
Salvador | -0.800 |
abul | -0.798 |
ⓘ | -0.795 |
Token | don |
Token ID | 836 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
recept | +0.485 |
acht | +0.473 |
xxxxxxxx | +0.445 |
phabet | +0.439 |
ieth | +0.425 |
Neg logit contributions | |
anamo | -0.862 |
DCS | -0.804 |
Salvador | -0.788 |
abul | -0.784 |
ⓘ | -0.780 |
Token | 't |
Token ID | 470 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
recept | +0.510 |
acht | +0.502 |
xxxxxxxx | +0.482 |
phabet | +0.475 |
ieth | +0.466 |
Neg logit contributions | |
anamo | -0.560 |
DCS | -0.512 |
Salvador | -0.501 |
abul | -0.499 |
ⓘ | -0.494 |
Token | have |
Token ID | 423 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
recept | +0.181 |
acht | +0.177 |
xxxxxxxx | +0.167 |
phabet | +0.166 |
ieth | +0.161 |
Neg logit contributions | |
anamo | -0.285 |
DCS | -0.266 |
Salvador | -0.261 |
abul | -0.259 |
ⓘ | -0.258 |
Token | the |
Token ID | 262 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
recept | +0.327 |
acht | +0.321 |
xxxxxxxx | +0.305 |
phabet | +0.303 |
ieth | +0.295 |
Neg logit contributions | |
anamo | -0.441 |
DCS | -0.410 |
Salvador | -0.401 |
abul | -0.399 |
ⓘ | -0.397 |
Token | PAX |
Token ID | 49742 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
recept | +0.134 |
acht | +0.131 |
xxxxxxxx | +0.124 |
phabet | +0.123 |
ieth | +0.120 |
Neg logit contributions | |
anamo | -0.171 |
DCS | -0.159 |
Salvador | -0.155 |
abul | -0.155 |
ⓘ | -0.154 |
Token | East |
Token ID | 3687 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
anamo | +3.481 |
DCS | +3.263 |
Salvador | +3.210 |
abul | +3.152 |
sole | +3.111 |
Neg logit contributions | |
recept | -2.988 |
acht | -2.933 |
xxxxxxxx | -2.834 |
phabet | -2.833 |
ieth | -2.763 |
Token | app |
Token ID | 598 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
recept | +0.144 |
acht | +0.140 |
xxxxxxxx | +0.133 |
phabet | +0.132 |
ieth | +0.128 |
Neg logit contributions | |
anamo | -0.204 |
DCS | -0.189 |
Salvador | -0.185 |
abul | -0.184 |
ⓘ | -0.184 |
Token | ( |
Token ID | 357 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
anamo | +0.476 |
DCS | +0.442 |
Salvador | +0.432 |
abul | +0.430 |
ⓘ | +0.428 |
Neg logit contributions | |
recept | -0.352 |
acht | -0.344 |
xxxxxxxx | -0.327 |
phabet | -0.325 |
ieth | -0.315 |
Token | iOS |
Token ID | 35742 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
recept | +0.438 |
acht | +0.436 |
xxxxxxxx | +0.421 |
phabet | +0.416 |
ieth | +0.405 |
Neg logit contributions | |
anamo | -0.407 |
DCS | -0.367 |
Salvador | -0.364 |
ⓘ | -0.361 |
abul | -0.359 |
Token | , |
Token ID | 11 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
anamo | +1.065 |
DCS | +0.988 |
Salvador | +0.966 |
abul | +0.961 |
ⓘ | +0.955 |
Neg logit contributions | |
recept | -0.834 |
acht | -0.819 |
xxxxxxxx | -0.780 |
phabet | -0.777 |
ieth | -0.754 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
recept | +0.267 |
acht | +0.261 |
xxxxxxxx | +0.248 |
phabet | +0.245 |
ieth | +0.239 |
Neg logit contributions | |
anamo | -0.362 |
DCS | -0.335 |
Salvador | -0.325 |
abul | -0.325 |
ⓘ | -0.324 |
Token | It |
Token ID | 632 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
recept | +0.339 |
acht | +0.334 |
xxxxxxxx | +0.323 |
phabet | +0.312 |
ieth | +0.309 |
Neg logit contributions | |
anamo | -0.404 |
DCS | -0.367 |
abul | -0.361 |
Salvador | -0.354 |
ⓘ | -0.354 |
Token | 's |
Token ID | 338 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
recept | +0.183 |
acht | +0.181 |
xxxxxxxx | +0.170 |
phabet | +0.168 |
ieth | +0.165 |
Neg logit contributions | |
anamo | -0.271 |
DCS | -0.252 |
Salvador | -0.246 |
abul | -0.245 |
ⓘ | -0.245 |
Token | anim |
Token ID | 2355 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
recept | +0.291 |
acht | +0.286 |
xxxxxxxx | +0.270 |
phabet | +0.268 |
ieth | +0.262 |
Neg logit contributions | |
anamo | -0.364 |
DCS | -0.336 |
abul | -0.326 |
Salvador | -0.326 |
ⓘ | -0.326 |
Token | mediately |
Token ID | 23802 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
anamo | +0.284 |
DCS | +0.261 |
Salvador | +0.255 |
abul | +0.252 |
ⓘ | +0.252 |
Neg logit contributions | |
recept | -0.287 |
acht | -0.283 |
xxxxxxxx | -0.271 |
phabet | -0.270 |
ieth | -0.264 |
Token | identifiable |
Token ID | 34450 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
recept | +0.292 |
acht | +0.287 |
xxxxxxxx | +0.272 |
phabet | +0.272 |
ieth | +0.267 |
Neg logit contributions | |
anamo | -0.323 |
DCS | -0.298 |
Salvador | -0.288 |
ⓘ | -0.288 |
abul | -0.287 |
Token | shri |
Token ID | 35064 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
anamo | +3.543 |
DCS | +3.271 |
Salvador | +3.228 |
abul | +3.200 |
sole | +3.172 |
Neg logit contributions | |
recept | -3.007 |
acht | -2.951 |
phabet | -2.839 |
xxxxxxxx | -2.825 |
ieth | -2.734 |
Token | ek |
Token ID | 988 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
anamo | +1.349 |
DCS | +1.277 |
Salvador | +1.263 |
abul | +1.261 |
ⓘ | +1.250 |
Neg logit contributions | |
recept | -0.335 |
acht | -0.320 |
phabet | -0.289 |
xxxxxxxx | -0.286 |
ieth | -0.264 |
Token | of |
Token ID | 286 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
anamo | +0.074 |
DCS | +0.069 |
Salvador | +0.067 |
abul | +0.067 |
ⓘ | +0.066 |
Neg logit contributions | |
recept | -0.056 |
acht | -0.055 |
xxxxxxxx | -0.052 |
phabet | -0.052 |
ieth | -0.051 |
Token | horror |
Token ID | 9961 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
anamo | +0.250 |
DCS | +0.231 |
abul | +0.223 |
Salvador | +0.222 |
ⓘ | +0.222 |
Neg logit contributions | |
recept | -0.248 |
acht | -0.244 |
xxxxxxxx | -0.233 |
phabet | -0.232 |
ieth | -0.226 |
Token | and |
Token ID | 290 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
anamo | +0.773 |
DCS | +0.719 |
Salvador | +0.700 |
abul | +0.698 |
ⓘ | +0.693 |
Neg logit contributions | |
recept | -0.592 |
acht | -0.583 |
xxxxxxxx | -0.553 |
phabet | -0.550 |
ieth | -0.535 |
Token | ity |
Token ID | 414 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
anamo | +0.725 |
DCS | +0.672 |
Salvador | +0.657 |
abul | +0.654 |
ⓘ | +0.649 |
Neg logit contributions | |
recept | -0.583 |
acht | -0.572 |
xxxxxxxx | -0.545 |
phabet | -0.544 |
ieth | -0.528 |
Token | of |
Token ID | 286 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
recept | +0.162 |
acht | +0.159 |
xxxxxxxx | +0.150 |
phabet | +0.148 |
ieth | +0.144 |
Neg logit contributions | |
anamo | -0.273 |
DCS | -0.255 |
Salvador | -0.250 |
abul | -0.249 |
ⓘ | -0.247 |
Token | it |
Token ID | 340 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
recept | +0.097 |
acht | +0.095 |
xxxxxxxx | +0.091 |
phabet | +0.090 |
ieth | +0.088 |
Neg logit contributions | |
anamo | -0.134 |
DCS | -0.125 |
Salvador | -0.122 |
abul | -0.122 |
ⓘ | -0.121 |
Token | alone |
Token ID | 3436 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
anamo | +0.157 |
DCS | +0.146 |
Salvador | +0.143 |
abul | +0.142 |
ⓘ | +0.141 |
Neg logit contributions | |
recept | -0.119 |
acht | -0.117 |
xxxxxxxx | -0.111 |
phabet | -0.111 |
ieth | -0.108 |
Token | lends |
Token ID | 37733 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
anamo | +1.238 |
DCS | +1.157 |
Salvador | +1.137 |
abul | +1.128 |
ⓘ | +1.124 |
Neg logit contributions | |
recept | -0.841 |
acht | -0.825 |
phabet | -0.788 |
xxxxxxxx | -0.784 |
ieth | -0.754 |
Token | cred |
Token ID | 2600 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
anamo | +0.649 |
DCS | +0.598 |
Salvador | +0.585 |
abul | +0.580 |
ⓘ | +0.576 |
Neg logit contributions | |
recept | -0.646 |
acht | -0.637 |
phabet | -0.609 |
xxxxxxxx | -0.609 |
ieth | -0.592 |
Token | ence |
Token ID | 594 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
anamo | +3.941 |
DCS | +3.712 |
abul | +3.690 |
sole | +3.625 |
Salvador | +3.615 |
Neg logit contributions | |
recept | -2.512 |
acht | -2.472 |
phabet | -2.345 |
xxxxxxxx | -2.283 |
ieth | -2.238 |
Token | to |
Token ID | 284 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
anamo | +0.062 |
DCS | +0.058 |
Salvador | +0.057 |
abul | +0.056 |
ⓘ | +0.056 |
Neg logit contributions | |
recept | -0.043 |
acht | -0.042 |
phabet | -0.040 |
xxxxxxxx | -0.040 |
ieth | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
anamo | +0.328 |
DCS | +0.306 |
Salvador | +0.300 |
abul | +0.297 |
ⓘ | +0.296 |
Neg logit contributions | |
recept | -0.241 |
acht | -0.237 |
xxxxxxxx | -0.225 |
phabet | -0.224 |
ieth | -0.217 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
anamo | +0.136 |
DCS | +0.125 |
abul | +0.123 |
Salvador | +0.122 |
ⓘ | +0.121 |
Neg logit contributions | |
recept | -0.096 |
acht | -0.093 |
xxxxxxxx | -0.088 |
phabet | -0.087 |
ieth | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
recept | +0.140 |
acht | +0.138 |
xxxxxxxx | +0.131 |
phabet | +0.131 |
ieth | +0.127 |
Neg logit contributions | |
anamo | -0.179 |
DCS | -0.166 |
Salvador | -0.163 |
abul | -0.162 |
ⓘ | -0.161 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
recept | +0.136 |
acht | +0.134 |
xxxxxxxx | +0.129 |
phabet | +0.128 |
ieth | +0.126 |
Neg logit contributions | |
anamo | -0.112 |
DCS | -0.101 |
Salvador | -0.098 |
abul | -0.098 |
ⓘ | -0.097 |
Token | boys |
Token ID | 13202 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
anamo | +0.222 |
DCS | +0.202 |
Salvador | +0.199 |
ⓘ | +0.198 |
abul | +0.197 |
Neg logit contributions | |
recept | -0.219 |
acht | -0.218 |
xxxxxxxx | -0.209 |
phabet | -0.207 |
ieth | -0.203 |
Token | beware |
Token ID | 40600 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
recept | +0.400 |
acht | +0.393 |
xxxxxxxx | +0.376 |
phabet | +0.373 |
ieth | +0.365 |
Neg logit contributions | |
anamo | -0.386 |
DCS | -0.355 |
Salvador | -0.345 |
abul | -0.341 |
ⓘ | -0.339 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
anamo | +0.351 |
DCS | +0.327 |
Salvador | +0.321 |
abul | +0.319 |
ⓘ | +0.318 |
Neg logit contributions | |
recept | -0.250 |
acht | -0.245 |
phabet | -0.233 |
xxxxxxxx | -0.232 |
ieth | -0.225 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
recept | +0.107 |
acht | +0.105 |
phabet | +0.100 |
xxxxxxxx | +0.099 |
ieth | +0.096 |
Neg logit contributions | |
anamo | -0.148 |
DCS | -0.139 |
Salvador | -0.136 |
abul | -0.135 |
ⓘ | -0.134 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
anamo | +0.106 |
DCS | +0.100 |
Salvador | +0.098 |
abul | +0.098 |
ⓘ | +0.097 |
Neg logit contributions | |
recept | -0.055 |
acht | -0.054 |
xxxxxxxx | -0.050 |
phabet | -0.050 |
ieth | -0.048 |
Token | : |
Token ID | 25 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
acht | +3.063 |
recept | +3.017 |
xxxxxxxx | +2.987 |
ieth | +2.696 |
phabet | +2.611 |
Neg logit contributions | |
anamo | -6.130 |
abul | -5.448 |
Jagu | -5.366 |
raught | -5.349 |
DCS | -5.349 |
Token | j |
Token ID | 474 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
anamo | +1.112 |
DCS | +1.030 |
Salvador | +1.015 |
abul | +1.001 |
ⓘ | +1.001 |
Neg logit contributions | |
recept | -0.958 |
acht | -0.943 |
phabet | -0.903 |
xxxxxxxx | -0.901 |
ieth | -0.878 |
Token | wt |
Token ID | 46569 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
anamo | +0.034 |
DCS | +0.032 |
Salvador | +0.031 |
abul | +0.031 |
ⓘ | +0.031 |
Neg logit contributions | |
recept | -0.028 |
acht | -0.028 |
xxxxxxxx | -0.026 |
phabet | -0.026 |
ieth | -0.025 |
Token | 0001 |
Token ID | 18005 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
recept | +0.992 |
acht | +0.986 |
xxxxxxxx | +0.936 |
phabet | +0.931 |
ieth | +0.913 |
Neg logit contributions | |
anamo | -1.106 |
DCS | -1.017 |
Salvador | -0.999 |
abul | -0.983 |
ⓘ | -0.982 |
Token | - |
Token ID | 532 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
recept | +0.105 |
acht | +0.103 |
xxxxxxxx | +0.098 |
phabet | +0.098 |
ieth | +0.096 |
Neg logit contributions | |
anamo | -0.113 |
DCS | -0.104 |
Salvador | -0.102 |
abul | -0.101 |
ⓘ | -0.101 |
Token | was |
Token ID | 373 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
recept | +0.053 |
acht | +0.052 |
xxxxxxxx | +0.049 |
phabet | +0.049 |
ieth | +0.048 |
Neg logit contributions | |
anamo | -0.084 |
DCS | -0.079 |
Salvador | -0.077 |
abul | -0.077 |
ⓘ | -0.076 |
Token | about |
Token ID | 546 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
anamo | +0.067 |
DCS | +0.062 |
Salvador | +0.060 |
abul | +0.060 |
ⓘ | +0.060 |
Neg logit contributions | |
recept | -0.054 |
acht | -0.053 |
xxxxxxxx | -0.050 |
phabet | -0.050 |
ieth | -0.049 |
Token | homosexuality |
Token ID | 19822 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
recept | +0.072 |
acht | +0.070 |
xxxxxxxx | +0.067 |
phabet | +0.067 |
ieth | +0.065 |
Neg logit contributions | |
anamo | -0.086 |
DCS | -0.080 |
abul | -0.078 |
Salvador | -0.078 |
ⓘ | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
recept | +0.448 |
acht | +0.438 |
xxxxxxxx | +0.417 |
phabet | +0.411 |
ieth | +0.403 |
Neg logit contributions | |
anamo | -0.604 |
DCS | -0.561 |
abul | -0.546 |
Salvador | -0.544 |
ⓘ | -0.541 |
Token |
|
Token ID | 198 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
recept | +0.126 |
acht | +0.123 |
xxxxxxxx | +0.117 |
phabet | +0.116 |
ieth | +0.113 |
Neg logit contributions | |
anamo | -0.178 |
DCS | -0.166 |
Salvador | -0.163 |
abul | -0.162 |
ⓘ | -0.161 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
anamo | +0.074 |
DCS | +0.068 |
Salvador | +0.067 |
abul | +0.066 |
ⓘ | +0.066 |
Neg logit contributions | |
recept | -0.066 |
acht | -0.065 |
xxxxxxxx | -0.063 |
phabet | -0.062 |
ieth | -0.060 |
Token | : |
Token ID | 25 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
recept | +3.110 |
acht | +3.059 |
xxxxxxxx | +2.836 |
phabet | +2.683 |
ieth | +2.680 |
Neg logit contributions | |
anamo | -5.795 |
DCS | -5.228 |
abul | -5.226 |
raught | -5.087 |
sole | -5.071 |
Token | k |
Token ID | 479 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
anamo | +1.163 |
DCS | +1.076 |
Salvador | +1.061 |
abul | +1.047 |
ⓘ | +1.046 |
Neg logit contributions | |
recept | -1.001 |
acht | -0.986 |
phabet | -0.944 |
xxxxxxxx | -0.942 |
ieth | -0.917 |
Token | imp |
Token ID | 11011 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
recept | +0.252 |
acht | +0.249 |
xxxxxxxx | +0.238 |
phabet | +0.236 |
ieth | +0.231 |
Neg logit contributions | |
anamo | -0.291 |
DCS | -0.269 |
Salvador | -0.263 |
abul | -0.260 |
ⓘ | -0.259 |
Token | unk |
Token ID | 2954 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
anamo | +0.932 |
DCS | +0.863 |
Salvador | +0.842 |
abul | +0.841 |
ⓘ | +0.833 |
Neg logit contributions | |
recept | -0.783 |
acht | -0.763 |
phabet | -0.729 |
xxxxxxxx | -0.729 |
ieth | -0.708 |
Token | rock |
Token ID | 10823 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
anamo | +0.019 |
DCS | +0.018 |
Salvador | +0.017 |
abul | +0.017 |
ⓘ | +0.017 |
Neg logit contributions | |
recept | -0.017 |
acht | -0.017 |
xxxxxxxx | -0.016 |
phabet | -0.016 |
ieth | -0.015 |
Token | iff |
Token ID | 733 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
acht | +0.243 |
recept | +0.241 |
xxxxxxxx | +0.223 |
phabet | +0.221 |
ieth | +0.212 |
Neg logit contributions | |
anamo | -0.700 |
DCS | -0.661 |
Salvador | -0.651 |
ⓘ | -0.644 |
abul | -0.644 |
Token | Tra |
Token ID | 15721 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
recept | +0.165 |
acht | +0.164 |
xxxxxxxx | +0.158 |
phabet | +0.152 |
ieth | +0.146 |
Neg logit contributions | |
anamo | -0.286 |
DCS | -0.265 |
abul | -0.261 |
Salvador | -0.261 |
ⓘ | -0.259 |
Token | x |
Token ID | 87 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
recept | +0.957 |
acht | +0.950 |
xxxxxxxx | +0.915 |
phabet | +0.877 |
ieth | +0.858 |
Neg logit contributions | |
anamo | -1.721 |
DCS | -1.597 |
Salvador | -1.575 |
abul | -1.568 |
ⓘ | -1.553 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
anamo | +0.535 |
DCS | +0.498 |
Salvador | +0.489 |
abul | +0.485 |
ⓘ | +0.483 |
Neg logit contributions | |
recept | -0.383 |
acht | -0.376 |
phabet | -0.358 |
xxxxxxxx | -0.355 |
ieth | -0.345 |
Token |
|
Token ID | 198 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
anamo | +0.197 |
DCS | +0.185 |
Salvador | +0.181 |
abul | +0.179 |
ⓘ | +0.179 |
Neg logit contributions | |
recept | -0.147 |
acht | -0.144 |
phabet | -0.138 |
xxxxxxxx | -0.135 |
ieth | -0.132 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
anamo | +0.463 |
DCS | +0.438 |
Salvador | +0.427 |
abul | +0.427 |
ⓘ | +0.423 |
Neg logit contributions | |
recept | -0.251 |
acht | -0.243 |
phabet | -0.227 |
xxxxxxxx | -0.226 |
ieth | -0.219 |
Token | : |
Token ID | 25 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
acht | +2.951 |
recept | +2.923 |
xxxxxxxx | +2.881 |
ieth | +2.613 |
phabet | +2.544 |
Neg logit contributions | |
anamo | -5.723 |
abul | -5.078 |
DCS | -5.010 |
Jagu | -4.994 |
raught | -4.984 |
Token | V |
Token ID | 569 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
anamo | +1.292 |
DCS | +1.197 |
Salvador | +1.182 |
ⓘ | +1.165 |
abul | +1.164 |
Neg logit contributions | |
recept | -1.110 |
acht | -1.094 |
phabet | -1.047 |
xxxxxxxx | -1.044 |
ieth | -1.018 |
Token | the |
Token ID | 1169 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
recept | +0.320 |
acht | +0.315 |
xxxxxxxx | +0.301 |
phabet | +0.300 |
ieth | +0.293 |
Neg logit contributions | |
anamo | -0.353 |
DCS | -0.326 |
Salvador | -0.319 |
abul | -0.316 |
ⓘ | -0.314 |
Token | Happy |
Token ID | 25082 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
anamo | +0.297 |
DCS | +0.274 |
Salvador | +0.268 |
abul | +0.266 |
ⓘ | +0.264 |
Neg logit contributions | |
recept | -0.280 |
acht | -0.276 |
xxxxxxxx | -0.264 |
phabet | -0.263 |
ieth | -0.256 |
Token | L |
Token ID | 43 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
anamo | +0.775 |
DCS | +0.714 |
Salvador | +0.697 |
abul | +0.693 |
ⓘ | +0.687 |
Neg logit contributions | |
recept | -0.754 |
acht | -0.741 |
xxxxxxxx | -0.709 |
phabet | -0.708 |
ieth | -0.690 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
recept | +0.087 |
acht | +0.086 |
phabet | +0.081 |
xxxxxxxx | +0.081 |
ieth | +0.078 |
Neg logit contributions | |
anamo | -0.141 |
DCS | -0.132 |
Salvador | -0.129 |
abul | -0.129 |
ⓘ | -0.128 |
Token | idea |
Token ID | 2126 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
recept | +1.012 |
acht | +0.983 |
xxxxxxxx | +0.918 |
phabet | +0.897 |
ieth | +0.876 |
Neg logit contributions | |
anamo | -1.873 |
DCS | -1.735 |
abul | -1.693 |
Salvador | -1.689 |
ⓘ | -1.669 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
recept | +0.160 |
acht | +0.157 |
xxxxxxxx | +0.149 |
phabet | +0.148 |
ieth | +0.143 |
Neg logit contributions | |
anamo | -0.250 |
DCS | -0.233 |
Salvador | -0.229 |
abul | -0.228 |
ⓘ | -0.226 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
recept | +0.374 |
acht | +0.366 |
phabet | +0.348 |
xxxxxxxx | +0.346 |
ieth | +0.336 |
Neg logit contributions | |
anamo | -0.482 |
DCS | -0.447 |
Salvador | -0.444 |
ⓘ | -0.437 |
abul | -0.436 |
Token |
|
Token ID | 198 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
recept | +0.295 |
acht | +0.289 |
phabet | +0.275 |
xxxxxxxx | +0.274 |
ieth | +0.266 |
Neg logit contributions | |
anamo | -0.410 |
DCS | -0.383 |
Salvador | -0.375 |
abul | -0.373 |
ⓘ | -0.371 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
recept | +0.082 |
acht | +0.080 |
xxxxxxxx | +0.075 |
phabet | +0.075 |
ieth | +0.072 |
Neg logit contributions | |
anamo | -0.163 |
DCS | -0.154 |
Salvador | -0.151 |
abul | -0.150 |
ⓘ | -0.149 |
Token | : |
Token ID | 25 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
acht | +2.878 |
recept | +2.866 |
xxxxxxxx | +2.803 |
ieth | +2.555 |
phabet | +2.475 |
Neg logit contributions | |
anamo | -5.497 |
abul | -4.900 |
DCS | -4.844 |
raught | -4.803 |
Jagu | -4.796 |
Token | Mike |
Token ID | 4995 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
anamo | +0.855 |
DCS | +0.791 |
Salvador | +0.780 |
abul | +0.769 |
ⓘ | +0.769 |
Neg logit contributions | |
recept | -0.746 |
acht | -0.736 |
phabet | -0.704 |
xxxxxxxx | -0.702 |
ieth | -0.684 |
Token | M |
Token ID | 44 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
anamo | +0.986 |
DCS | +0.912 |
Salvador | +0.891 |
abul | +0.883 |
ⓘ | +0.878 |
Neg logit contributions | |
recept | -0.955 |
acht | -0.937 |
phabet | -0.897 |
xxxxxxxx | -0.895 |
ieth | -0.873 |
Token | anners |
Token ID | 15672 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
recept | +0.111 |
acht | +0.109 |
xxxxxxxx | +0.106 |
phabet | +0.105 |
ieth | +0.103 |
Neg logit contributions | |
anamo | -0.069 |
DCS | -0.062 |
Salvador | -0.060 |
abul | -0.060 |
ⓘ | -0.059 |
Token | - |
Token ID | 532 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
recept | +0.219 |
acht | +0.215 |
phabet | +0.206 |
xxxxxxxx | +0.205 |
ieth | +0.200 |
Neg logit contributions | |
anamo | -0.225 |
DCS | -0.208 |
Salvador | -0.203 |
abul | -0.201 |
ⓘ | -0.200 |
Token | , |
Token ID | 11 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
recept | +0.128 |
acht | +0.126 |
xxxxxxxx | +0.120 |
phabet | +0.119 |
ieth | +0.116 |
Neg logit contributions | |
anamo | -0.177 |
DCS | -0.164 |
Salvador | -0.160 |
abul | -0.160 |
ⓘ | -0.159 |
Token | I |
Token ID | 314 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
anamo | +0.159 |
DCS | +0.148 |
Salvador | +0.146 |
ⓘ | +0.143 |
abul | +0.143 |
Neg logit contributions | |
recept | -0.121 |
acht | -0.120 |
phabet | -0.113 |
xxxxxxxx | -0.113 |
ieth | -0.109 |
Token | think |
Token ID | 892 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
anamo | +0.168 |
DCS | +0.154 |
Salvador | +0.150 |
abul | +0.149 |
ⓘ | +0.148 |
Neg logit contributions | |
recept | -0.169 |
acht | -0.166 |
xxxxxxxx | -0.159 |
phabet | -0.159 |
ieth | -0.155 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
recept | +0.051 |
acht | +0.050 |
xxxxxxxx | +0.048 |
phabet | +0.048 |
ieth | +0.046 |
Neg logit contributions | |
anamo | -0.073 |
DCS | -0.068 |
Salvador | -0.067 |
abul | -0.066 |
ⓘ | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
recept | +0.091 |
acht | +0.089 |
phabet | +0.085 |
xxxxxxxx | +0.084 |
ieth | +0.082 |
Neg logit contributions | |
anamo | -0.123 |
DCS | -0.116 |
Salvador | -0.113 |
abul | -0.112 |
ⓘ | -0.112 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.49e+00 |
Pos logit contributions | |
anamo | +0.218 |
DCS | +0.206 |
Salvador | +0.201 |
abul | +0.201 |
ⓘ | +0.199 |
Neg logit contributions | |
recept | -0.119 |
acht | -0.115 |
xxxxxxxx | -0.107 |
phabet | -0.107 |
ieth | -0.104 |
Token | : |
Token ID | 25 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
acht | +2.824 |
recept | +2.797 |
xxxxxxxx | +2.753 |
ieth | +2.500 |
phabet | +2.436 |
Neg logit contributions | |
anamo | -5.429 |
abul | -4.830 |
DCS | -4.760 |
raught | -4.732 |
Jagu | -4.730 |
Token | B |
Token ID | 347 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
anamo | +1.210 |
DCS | +1.120 |
Salvador | +1.106 |
ⓘ | +1.090 |
abul | +1.089 |
Neg logit contributions | |
recept | -1.051 |
acht | -1.037 |
phabet | -0.993 |
xxxxxxxx | -0.990 |
ieth | -0.965 |
Token | iz |
Token ID | 528 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
anamo | +0.197 |
DCS | +0.183 |
Salvador | +0.178 |
abul | +0.177 |
ⓘ | +0.176 |
Neg logit contributions | |
recept | -0.172 |
acht | -0.169 |
xxxxxxxx | -0.161 |
phabet | -0.161 |
ieth | -0.156 |
Token | r |
Token ID | 81 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
recept | +0.877 |
acht | +0.868 |
xxxxxxxx | +0.832 |
phabet | +0.825 |
ieth | +0.807 |
Neg logit contributions | |
anamo | -0.941 |
DCS | -0.862 |
Salvador | -0.845 |
abul | -0.836 |
ⓘ | -0.834 |
Token | Pix |
Token ID | 21642 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
anamo | +0.134 |
DCS | +0.123 |
Salvador | +0.120 |
abul | +0.120 |
ⓘ | +0.119 |
Neg logit contributions | |
recept | -0.121 |
acht | -0.119 |
xxxxxxxx | -0.114 |
phabet | -0.113 |
ieth | -0.110 |
Token | er |
Token ID | 263 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
recept | +0.887 |
acht | +0.868 |
xxxxxxxx | +0.824 |
phabet | +0.810 |
ieth | +0.788 |
Neg logit contributions | |
anamo | -1.468 |
DCS | -1.368 |
abul | -1.331 |
Salvador | -1.330 |
ⓘ | -1.327 |
Token | magnet |
Token ID | 19972 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
recept | +0.672 |
acht | +0.645 |
xxxxxxxx | +0.611 |
phabet | +0.602 |
ieth | +0.581 |
Neg logit contributions | |
anamo | -1.240 |
DCS | -1.154 |
abul | -1.128 |
Salvador | -1.122 |
ⓘ | -1.112 |
Token | ? |
Token ID | 30 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
anamo | +0.971 |
DCS | +0.903 |
Salvador | +0.888 |
abul | +0.875 |
ⓘ | +0.874 |
Neg logit contributions | |
recept | -0.725 |
acht | -0.716 |
phabet | -0.684 |
xxxxxxxx | -0.673 |
ieth | -0.649 |
Token |
|
Token ID | 198 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
anamo | +0.824 |
DCS | +0.766 |
Salvador | +0.758 |
ⓘ | +0.747 |
abul | +0.744 |
Neg logit contributions | |
recept | -0.598 |
acht | -0.588 |
phabet | -0.557 |
xxxxxxxx | -0.553 |
ieth | -0.538 |
Token |
|
Token ID | 198 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
recept | +0.002 |
acht | +0.002 |
phabet | +0.002 |
xxxxxxxx | +0.002 |
ieth | +0.002 |
Neg logit contributions | |
anamo | -0.003 |
DCS | -0.002 |
Salvador | -0.002 |
abul | -0.002 |
ⓘ | -0.002 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
anamo | +0.219 |
DCS | +0.207 |
Salvador | +0.203 |
abul | +0.202 |
ⓘ | +0.200 |
Neg logit contributions | |
recept | -0.117 |
acht | -0.114 |
phabet | -0.106 |
xxxxxxxx | -0.106 |
ieth | -0.103 |
Token | : |
Token ID | 25 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
acht | +2.781 |
recept | +2.762 |
xxxxxxxx | +2.712 |
ieth | +2.470 |
phabet | +2.401 |
Neg logit contributions | |
anamo | -5.282 |
abul | -4.704 |
DCS | -4.646 |
raught | -4.613 |
Jagu | -4.601 |
Token | hey |
Token ID | 17207 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
anamo | +1.025 |
DCS | +0.948 |
Salvador | +0.935 |
abul | +0.922 |
ⓘ | +0.921 |
Neg logit contributions | |
recept | -0.894 |
acht | -0.882 |
phabet | -0.844 |
xxxxxxxx | -0.842 |
ieth | -0.820 |
Token | _ |
Token ID | 62 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
recept | +0.703 |
acht | +0.694 |
xxxxxxxx | +0.664 |
phabet | +0.659 |
ieth | +0.644 |
Neg logit contributions | |
anamo | -0.793 |
DCS | -0.731 |
Salvador | -0.716 |
abul | -0.707 |
ⓘ | -0.706 |
Token | ler |
Token ID | 1754 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
recept | +0.810 |
acht | +0.802 |
xxxxxxxx | +0.768 |
phabet | +0.761 |
ieth | +0.743 |
Neg logit contributions | |
anamo | -0.898 |
DCS | -0.827 |
Salvador | -0.811 |
abul | -0.801 |
ⓘ | -0.800 |
Token | oy |
Token ID | 726 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
recept | +0.171 |
acht | +0.168 |
xxxxxxxx | +0.160 |
phabet | +0.159 |
ieth | +0.155 |
Neg logit contributions | |
anamo | -0.208 |
DCS | -0.193 |
Salvador | -0.189 |
abul | -0.187 |
ⓘ | -0.186 |
Token | after |
Token ID | 706 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
recept | +0.874 |
acht | +0.858 |
xxxxxxxx | +0.811 |
phabet | +0.811 |
ieth | +0.784 |
Neg logit contributions | |
anamo | -1.198 |
DCS | -1.112 |
Salvador | -1.082 |
abul | -1.081 |
ⓘ | -1.073 |
Token | a |
Token ID | 257 |
Feature activation | -8.92e-02 |
Pos logit contributions | |
anamo | +0.531 |
DCS | +0.491 |
Salvador | +0.479 |
abul | +0.477 |
ⓘ | +0.473 |
Neg logit contributions | |
recept | -0.474 |
acht | -0.465 |
xxxxxxxx | -0.444 |
phabet | -0.443 |
ieth | -0.432 |
Token | model |
Token ID | 2746 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
recept | +0.066 |
acht | +0.064 |
xxxxxxxx | +0.061 |
phabet | +0.061 |
ieth | +0.060 |
Neg logit contributions | |
anamo | -0.068 |
DCS | -0.062 |
abul | -0.061 |
Salvador | -0.059 |
ⓘ | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
recept | +0.360 |
acht | +0.351 |
xxxxxxxx | +0.332 |
phabet | +0.330 |
ieth | +0.325 |
Neg logit contributions | |
anamo | -0.488 |
DCS | -0.453 |
abul | -0.439 |
Salvador | -0.438 |
ⓘ | -0.437 |
Token | Pont |
Token ID | 26345 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
recept | +0.167 |
acht | +0.163 |
xxxxxxxx | +0.155 |
phabet | +0.154 |
ieth | +0.151 |
Neg logit contributions | |
anamo | -0.193 |
DCS | -0.178 |
abul | -0.173 |
Salvador | -0.171 |
ⓘ | -0.171 |
Token | iac |
Token ID | 9607 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
recept | +1.541 |
acht | +1.519 |
phabet | +1.410 |
xxxxxxxx | +1.398 |
ieth | +1.365 |
Neg logit contributions | |
anamo | -2.897 |
DCS | -2.734 |
Salvador | -2.675 |
abul | -2.659 |
ⓘ | -2.643 |
Token | GT |
Token ID | 7963 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
recept | +3.600 |
acht | +3.546 |
phabet | +3.304 |
xxxxxxxx | +3.260 |
ieth | +3.256 |
Neg logit contributions | |
anamo | -4.107 |
DCS | -3.753 |
abul | -3.683 |
Salvador | -3.602 |
ⓘ | -3.571 |
Token | O |
Token ID | 46 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
anamo | +0.641 |
DCS | +0.593 |
Salvador | +0.579 |
abul | +0.577 |
ⓘ | +0.574 |
Neg logit contributions | |
recept | -0.530 |
acht | -0.520 |
xxxxxxxx | -0.495 |
phabet | -0.493 |
ieth | -0.481 |
Token | sold |
Token ID | 2702 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
recept | +0.849 |
acht | +0.831 |
xxxxxxxx | +0.785 |
phabet | +0.781 |
ieth | +0.762 |
Neg logit contributions | |
anamo | -1.039 |
DCS | -0.959 |
abul | -0.935 |
Salvador | -0.929 |
ⓘ | -0.925 |
Token | from |
Token ID | 422 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
recept | +1.202 |
acht | +1.181 |
xxxxxxxx | +1.111 |
phabet | +1.109 |
ieth | +1.087 |
Neg logit contributions | |
anamo | -1.708 |
DCS | -1.592 |
ⓘ | -1.538 |
Salvador | -1.537 |
abul | -1.537 |
Token | 1969 |
Token ID | 16450 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
recept | +0.492 |
acht | +0.485 |
xxxxxxxx | +0.464 |
phabet | +0.461 |
ieth | +0.453 |
Neg logit contributions | |
anamo | -0.390 |
DCS | -0.354 |
abul | -0.342 |
Salvador | -0.338 |
ⓘ | -0.335 |
Token | are |
Token ID | 389 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
recept | +0.829 |
acht | +0.793 |
xxxxxxxx | +0.754 |
phabet | +0.731 |
ieth | +0.715 |
Neg logit contributions | |
anamo | -1.546 |
DCS | -1.433 |
abul | -1.402 |
ⓘ | -1.399 |
Salvador | -1.393 |
Token | Here |
Token ID | 3423 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
anamo | +0.682 |
DCS | +0.634 |
Salvador | +0.630 |
ⓘ | +0.623 |
abul | +0.620 |
Neg logit contributions | |
recept | -0.430 |
acht | -0.422 |
phabet | -0.399 |
xxxxxxxx | -0.395 |
ieth | -0.387 |
Token | .... |
Token ID | 1106 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
recept | +0.289 |
acht | +0.284 |
xxxxxxxx | +0.273 |
phabet | +0.272 |
ieth | +0.266 |
Neg logit contributions | |
anamo | -0.255 |
DCS | -0.233 |
Salvador | -0.227 |
abul | -0.226 |
ⓘ | -0.224 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
anamo | +0.287 |
DCS | +0.267 |
Salvador | +0.264 |
ⓘ | +0.260 |
abul | +0.260 |
Neg logit contributions | |
recept | -0.202 |
acht | -0.198 |
xxxxxxxx | -0.186 |
phabet | -0.186 |
ieth | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
recept | +0.200 |
acht | +0.196 |
phabet | +0.186 |
xxxxxxxx | +0.185 |
ieth | +0.180 |
Neg logit contributions | |
anamo | -0.278 |
DCS | -0.259 |
Salvador | -0.254 |
abul | -0.252 |
ⓘ | -0.251 |
Token | Reviewer |
Token ID | 35407 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
recept | +0.055 |
acht | +0.054 |
xxxxxxxx | +0.050 |
phabet | +0.050 |
ieth | +0.048 |
Neg logit contributions | |
anamo | -0.106 |
DCS | -0.100 |
Salvador | -0.098 |
abul | -0.097 |
ⓘ | -0.097 |
Token | : |
Token ID | 25 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
acht | +2.686 |
recept | +2.670 |
xxxxxxxx | +2.614 |
ieth | +2.394 |
phabet | +2.335 |
Neg logit contributions | |
anamo | -5.013 |
abul | -4.470 |
DCS | -4.423 |
raught | -4.386 |
Jagu | -4.364 |
Token | SAS |
Token ID | 35516 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
anamo | +0.703 |
DCS | +0.649 |
Salvador | +0.640 |
abul | +0.631 |
ⓘ | +0.630 |
Neg logit contributions | |
recept | -0.626 |
acht | -0.617 |
phabet | -0.590 |
xxxxxxxx | -0.589 |
ieth | -0.574 |
Token | K |
Token ID | 42 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
recept | +0.640 |
acht | +0.630 |
xxxxxxxx | +0.605 |
phabet | +0.601 |
ieth | +0.588 |
Neg logit contributions | |
anamo | -0.653 |
DCS | -0.600 |
Salvador | -0.586 |
abul | -0.581 |
ⓘ | -0.579 |
Token | ATCH |
Token ID | 11417 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
recept | +0.100 |
acht | +0.099 |
xxxxxxxx | +0.095 |
phabet | +0.094 |
ieth | +0.092 |
Neg logit contributions | |
anamo | -0.103 |
DCS | -0.094 |
Salvador | -0.092 |
abul | -0.091 |
ⓘ | -0.091 |
Token | EW |
Token ID | 6217 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
anamo | +1.222 |
DCS | +1.134 |
Salvador | +1.105 |
abul | +1.096 |
ⓘ | +1.090 |
Neg logit contributions | |
recept | -1.115 |
acht | -1.095 |
phabet | -1.047 |
xxxxxxxx | -1.044 |
ieth | -1.015 |
Token | security |
Token ID | 12961 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
recept | +0.126 |
acht | +0.125 |
xxxxxxxx | +0.120 |
phabet | +0.119 |
ieth | +0.117 |
Neg logit contributions | |
anamo | -0.089 |
DCS | -0.080 |
Salvador | -0.078 |
abul | -0.077 |
ⓘ | -0.077 |
Token | inmate |
Token ID | 28414 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
anamo | +0.366 |
DCS | +0.335 |
Salvador | +0.324 |
abul | +0.323 |
ⓘ | +0.321 |
Neg logit contributions | |
recept | -0.412 |
acht | -0.405 |
xxxxxxxx | -0.388 |
phabet | -0.387 |
ieth | -0.378 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
recept | +0.477 |
acht | +0.466 |
xxxxxxxx | +0.441 |
phabet | +0.439 |
ieth | +0.425 |
Neg logit contributions | |
anamo | -0.689 |
DCS | -0.642 |
Salvador | -0.624 |
abul | -0.624 |
ⓘ | -0.621 |
Token | transferred |
Token ID | 11172 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
recept | +0.009 |
acht | +0.009 |
xxxxxxxx | +0.008 |
phabet | +0.008 |
ieth | +0.008 |
Neg logit contributions | |
anamo | -0.012 |
DCS | -0.011 |
abul | -0.011 |
Salvador | -0.011 |
ⓘ | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
anamo | +1.039 |
DCS | +0.970 |
Salvador | +0.948 |
abul | +0.946 |
ⓘ | +0.940 |
Neg logit contributions | |
recept | -0.673 |
acht | -0.658 |
xxxxxxxx | -0.622 |
phabet | -0.619 |
ieth | -0.598 |
Token | Bow |
Token ID | 9740 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
anamo | +0.373 |
DCS | +0.345 |
Salvador | +0.336 |
abul | +0.335 |
ⓘ | +0.333 |
Neg logit contributions | |
recept | -0.320 |
acht | -0.314 |
xxxxxxxx | -0.299 |
phabet | -0.298 |
ieth | -0.290 |
Token | den |
Token ID | 6559 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
acht | +3.468 |
recept | +3.417 |
xxxxxxxx | +3.191 |
phabet | +3.180 |
ieth | +3.127 |
Neg logit contributions | |
anamo | -3.773 |
DCS | -3.564 |
Salvador | -3.511 |
abul | -3.504 |
ⓘ | -3.433 |
Token | Institution |
Token ID | 29426 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
anamo | +0.606 |
DCS | +0.562 |
Salvador | +0.549 |
abul | +0.547 |
ⓘ | +0.543 |
Neg logit contributions | |
recept | -0.485 |
acht | -0.476 |
xxxxxxxx | -0.453 |
phabet | -0.452 |
ieth | -0.439 |
Token | in |
Token ID | 287 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
anamo | +0.350 |
DCS | +0.326 |
Salvador | +0.318 |
abul | +0.317 |
ⓘ | +0.315 |
Neg logit contributions | |
recept | -0.252 |
acht | -0.248 |
xxxxxxxx | -0.234 |
phabet | -0.234 |
ieth | -0.227 |
Token | central |
Token ID | 4318 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
anamo | +0.044 |
DCS | +0.040 |
abul | +0.038 |
Salvador | +0.038 |
ⓘ | +0.038 |
Neg logit contributions | |
recept | -0.048 |
acht | -0.047 |
xxxxxxxx | -0.045 |
phabet | -0.045 |
ieth | -0.044 |
Token | Alberta |
Token ID | 15555 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
anamo | +0.891 |
DCS | +0.816 |
Salvador | +0.795 |
abul | +0.789 |
ⓘ | +0.783 |
Neg logit contributions | |
recept | -0.975 |
acht | -0.959 |
xxxxxxxx | -0.921 |
phabet | -0.918 |
ieth | -0.897 |
Token | practice |
Token ID | 3357 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
anamo | +0.324 |
DCS | +0.300 |
Salvador | +0.293 |
abul | +0.292 |
ⓘ | +0.290 |
Neg logit contributions | |
recept | -0.276 |
acht | -0.271 |
xxxxxxxx | -0.259 |
phabet | -0.258 |
ieth | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | -9.18e-02 |
Pos logit contributions | |
anamo | +0.431 |
DCS | +0.402 |
Salvador | +0.397 |
abul | +0.393 |
ⓘ | +0.391 |
Neg logit contributions | |
recept | -0.307 |
acht | -0.301 |
xxxxxxxx | -0.287 |
phabet | -0.287 |
ieth | -0.277 |
Token |
|
Token ID | 198 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
recept | +0.058 |
acht | +0.057 |
phabet | +0.054 |
xxxxxxxx | +0.054 |
ieth | +0.053 |
Neg logit contributions | |
anamo | -0.078 |
DCS | -0.073 |
Salvador | -0.072 |
ⓘ | -0.071 |
abul | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
recept | +0.238 |
acht | +0.233 |
xxxxxxxx | +0.222 |
phabet | +0.220 |
ieth | +0.214 |
Neg logit contributions | |
anamo | -0.344 |
DCS | -0.319 |
Salvador | -0.313 |
abul | -0.311 |
ⓘ | -0.309 |
Token | The |
Token ID | 464 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
recept | +0.100 |
acht | +0.098 |
xxxxxxxx | +0.094 |
phabet | +0.093 |
ieth | +0.091 |
Neg logit contributions | |
anamo | -0.112 |
DCS | -0.103 |
Salvador | -0.101 |
abul | -0.100 |
ⓘ | -0.099 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
recept | +0.287 |
acht | +0.280 |
xxxxxxxx | +0.267 |
phabet | +0.265 |
ieth | +0.258 |
Neg logit contributions | |
anamo | -0.339 |
DCS | -0.315 |
abul | -0.305 |
Salvador | -0.304 |
ⓘ | -0.301 |
Token | do |
Token ID | 4598 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
acht | +3.879 |
recept | +3.756 |
xxxxxxxx | +3.671 |
phabet | +3.592 |
ieth | +3.492 |
Neg logit contributions | |
anamo | -3.325 |
DCS | -3.007 |
abul | -2.961 |
Salvador | -2.954 |
Jagu | -2.897 |
Token | in |
Token ID | 259 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
anamo | +0.697 |
DCS | +0.643 |
Salvador | +0.628 |
abul | +0.624 |
ⓘ | +0.620 |
Neg logit contributions | |
recept | -0.639 |
acht | -0.628 |
xxxxxxxx | -0.600 |
phabet | -0.599 |
ieth | -0.583 |
Token | student |
Token ID | 3710 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
anamo | +0.401 |
DCS | +0.369 |
Salvador | +0.360 |
abul | +0.358 |
ⓘ | +0.355 |
Neg logit contributions | |
recept | -0.384 |
acht | -0.377 |
xxxxxxxx | -0.360 |
phabet | -0.359 |
ieth | -0.351 |
Token | newspaper |
Token ID | 7533 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
recept | +0.173 |
acht | +0.169 |
xxxxxxxx | +0.160 |
phabet | +0.160 |
ieth | +0.155 |
Neg logit contributions | |
anamo | -0.249 |
DCS | -0.232 |
Salvador | -0.226 |
abul | -0.225 |
ⓘ | -0.224 |
Token | reports |
Token ID | 3136 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
anamo | +0.243 |
DCS | +0.225 |
Salvador | +0.220 |
abul | +0.219 |
ⓘ | +0.217 |
Neg logit contributions | |
recept | -0.201 |
acht | -0.198 |
xxxxxxxx | -0.188 |
phabet | -0.187 |
ieth | -0.182 |
Token | row |
Token ID | 5752 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
recept | +0.135 |
acht | +0.131 |
xxxxxxxx | +0.124 |
phabet | +0.123 |
ieth | +0.121 |
Neg logit contributions | |
anamo | -0.161 |
DCS | -0.148 |
abul | -0.144 |
Salvador | -0.142 |
ⓘ | -0.142 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
anamo | +0.362 |
DCS | +0.338 |
Salvador | +0.332 |
abul | +0.330 |
ⓘ | +0.328 |
Neg logit contributions | |
recept | -0.225 |
acht | -0.219 |
xxxxxxxx | -0.208 |
phabet | -0.207 |
ieth | -0.200 |
Token | which |
Token ID | 543 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
anamo | +0.002 |
DCS | +0.001 |
Salvador | +0.001 |
abul | +0.001 |
ⓘ | +0.001 |
Neg logit contributions | |
recept | -0.001 |
acht | -0.001 |
xxxxxxxx | -0.001 |
phabet | -0.001 |
ieth | -0.001 |
Token | erupted |
Token ID | 23681 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
anamo | +0.185 |
DCS | +0.173 |
Salvador | +0.170 |
abul | +0.169 |
ⓘ | +0.168 |
Neg logit contributions | |
recept | -0.105 |
acht | -0.103 |
xxxxxxxx | -0.097 |
phabet | -0.097 |
ieth | -0.093 |
Token | at |
Token ID | 379 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
recept | +0.235 |
acht | +0.230 |
xxxxxxxx | +0.217 |
phabet | +0.216 |
ieth | +0.210 |
Neg logit contributions | |
anamo | -0.341 |
DCS | -0.317 |
Salvador | -0.309 |
abul | -0.309 |
ⓘ | -0.306 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
recept | +0.240 |
acht | +0.236 |
xxxxxxxx | +0.224 |
phabet | +0.223 |
ieth | +0.219 |
Neg logit contributions | |
anamo | -0.271 |
DCS | -0.250 |
abul | -0.243 |
Salvador | -0.241 |
ⓘ | -0.239 |
Token | do |
Token ID | 4598 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
acht | +3.501 |
recept | +3.454 |
xxxxxxxx | +3.239 |
phabet | +3.213 |
ieth | +3.188 |
Neg logit contributions | |
anamo | -3.582 |
DCS | -3.313 |
abul | -3.285 |
Salvador | -3.265 |
ⓘ | -3.202 |
Token | in |
Token ID | 259 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
anamo | +0.631 |
DCS | +0.583 |
Salvador | +0.570 |
abul | +0.565 |
ⓘ | +0.563 |
Neg logit contributions | |
recept | -0.595 |
acht | -0.585 |
xxxxxxxx | -0.559 |
phabet | -0.558 |
ieth | -0.543 |
Token | College |
Token ID | 5535 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
anamo | +0.303 |
DCS | +0.277 |
Salvador | +0.269 |
abul | +0.268 |
ⓘ | +0.265 |
Neg logit contributions | |
recept | -0.318 |
acht | -0.314 |
xxxxxxxx | -0.300 |
phabet | -0.299 |
ieth | -0.293 |
Token | , |
Token ID | 11 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
anamo | +1.764 |
DCS | +1.642 |
Salvador | +1.613 |
abul | +1.601 |
ⓘ | +1.593 |
Neg logit contributions | |
recept | -1.328 |
acht | -1.301 |
xxxxxxxx | -1.244 |
phabet | -1.239 |
ieth | -1.200 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
anamo | +0.126 |
DCS | +0.118 |
Salvador | +0.115 |
abul | +0.115 |
ⓘ | +0.114 |
Neg logit contributions | |
recept | -0.081 |
acht | -0.079 |
xxxxxxxx | -0.075 |
phabet | -0.074 |
ieth | -0.072 |
Token | to |
Token ID | 284 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
anamo | +1.417 |
DCS | +1.317 |
Salvador | +1.308 |
abul | +1.293 |
ⓘ | +1.286 |
Neg logit contributions | |
recept | -1.006 |
acht | -0.985 |
phabet | -0.943 |
xxxxxxxx | -0.940 |
ieth | -0.913 |
Token | gain |
Token ID | 4461 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
anamo | +0.231 |
DCS | +0.214 |
Salvador | +0.209 |
abul | +0.208 |
ⓘ | +0.206 |
Neg logit contributions | |
recept | -0.197 |
acht | -0.193 |
xxxxxxxx | -0.184 |
phabet | -0.184 |
ieth | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
anamo | +0.141 |
DCS | +0.131 |
Salvador | +0.128 |
abul | +0.127 |
ⓘ | +0.126 |
Neg logit contributions | |
recept | -0.115 |
acht | -0.113 |
xxxxxxxx | -0.107 |
phabet | -0.107 |
ieth | -0.104 |
Token | release |
Token ID | 2650 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
anamo | +0.016 |
DCS | +0.015 |
abul | +0.015 |
Salvador | +0.015 |
ⓘ | +0.014 |
Neg logit contributions | |
recept | -0.016 |
acht | -0.015 |
xxxxxxxx | -0.014 |
phabet | -0.014 |
ieth | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
anamo | +0.222 |
DCS | +0.207 |
Salvador | +0.205 |
abul | +0.203 |
ⓘ | +0.202 |
Neg logit contributions | |
recept | -0.133 |
acht | -0.131 |
xxxxxxxx | -0.123 |
phabet | -0.122 |
ieth | -0.119 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
anamo | +0.069 |
DCS | +0.063 |
abul | +0.061 |
Salvador | +0.061 |
ⓘ | +0.060 |
Neg logit contributions | |
recept | -0.072 |
acht | -0.071 |
xxxxxxxx | -0.068 |
phabet | -0.068 |
ieth | -0.066 |
Token | e |
Token ID | 68 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
acht | +3.112 |
recept | +3.110 |
xxxxxxxx | +2.918 |
phabet | +2.892 |
ieth | +2.793 |
Neg logit contributions | |
anamo | -4.025 |
DCS | -3.753 |
Salvador | -3.659 |
abul | -3.647 |
ⓘ | -3.606 |
Token | Ber |
Token ID | 4312 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
anamo | +0.187 |
Salvador | +0.169 |
DCS | +0.169 |
ⓘ | +0.168 |
abul | +0.166 |
Neg logit contributions | |
recept | -0.153 |
acht | -0.149 |
phabet | -0.146 |
xxxxxxxx | -0.143 |
ieth | -0.140 |
Token | gd |
Token ID | 21287 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
recept | +0.388 |
acht | +0.377 |
phabet | +0.367 |
xxxxxxxx | +0.364 |
ieth | +0.352 |
Neg logit contributions | |
anamo | -0.472 |
DCS | -0.437 |
Salvador | -0.426 |
abul | -0.426 |
ⓘ | -0.420 |
Token | ahl |
Token ID | 15668 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
anamo | +0.713 |
DCS | +0.649 |
Salvador | +0.631 |
abul | +0.626 |
ⓘ | +0.621 |
Neg logit contributions | |
recept | -0.893 |
acht | -0.880 |
xxxxxxxx | -0.847 |
phabet | -0.845 |
ieth | -0.826 |
Token | had |
Token ID | 550 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
recept | +0.586 |
acht | +0.577 |
xxxxxxxx | +0.554 |
phabet | +0.552 |
ieth | +0.538 |
Neg logit contributions | |
anamo | -0.547 |
DCS | -0.502 |
Salvador | -0.487 |
abul | -0.485 |
ⓘ | -0.482 |
Token | box |
Token ID | 3524 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
recept | +0.493 |
acht | +0.476 |
xxxxxxxx | +0.438 |
phabet | +0.436 |
ieth | +0.416 |
Neg logit contributions | |
anamo | -1.294 |
DCS | -1.223 |
Salvador | -1.201 |
abul | -1.196 |
ⓘ | -1.190 |
Token | of |
Token ID | 286 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
anamo | +2.182 |
DCS | +2.039 |
Salvador | +2.029 |
ⓘ | +1.991 |
abul | +1.986 |
Neg logit contributions | |
recept | -1.481 |
acht | -1.479 |
phabet | -1.423 |
xxxxxxxx | -1.406 |
ieth | -1.364 |
Token | our |
Token ID | 674 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
recept | +0.015 |
acht | +0.014 |
xxxxxxxx | +0.014 |
phabet | +0.014 |
ieth | +0.013 |
Neg logit contributions | |
anamo | -0.018 |
DCS | -0.017 |
Salvador | -0.016 |
abul | -0.016 |
ⓘ | -0.016 |
Token | old |
Token ID | 1468 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
anamo | +0.186 |
DCS | +0.172 |
Salvador | +0.168 |
abul | +0.168 |
ⓘ | +0.167 |
Neg logit contributions | |
recept | -0.139 |
acht | -0.136 |
xxxxxxxx | -0.130 |
phabet | -0.129 |
ieth | -0.125 |
Token | Pont |
Token ID | 26345 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
anamo | +0.056 |
DCS | +0.052 |
Salvador | +0.050 |
abul | +0.050 |
ⓘ | +0.050 |
Neg logit contributions | |
recept | -0.045 |
acht | -0.044 |
xxxxxxxx | -0.042 |
phabet | -0.042 |
ieth | -0.041 |
Token | iac |
Token ID | 9607 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
recept | +1.398 |
acht | +1.367 |
xxxxxxxx | +1.265 |
phabet | +1.261 |
ieth | +1.217 |
Neg logit contributions | |
anamo | -2.937 |
DCS | -2.767 |
Salvador | -2.716 |
abul | -2.703 |
ⓘ | -2.681 |
Token | Bon |
Token ID | 7979 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
recept | +3.433 |
acht | +3.394 |
xxxxxxxx | +3.189 |
phabet | +3.163 |
ieth | +3.111 |
Neg logit contributions | |
anamo | -3.728 |
DCS | -3.410 |
abul | -3.326 |
Salvador | -3.271 |
sole | -3.254 |
Token | ne |
Token ID | 710 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
anamo | +0.757 |
DCS | +0.696 |
Salvador | +0.683 |
abul | +0.676 |
ⓘ | +0.672 |
Neg logit contributions | |
recept | -0.712 |
acht | -0.699 |
xxxxxxxx | -0.669 |
phabet | -0.667 |
ieth | -0.651 |
Token | ville |
Token ID | 4244 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
recept | +1.298 |
acht | +1.273 |
xxxxxxxx | +1.222 |
phabet | +1.219 |
ieth | +1.171 |
Neg logit contributions | |
anamo | -1.209 |
DCS | -1.129 |
abul | -1.082 |
Salvador | -1.074 |
ⓘ | -1.053 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
recept | +0.144 |
acht | +0.142 |
xxxxxxxx | +0.135 |
phabet | +0.135 |
ieth | +0.131 |
Neg logit contributions | |
anamo | -0.169 |
DCS | -0.156 |
Salvador | -0.153 |
abul | -0.152 |
ⓘ | -0.151 |
Token | Sally |
Token ID | 25737 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
recept | +0.202 |
acht | +0.198 |
xxxxxxxx | +0.191 |
phabet | +0.187 |
ieth | +0.183 |
Neg logit contributions | |
anamo | -0.251 |
DCS | -0.230 |
abul | -0.225 |
Salvador | -0.223 |
ⓘ | -0.221 |
Token | follows |
Token ID | 5679 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
recept | +0.287 |
acht | +0.282 |
xxxxxxxx | +0.267 |
phabet | +0.267 |
ieth | +0.259 |
Neg logit contributions | |
anamo | -0.400 |
DCS | -0.372 |
Salvador | -0.365 |
abul | -0.362 |
ⓘ | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
recept | +1.652 |
acht | +1.610 |
xxxxxxxx | +1.533 |
phabet | +1.523 |
ieth | +1.472 |
Neg logit contributions | |
anamo | -2.351 |
DCS | -2.183 |
abul | -2.127 |
Salvador | -2.120 |
ⓘ | -2.113 |
Token |
|
Token ID | 198 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
recept | +0.281 |
acht | +0.276 |
xxxxxxxx | +0.262 |
phabet | +0.261 |
ieth | +0.254 |
Neg logit contributions | |
anamo | -0.387 |
DCS | -0.360 |
Salvador | -0.353 |
abul | -0.351 |
ⓘ | -0.348 |
Token |
|
Token ID | 198 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
recept | +0.301 |
acht | +0.295 |
xxxxxxxx | +0.281 |
phabet | +0.278 |
ieth | +0.270 |
Neg logit contributions | |
anamo | -0.437 |
DCS | -0.406 |
Salvador | -0.398 |
abul | -0.396 |
ⓘ | -0.393 |
Token | # |
Token ID | 2 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
recept | +0.221 |
acht | +0.217 |
xxxxxxxx | +0.207 |
phabet | +0.206 |
ieth | +0.200 |
Neg logit contributions | |
anamo | -0.278 |
DCS | -0.258 |
Salvador | -0.252 |
abul | -0.251 |
ⓘ | -0.249 |
Token | !/ |
Token ID | 48443 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
anamo | +0.118 |
DCS | +0.111 |
Salvador | +0.109 |
abul | +0.108 |
ⓘ | +0.108 |
Neg logit contributions | |
recept | -0.059 |
acht | -0.058 |
xxxxxxxx | -0.054 |
phabet | -0.054 |
ieth | -0.052 |
Token | bin |
Token ID | 8800 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
recept | +2.259 |
acht | +2.221 |
xxxxxxxx | +2.148 |
phabet | +1.986 |
ieth | +1.904 |
Neg logit contributions | |
anamo | -4.750 |
DCS | -4.422 |
ⓘ | -4.392 |
Salvador | -4.332 |
abul | -4.307 |
Token | / |
Token ID | 14 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
recept | +0.379 |
acht | +0.372 |
xxxxxxxx | +0.355 |
phabet | +0.345 |
ieth | +0.335 |
Neg logit contributions | |
anamo | -0.606 |
DCS | -0.564 |
Salvador | -0.550 |
abul | -0.550 |
ⓘ | -0.546 |
Token | sh |
Token ID | 1477 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
recept | +2.691 |
acht | +2.674 |
xxxxxxxx | +2.573 |
phabet | +2.531 |
ieth | +2.481 |
Neg logit contributions | |
anamo | -2.294 |
DCS | -2.078 |
Salvador | -2.038 |
abul | -2.018 |
ⓘ | -2.005 |
Token | / |
Token ID | 1220 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
anamo | +0.811 |
DCS | +0.753 |
Salvador | +0.738 |
abul | +0.732 |
ⓘ | +0.727 |
Neg logit contributions | |
recept | -0.656 |
acht | -0.646 |
phabet | -0.616 |
xxxxxxxx | -0.616 |
ieth | -0.601 |
Token | s |
Token ID | 82 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
recept | +2.076 |
acht | +2.020 |
xxxxxxxx | +1.950 |
phabet | +1.878 |
ieth | +1.808 |
Neg logit contributions | |
anamo | -3.038 |
DCS | -2.779 |
Salvador | -2.738 |
abul | -2.734 |
ⓘ | -2.721 |
Token | [ |
Token ID | 685 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
recept | +0.881 |
acht | +0.864 |
xxxxxxxx | +0.821 |
phabet | +0.818 |
ieth | +0.794 |
Neg logit contributions | |
anamo | -1.206 |
DCS | -1.122 |
Salvador | -1.098 |
abul | -1.092 |
ⓘ | -1.085 |
Token | Event |
Token ID | 9237 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
recept | +0.389 |
acht | +0.384 |
xxxxxxxx | +0.370 |
phabet | +0.366 |
ieth | +0.356 |
Neg logit contributions | |
anamo | -0.436 |
DCS | -0.397 |
Salvador | -0.389 |
abul | -0.387 |
ⓘ | -0.386 |
Token | " |
Token ID | 366 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
recept | +0.172 |
acht | +0.166 |
xxxxxxxx | +0.159 |
phabet | +0.157 |
ieth | +0.152 |
Neg logit contributions | |
anamo | -0.207 |
DCS | -0.192 |
ⓘ | -0.186 |
Salvador | -0.185 |
abul | -0.183 |
Token | 78 |
Token ID | 3695 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
recept | +0.296 |
acht | +0.292 |
xxxxxxxx | +0.281 |
phabet | +0.279 |
ieth | +0.272 |
Neg logit contributions | |
anamo | -0.293 |
DCS | -0.266 |
Salvador | -0.262 |
abul | -0.260 |
ⓘ | -0.258 |
Token | th |
Token ID | 400 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
recept | +0.438 |
acht | +0.431 |
xxxxxxxx | +0.412 |
phabet | +0.410 |
ieth | +0.400 |
Neg logit contributions | |
anamo | -0.535 |
DCS | -0.491 |
Salvador | -0.479 |
abul | -0.479 |
ⓘ | -0.475 |
Token | Tata |
Token ID | 49963 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
recept | +0.456 |
acht | +0.448 |
xxxxxxxx | +0.431 |
phabet | +0.428 |
ieth | +0.420 |
Neg logit contributions | |
anamo | -0.444 |
DCS | -0.403 |
abul | -0.393 |
Salvador | -0.392 |
ⓘ | -0.387 |
Token | Steel |
Token ID | 7851 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
acht | +3.356 |
recept | +3.314 |
ieth | +3.199 |
xxxxxxxx | +3.199 |
phabet | +3.142 |
Neg logit contributions | |
anamo | -3.673 |
DCS | -3.211 |
abul | -3.195 |
sole | -3.157 |
Salvador | -3.140 |
Token | Chess |
Token ID | 25774 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
recept | +0.785 |
acht | +0.774 |
xxxxxxxx | +0.739 |
phabet | +0.736 |
ieth | +0.722 |
Neg logit contributions | |
anamo | -0.806 |
DCS | -0.735 |
Salvador | -0.718 |
abul | -0.715 |
ⓘ | -0.706 |
Token | Chall |
Token ID | 10772 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anamo | +0.270 |
DCS | +0.249 |
Salvador | +0.243 |
abul | +0.241 |
ⓘ | +0.239 |
Neg logit contributions | |
recept | -0.272 |
acht | -0.268 |
xxxxxxxx | -0.257 |
phabet | -0.256 |
ieth | -0.250 |
Token | engers |
Token ID | 9302 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
recept | +0.867 |
acht | +0.863 |
xxxxxxxx | +0.819 |
phabet | +0.814 |
ieth | +0.810 |
Neg logit contributions | |
anamo | -0.809 |
DCS | -0.733 |
Salvador | -0.713 |
abul | -0.710 |
ⓘ | -0.708 |
Token | "] |
Token ID | 8973 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
recept | +1.951 |
acht | +1.931 |
xxxxxxxx | +1.830 |
phabet | +1.822 |
ieth | +1.779 |
Neg logit contributions | |
anamo | -2.382 |
DCS | -2.180 |
abul | -2.125 |
Salvador | -2.110 |
ⓘ | -2.090 |
Token |
|
Token ID | 198 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
recept | +0.117 |
acht | +0.115 |
xxxxxxxx | +0.109 |
phabet | +0.108 |
ieth | +0.105 |
Neg logit contributions | |
anamo | -0.171 |
DCS | -0.159 |
Salvador | -0.156 |
abul | -0.155 |
ⓘ | -0.154 |
Token | The |
Token ID | 464 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
anamo | +0.037 |
DCS | +0.034 |
Salvador | +0.033 |
abul | +0.033 |
ⓘ | +0.033 |
Neg logit contributions | |
recept | -0.032 |
acht | -0.032 |
xxxxxxxx | -0.030 |
phabet | -0.030 |
ieth | -0.029 |
Token | General |
Token ID | 3611 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
recept | +0.206 |
acht | +0.201 |
xxxxxxxx | +0.192 |
phabet | +0.189 |
ieth | +0.185 |
Neg logit contributions | |
anamo | -0.236 |
DCS | -0.219 |
abul | -0.212 |
Salvador | -0.211 |
ⓘ | -0.209 |
Token | Assembly |
Token ID | 10006 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
recept | +0.358 |
acht | +0.351 |
xxxxxxxx | +0.336 |
phabet | +0.335 |
ieth | +0.327 |
Neg logit contributions | |
anamo | -0.386 |
DCS | -0.357 |
Salvador | -0.346 |
abul | -0.344 |
ⓘ | -0.341 |
Token | of |
Token ID | 286 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
recept | +0.649 |
acht | +0.633 |
xxxxxxxx | +0.599 |
phabet | +0.594 |
ieth | +0.578 |
Neg logit contributions | |
anamo | -0.933 |
DCS | -0.869 |
Salvador | -0.845 |
abul | -0.843 |
ⓘ | -0.836 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
anamo | +0.012 |
DCS | +0.011 |
Salvador | +0.011 |
abul | +0.011 |
ⓘ | +0.011 |
Neg logit contributions | |
recept | -0.011 |
acht | -0.011 |
xxxxxxxx | -0.010 |
phabet | -0.010 |
ieth | -0.010 |
Token | do |
Token ID | 4598 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
acht | +3.730 |
recept | +3.601 |
xxxxxxxx | +3.525 |
phabet | +3.436 |
ieth | +3.340 |
Neg logit contributions | |
anamo | -3.182 |
DCS | -2.860 |
Salvador | -2.828 |
abul | -2.815 |
raught | -2.768 |
Token | in |
Token ID | 259 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
anamo | +0.744 |
DCS | +0.687 |
Salvador | +0.671 |
abul | +0.667 |
ⓘ | +0.665 |
Neg logit contributions | |
recept | -0.724 |
acht | -0.709 |
phabet | -0.682 |
xxxxxxxx | -0.679 |
ieth | -0.662 |
Token | students |
Token ID | 2444 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
anamo | +0.367 |
DCS | +0.338 |
Salvador | +0.330 |
abul | +0.328 |
ⓘ | +0.325 |
Neg logit contributions | |
recept | -0.341 |
acht | -0.335 |
xxxxxxxx | -0.320 |
phabet | -0.318 |
ieth | -0.311 |
Token | issued |
Token ID | 4884 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
anamo | +0.302 |
DCS | +0.281 |
Salvador | +0.275 |
abul | +0.273 |
ⓘ | +0.272 |
Neg logit contributions | |
recept | -0.225 |
acht | -0.221 |
xxxxxxxx | -0.210 |
phabet | -0.209 |
ieth | -0.203 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
anamo | +0.060 |
DCS | +0.056 |
Salvador | +0.055 |
abul | +0.055 |
ⓘ | +0.054 |
Neg logit contributions | |
recept | -0.045 |
acht | -0.045 |
xxxxxxxx | -0.042 |
phabet | -0.042 |
ieth | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
anamo | +0.220 |
DCS | +0.203 |
Salvador | +0.201 |
abul | +0.199 |
ⓘ | +0.198 |
Neg logit contributions | |
recept | -0.179 |
acht | -0.174 |
xxxxxxxx | -0.168 |
phabet | -0.166 |
ieth | -0.161 |
Token | S |
Token ID | 311 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
anamo | +0.327 |
DCS | +0.296 |
abul | +0.291 |
Salvador | +0.285 |
sole | +0.285 |
Neg logit contributions | |
recept | -0.292 |
acht | -0.286 |
xxxxxxxx | -0.276 |
phabet | -0.268 |
ieth | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
recept | +0.210 |
acht | +0.206 |
xxxxxxxx | +0.199 |
phabet | +0.197 |
ieth | +0.193 |
Neg logit contributions | |
anamo | -0.172 |
DCS | -0.157 |
Salvador | -0.154 |
abul | -0.153 |
ⓘ | -0.152 |
Token | R |
Token ID | 371 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
anamo | +1.382 |
DCS | +1.274 |
Salvador | +1.243 |
abul | +1.240 |
ⓘ | +1.226 |
Neg logit contributions | |
recept | -1.190 |
acht | -1.167 |
xxxxxxxx | -1.116 |
phabet | -1.109 |
ieth | -1.082 |
Token | ., |
Token ID | 1539 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
anamo | +0.133 |
DCS | +0.121 |
Salvador | +0.119 |
abul | +0.118 |
ⓘ | +0.117 |
Neg logit contributions | |
recept | -0.180 |
acht | -0.176 |
xxxxxxxx | -0.171 |
phabet | -0.169 |
ieth | -0.165 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
anamo | +0.719 |
DCS | +0.661 |
Salvador | +0.648 |
abul | +0.640 |
ⓘ | +0.638 |
Neg logit contributions | |
recept | -0.758 |
acht | -0.745 |
xxxxxxxx | -0.714 |
phabet | -0.714 |
ieth | -0.695 |
Token | es |
Token ID | 274 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
acht | +2.883 |
recept | +2.814 |
xxxxxxxx | +2.634 |
phabet | +2.632 |
ieth | +2.608 |
Neg logit contributions | |
anamo | -3.874 |
DCS | -3.633 |
Salvador | -3.590 |
abul | -3.536 |
ⓘ | -3.505 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
recept | +0.695 |
acht | +0.680 |
xxxxxxxx | +0.648 |
phabet | +0.644 |
ieth | +0.626 |
Neg logit contributions | |
anamo | -0.896 |
DCS | -0.831 |
Salvador | -0.814 |
abul | -0.809 |
ⓘ | -0.804 |
Token | L |
Token ID | 406 |
Feature activation | +9.22e-02 |
Pos logit contributions | |
anamo | +0.239 |
DCS | +0.215 |
abul | +0.213 |
sole | +0.208 |
Salvador | +0.207 |
Neg logit contributions | |
recept | -0.218 |
acht | -0.213 |
xxxxxxxx | -0.206 |
phabet | -0.200 |
ieth | -0.198 |
Token | ., |
Token ID | 1539 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
anamo | +0.071 |
DCS | +0.066 |
Salvador | +0.065 |
abul | +0.064 |
ⓘ | +0.064 |
Neg logit contributions | |
recept | -0.066 |
acht | -0.064 |
xxxxxxxx | -0.062 |
phabet | -0.061 |
ieth | -0.059 |
Token | O |
Token ID | 440 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
anamo | +0.683 |
DCS | +0.627 |
Salvador | +0.615 |
abul | +0.608 |
ⓘ | +0.606 |
Neg logit contributions | |
recept | -0.720 |
acht | -0.707 |
xxxxxxxx | -0.678 |
phabet | -0.678 |
ieth | -0.660 |
Token | s |
Token ID | 82 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
anamo | +0.252 |
DCS | +0.232 |
Salvador | +0.226 |
abul | +0.225 |
ⓘ | +0.223 |
Neg logit contributions | |
recept | -0.228 |
acht | -0.225 |
xxxxxxxx | -0.215 |
phabet | -0.214 |
ieth | -0.209 |
Token | Cors |
Token ID | 26978 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
recept | +0.184 |
acht | +0.181 |
xxxxxxxx | +0.171 |
phabet | +0.170 |
ieth | +0.166 |
Neg logit contributions | |
anamo | -0.262 |
DCS | -0.245 |
Salvador | -0.238 |
abul | -0.238 |
ⓘ | -0.236 |
Token | airs |
Token ID | 3468 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
anamo | +0.233 |
DCS | +0.217 |
Salvador | +0.214 |
abul | +0.212 |
ⓘ | +0.211 |
Neg logit contributions | |
recept | -0.155 |
acht | -0.151 |
phabet | -0.143 |
xxxxxxxx | -0.143 |
ieth | -0.138 |
Token | are |
Token ID | 389 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
recept | +0.279 |
acht | +0.274 |
xxxxxxxx | +0.259 |
phabet | +0.257 |
ieth | +0.251 |
Neg logit contributions | |
anamo | -0.401 |
DCS | -0.374 |
Salvador | -0.365 |
abul | -0.364 |
ⓘ | -0.361 |
Token | the |
Token ID | 262 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
anamo | +0.579 |
DCS | +0.537 |
Salvador | +0.526 |
abul | +0.522 |
ⓘ | +0.519 |
Neg logit contributions | |
recept | -0.461 |
acht | -0.453 |
xxxxxxxx | -0.432 |
phabet | -0.431 |
ieth | -0.418 |
Token | guardians |
Token ID | 32769 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
anamo | +0.045 |
DCS | +0.042 |
Salvador | +0.041 |
abul | +0.040 |
ⓘ | +0.040 |
Neg logit contributions | |
recept | -0.037 |
acht | -0.036 |
xxxxxxxx | -0.035 |
phabet | -0.035 |
ieth | -0.033 |
Token | of |
Token ID | 286 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
recept | +2.377 |
acht | +2.317 |
xxxxxxxx | +2.160 |
phabet | +2.139 |
ieth | +2.133 |
Neg logit contributions | |
anamo | -4.422 |
DCS | -4.167 |
abul | -4.038 |
Salvador | -4.037 |
ⓘ | -4.031 |
Token | values |
Token ID | 3815 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
anamo | +0.022 |
DCS | +0.021 |
Salvador | +0.020 |
abul | +0.020 |
ⓘ | +0.020 |
Neg logit contributions | |
recept | -0.018 |
acht | -0.018 |
xxxxxxxx | -0.017 |
phabet | -0.017 |
ieth | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
recept | +0.203 |
acht | +0.198 |
xxxxxxxx | +0.188 |
phabet | +0.186 |
ieth | +0.183 |
Neg logit contributions | |
anamo | -0.268 |
DCS | -0.249 |
Salvador | -0.242 |
abul | -0.241 |
ⓘ | -0.240 |
Token | spirit |
Token ID | 4437 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
anamo | +0.039 |
DCS | +0.036 |
Salvador | +0.036 |
abul | +0.035 |
ⓘ | +0.035 |
Neg logit contributions | |
recept | -0.032 |
acht | -0.032 |
xxxxxxxx | -0.030 |
phabet | -0.030 |
ieth | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
recept | +0.088 |
acht | +0.086 |
xxxxxxxx | +0.082 |
phabet | +0.081 |
ieth | +0.079 |
Neg logit contributions | |
anamo | -0.122 |
DCS | -0.113 |
Salvador | -0.111 |
abul | -0.110 |
ⓘ | -0.110 |
Token | � |
Token ID | 447 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
anamo | +0.200 |
DCS | +0.185 |
Salvador | +0.180 |
abul | +0.179 |
ⓘ | +0.179 |
Neg logit contributions | |
recept | -0.175 |
acht | -0.172 |
xxxxxxxx | -0.165 |
phabet | -0.164 |
ieth | -0.159 |
Token | � |
Token ID | 251 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
anamo | +0.034 |
DCS | +0.031 |
Salvador | +0.030 |
abul | +0.030 |
ⓘ | +0.029 |
Neg logit contributions | |
recept | -0.038 |
acht | -0.037 |
xxxxxxxx | -0.036 |
phabet | -0.036 |
ieth | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
recept | +0.048 |
acht | +0.047 |
xxxxxxxx | +0.045 |
phabet | +0.045 |
ieth | +0.044 |
Neg logit contributions | |
anamo | -0.059 |
DCS | -0.055 |
Salvador | -0.053 |
abul | -0.053 |
ⓘ | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
anamo | +0.326 |
DCS | +0.303 |
Salvador | +0.296 |
abul | +0.295 |
ⓘ | +0.293 |
Neg logit contributions | |
recept | -0.239 |
acht | -0.234 |
xxxxxxxx | -0.222 |
phabet | -0.222 |
ieth | -0.215 |
Token | contr |
Token ID | 3445 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
anamo | +0.146 |
DCS | +0.134 |
abul | +0.131 |
Salvador | +0.130 |
ⓘ | +0.129 |
Neg logit contributions | |
recept | -0.135 |
acht | -0.132 |
xxxxxxxx | -0.125 |
phabet | -0.124 |
ieth | -0.121 |
Token | aband |
Token ID | 49248 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
recept | +0.027 |
acht | +0.026 |
xxxxxxxx | +0.025 |
phabet | +0.025 |
ieth | +0.024 |
Neg logit contributions | |
anamo | -0.029 |
DCS | -0.027 |
Salvador | -0.027 |
ⓘ | -0.026 |
abul | -0.026 |
Token | trade |
Token ID | 3292 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
recept | +3.064 |
acht | +2.935 |
xxxxxxxx | +2.794 |
phabet | +2.776 |
ieth | +2.735 |
Neg logit contributions | |
anamo | -3.745 |
DCS | -3.514 |
abul | -3.393 |
Salvador | -3.374 |
ⓘ | -3.360 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
anamo | +0.530 |
DCS | +0.492 |
Salvador | +0.481 |
abul | +0.478 |
ⓘ | +0.475 |
Neg logit contributions | |
recept | -0.431 |
acht | -0.423 |
xxxxxxxx | -0.403 |
phabet | -0.402 |
ieth | -0.391 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
anamo | +0.309 |
DCS | +0.285 |
abul | +0.278 |
Salvador | +0.278 |
ⓘ | +0.275 |
Neg logit contributions | |
recept | -0.243 |
acht | -0.239 |
xxxxxxxx | -0.229 |
phabet | -0.226 |
ieth | -0.220 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
anamo | +0.092 |
DCS | +0.085 |
Salvador | +0.084 |
abul | +0.083 |
ⓘ | +0.083 |
Neg logit contributions | |
recept | -0.063 |
acht | -0.062 |
xxxxxxxx | -0.059 |
phabet | -0.058 |
ieth | -0.057 |
Token | The |
Token ID | 464 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
anamo | +0.288 |
DCS | +0.264 |
Salvador | +0.259 |
abul | +0.257 |
ⓘ | +0.256 |
Neg logit contributions | |
recept | -0.256 |
acht | -0.253 |
xxxxxxxx | -0.242 |
phabet | -0.240 |
ieth | -0.234 |
Token | willing |
Token ID | 4684 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
anamo | +0.674 |
DCS | +0.626 |
Salvador | +0.611 |
abul | +0.609 |
ⓘ | +0.605 |
Neg logit contributions | |
recept | -0.528 |
acht | -0.518 |
xxxxxxxx | -0.493 |
phabet | -0.491 |
ieth | -0.478 |
Token | to |
Token ID | 284 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
anamo | +0.178 |
DCS | +0.166 |
Salvador | +0.163 |
abul | +0.162 |
ⓘ | +0.161 |
Neg logit contributions | |
recept | -0.123 |
acht | -0.121 |
phabet | -0.115 |
xxxxxxxx | -0.114 |
ieth | -0.112 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anamo | +0.350 |
DCS | +0.325 |
Salvador | +0.318 |
abul | +0.316 |
ⓘ | +0.314 |
Neg logit contributions | |
recept | -0.272 |
acht | -0.267 |
xxxxxxxx | -0.254 |
phabet | -0.254 |
ieth | -0.246 |
Token | at |
Token ID | 379 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
anamo | +1.530 |
DCS | +1.422 |
Salvador | +1.395 |
abul | +1.385 |
ⓘ | +1.377 |
Neg logit contributions | |
recept | -1.131 |
acht | -1.110 |
xxxxxxxx | -1.055 |
phabet | -1.052 |
ieth | -1.021 |
Token | the |
Token ID | 262 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
anamo | +0.046 |
DCS | +0.043 |
Salvador | +0.041 |
abul | +0.041 |
ⓘ | +0.041 |
Neg logit contributions | |
recept | -0.039 |
acht | -0.039 |
xxxxxxxx | -0.037 |
phabet | -0.037 |
ieth | -0.036 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
anamo | +0.296 |
DCS | +0.271 |
abul | +0.262 |
Salvador | +0.261 |
ⓘ | +0.259 |
Neg logit contributions | |
recept | -0.349 |
acht | -0.343 |
xxxxxxxx | -0.329 |
phabet | -0.326 |
ieth | -0.321 |
Token | den |
Token ID | 6559 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
acht | +1.685 |
recept | +1.622 |
xxxxxxxx | +1.482 |
phabet | +1.401 |
ieth | +1.356 |
Neg logit contributions | |
anamo | -4.919 |
Salvador | -4.627 |
DCS | -4.602 |
abul | -4.575 |
Jagu | -4.554 |
Token | prison |
Token ID | 3770 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
anamo | +0.739 |
DCS | +0.688 |
Salvador | +0.676 |
abul | +0.671 |
ⓘ | +0.668 |
Neg logit contributions | |
recept | -0.513 |
acht | -0.504 |
xxxxxxxx | -0.479 |
phabet | -0.478 |
ieth | -0.462 |
Token | because |
Token ID | 780 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
anamo | +0.257 |
DCS | +0.239 |
abul | +0.234 |
Salvador | +0.233 |
ⓘ | +0.231 |
Neg logit contributions | |
recept | -0.179 |
acht | -0.174 |
xxxxxxxx | -0.165 |
phabet | -0.163 |
ieth | -0.159 |
Token | he |
Token ID | 339 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
recept | +0.132 |
acht | +0.130 |
xxxxxxxx | +0.124 |
phabet | +0.124 |
ieth | +0.121 |
Neg logit contributions | |
anamo | -0.148 |
DCS | -0.137 |
Salvador | -0.133 |
abul | -0.133 |
ⓘ | -0.132 |
Token | is |
Token ID | 318 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
anamo | +0.232 |
DCS | +0.217 |
Salvador | +0.213 |
abul | +0.212 |
ⓘ | +0.210 |
Neg logit contributions | |
recept | -0.142 |
acht | -0.139 |
xxxxxxxx | -0.131 |
phabet | -0.131 |
ieth | -0.126 |
Token | women |
Token ID | 1466 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
anamo | +0.046 |
DCS | +0.042 |
abul | +0.040 |
ⓘ | +0.040 |
sole | +0.040 |
Neg logit contributions | |
recept | -0.053 |
acht | -0.051 |
xxxxxxxx | -0.049 |
phabet | -0.049 |
ieth | -0.048 |
Token | watch |
Token ID | 2342 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
anamo | +0.761 |
DCS | +0.705 |
Salvador | +0.690 |
abul | +0.686 |
ⓘ | +0.682 |
Neg logit contributions | |
recept | -0.602 |
acht | -0.590 |
xxxxxxxx | -0.562 |
phabet | -0.560 |
ieth | -0.544 |
Token | on |
Token ID | 319 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
recept | +0.036 |
acht | +0.035 |
xxxxxxxx | +0.033 |
phabet | +0.033 |
ieth | +0.032 |
Neg logit contributions | |
anamo | -0.045 |
DCS | -0.041 |
abul | -0.040 |
Salvador | -0.040 |
ⓘ | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
anamo | +0.250 |
DCS | +0.232 |
Salvador | +0.226 |
abul | +0.226 |
ⓘ | +0.223 |
Neg logit contributions | |
recept | -0.197 |
acht | -0.193 |
xxxxxxxx | -0.183 |
phabet | -0.182 |
ieth | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
recept | +0.048 |
acht | +0.047 |
xxxxxxxx | +0.044 |
phabet | +0.044 |
ieth | +0.043 |
Neg logit contributions | |
anamo | -0.059 |
DCS | -0.055 |
abul | -0.054 |
Salvador | -0.054 |
ⓘ | -0.053 |
Token | pro |
Token ID | 386 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
anamo | +0.340 |
DCS | +0.316 |
abul | +0.307 |
Salvador | +0.306 |
ⓘ | +0.304 |
Neg logit contributions | |
recept | -0.267 |
acht | -0.261 |
xxxxxxxx | -0.248 |
phabet | -0.246 |
ieth | -0.240 |
Token | - |
Token ID | 12 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
anamo | +2.898 |
DCS | +2.737 |
Salvador | +2.685 |
ⓘ | +2.646 |
abul | +2.643 |
Neg logit contributions | |
recept | -2.013 |
acht | -1.969 |
phabet | -1.882 |
xxxxxxxx | -1.874 |
ieth | -1.803 |
Token | independence |
Token ID | 39894 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
anamo | +0.136 |
DCS | +0.124 |
Salvador | +0.120 |
abul | +0.119 |
ⓘ | +0.119 |
Neg logit contributions | |
recept | -0.172 |
acht | -0.170 |
xxxxxxxx | -0.163 |
phabet | -0.163 |
ieth | -0.159 |
Token | rally |
Token ID | 7903 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
anamo | +0.929 |
DCS | +0.850 |
Salvador | +0.833 |
abul | +0.821 |
ⓘ | +0.818 |
Neg logit contributions | |
recept | -1.085 |
acht | -1.069 |
xxxxxxxx | -1.031 |
phabet | -1.029 |
ieth | -1.005 |
Token | at |
Token ID | 379 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
anamo | +0.455 |
DCS | +0.423 |
Salvador | +0.414 |
abul | +0.412 |
ⓘ | +0.409 |
Neg logit contributions | |
recept | -0.337 |
acht | -0.330 |
xxxxxxxx | -0.314 |
phabet | -0.313 |
ieth | -0.304 |
Token | Plaza |
Token ID | 23280 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
anamo | +0.071 |
DCS | +0.064 |
Salvador | +0.063 |
abul | +0.062 |
ⓘ | +0.062 |
Neg logit contributions | |
recept | -0.090 |
acht | -0.088 |
xxxxxxxx | -0.085 |
phabet | -0.085 |
ieth | -0.083 |
Token | https |
Token ID | 3740 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
recept | +0.097 |
acht | +0.095 |
xxxxxxxx | +0.091 |
phabet | +0.090 |
ieth | +0.088 |
Neg logit contributions | |
anamo | -0.128 |
DCS | -0.119 |
Salvador | -0.116 |
abul | -0.115 |
ⓘ | -0.115 |
Token | :// |
Token ID | 1378 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
recept | +0.542 |
acht | +0.530 |
xxxxxxxx | +0.488 |
phabet | +0.465 |
ieth | +0.448 |
Neg logit contributions | |
anamo | -1.897 |
DCS | -1.786 |
Salvador | -1.758 |
abul | -1.755 |
ⓘ | -1.741 |
Token | old |
Token ID | 727 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
acht | +1.516 |
recept | +1.509 |
xxxxxxxx | +1.447 |
phabet | +1.397 |
ieth | +1.380 |
Neg logit contributions | |
anamo | -2.118 |
DCS | -1.954 |
Salvador | -1.923 |
abul | -1.896 |
ⓘ | -1.894 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
anamo | +0.735 |
DCS | +0.696 |
Salvador | +0.681 |
ⓘ | +0.675 |
abul | +0.674 |
Neg logit contributions | |
recept | -0.522 |
acht | -0.508 |
phabet | -0.488 |
xxxxxxxx | -0.479 |
ieth | -0.468 |
Token | nice |
Token ID | 44460 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
anamo | +0.332 |
DCS | +0.309 |
Salvador | +0.302 |
abul | +0.301 |
ⓘ | +0.299 |
Neg logit contributions | |
recept | -0.242 |
acht | -0.237 |
phabet | -0.225 |
xxxxxxxx | -0.224 |
ieth | -0.218 |
Token | hash |
Token ID | 17831 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
anamo | +0.651 |
DCS | +0.578 |
abul | +0.556 |
Salvador | +0.553 |
ⓘ | +0.549 |
Neg logit contributions | |
recept | -1.198 |
acht | -1.174 |
phabet | -1.140 |
xxxxxxxx | -1.136 |
ieth | -1.115 |
Token | . |
Token ID | 13 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
anamo | +2.578 |
DCS | +2.540 |
Salvador | +2.464 |
ⓘ | +2.458 |
abul | +2.424 |
Neg logit contributions | |
recept | -2.209 |
acht | -2.115 |
phabet | -2.106 |
ieth | -1.995 |
xxxxxxxx | -1.978 |
Token | com |
Token ID | 785 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
anamo | +0.075 |
DCS | +0.071 |
Salvador | +0.069 |
abul | +0.069 |
ⓘ | +0.069 |
Neg logit contributions | |
recept | -0.049 |
acht | -0.048 |
phabet | -0.046 |
xxxxxxxx | -0.045 |
ieth | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
recept | +0.315 |
acht | +0.309 |
xxxxxxxx | +0.294 |
phabet | +0.290 |
ieth | +0.283 |
Neg logit contributions | |
anamo | -0.439 |
DCS | -0.406 |
Salvador | -0.397 |
abul | -0.397 |
ⓘ | -0.391 |
Token | but |
Token ID | 475 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
recept | +0.184 |
acht | +0.181 |
xxxxxxxx | +0.173 |
phabet | +0.172 |
ieth | +0.168 |
Neg logit contributions | |
anamo | -0.196 |
DCS | -0.180 |
Salvador | -0.175 |
abul | -0.175 |
ⓘ | -0.173 |
Token | will |
Token ID | 481 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
recept | +0.208 |
acht | +0.203 |
xxxxxxxx | +0.194 |
phabet | +0.191 |
ieth | +0.186 |
Neg logit contributions | |
anamo | -0.292 |
DCS | -0.270 |
abul | -0.264 |
Salvador | -0.264 |
ⓘ | -0.261 |
Token | ception |
Token ID | 4516 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
anamo | +0.601 |
DCS | +0.550 |
Salvador | +0.537 |
abul | +0.533 |
ⓘ | +0.530 |
Neg logit contributions | |
recept | -0.636 |
acht | -0.627 |
xxxxxxxx | -0.598 |
phabet | -0.596 |
ieth | -0.583 |
Token | . |
Token ID | 13 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
anamo | +0.363 |
DCS | +0.337 |
Salvador | +0.329 |
abul | +0.328 |
ⓘ | +0.325 |
Neg logit contributions | |
recept | -0.282 |
acht | -0.277 |
xxxxxxxx | -0.263 |
phabet | -0.262 |
ieth | -0.255 |
Token | It |
Token ID | 632 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
anamo | +0.204 |
DCS | +0.189 |
Salvador | +0.184 |
abul | +0.184 |
ⓘ | +0.182 |
Neg logit contributions | |
recept | -0.166 |
acht | -0.163 |
xxxxxxxx | -0.156 |
phabet | -0.155 |
ieth | -0.151 |
Token | has |
Token ID | 468 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
anamo | +0.171 |
DCS | +0.160 |
Salvador | +0.156 |
abul | +0.155 |
ⓘ | +0.155 |
Neg logit contributions | |
recept | -0.109 |
acht | -0.106 |
xxxxxxxx | -0.100 |
phabet | -0.100 |
ieth | -0.097 |
Token | been |
Token ID | 587 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
anamo | +0.198 |
DCS | +0.184 |
Salvador | +0.180 |
abul | +0.179 |
ⓘ | +0.178 |
Neg logit contributions | |
recept | -0.139 |
acht | -0.136 |
xxxxxxxx | -0.129 |
phabet | -0.128 |
ieth | -0.124 |
Token | known |
Token ID | 1900 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
anamo | +0.609 |
DCS | +0.564 |
Salvador | +0.549 |
abul | +0.548 |
ⓘ | +0.545 |
Neg logit contributions | |
recept | -0.512 |
acht | -0.503 |
xxxxxxxx | -0.478 |
phabet | -0.475 |
ieth | -0.464 |
Token | from |
Token ID | 422 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
anamo | +2.475 |
DCS | +2.286 |
Salvador | +2.245 |
abul | +2.225 |
ⓘ | +2.209 |
Neg logit contributions | |
recept | -2.103 |
acht | -2.067 |
phabet | -1.979 |
xxxxxxxx | -1.973 |
ieth | -1.918 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
recept | +0.311 |
acht | +0.305 |
xxxxxxxx | +0.289 |
phabet | +0.286 |
ieth | +0.278 |
Neg logit contributions | |
anamo | -0.386 |
DCS | -0.357 |
abul | -0.348 |
ⓘ | -0.347 |
Salvador | -0.346 |
Token | beginning |
Token ID | 3726 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
anamo | +0.277 |
DCS | +0.259 |
Salvador | +0.252 |
abul | +0.252 |
ⓘ | +0.251 |
Neg logit contributions | |
recept | -0.185 |
acht | -0.181 |
xxxxxxxx | -0.172 |
phabet | -0.170 |
ieth | -0.166 |
Token | that |
Token ID | 326 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
recept | +1.225 |
acht | +1.201 |
xxxxxxxx | +1.147 |
phabet | +1.132 |
ieth | +1.101 |
Neg logit contributions | |
anamo | -1.520 |
DCS | -1.414 |
abul | -1.375 |
Salvador | -1.368 |
ⓘ | -1.359 |
Token | Ber |
Token ID | 4312 |
Feature activation | -7.65e-01 |
Pos logit contributions | |
recept | +0.075 |
acht | +0.073 |
xxxxxxxx | +0.070 |
phabet | +0.070 |
ieth | +0.068 |
Neg logit contributions | |
anamo | -0.093 |
DCS | -0.086 |
Salvador | -0.084 |
abul | -0.084 |
ⓘ | -0.084 |
Token | sent |
Token ID | 1908 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
anamo | +0.189 |
DCS | +0.176 |
Salvador | +0.172 |
abul | +0.171 |
ⓘ | +0.170 |
Neg logit contributions | |
recept | -0.123 |
acht | -0.120 |
xxxxxxxx | -0.114 |
phabet | -0.112 |
ieth | -0.109 |
Token | out |
Token ID | 503 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
recept | +0.358 |
acht | +0.350 |
xxxxxxxx | +0.334 |
phabet | +0.331 |
ieth | +0.324 |
Neg logit contributions | |
anamo | -0.389 |
DCS | -0.357 |
abul | -0.346 |
Salvador | -0.345 |
ⓘ | -0.343 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
recept | +0.324 |
acht | +0.315 |
xxxxxxxx | +0.300 |
phabet | +0.297 |
ieth | +0.291 |
Neg logit contributions | |
anamo | -0.371 |
DCS | -0.341 |
abul | -0.330 |
Salvador | -0.329 |
ⓘ | -0.328 |
Token | series |
Token ID | 2168 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
anamo | +0.137 |
DCS | +0.125 |
abul | +0.121 |
Salvador | +0.121 |
ⓘ | +0.120 |
Neg logit contributions | |
recept | -0.135 |
acht | -0.131 |
xxxxxxxx | -0.126 |
phabet | -0.125 |
ieth | -0.122 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
recept | +0.433 |
acht | +0.422 |
xxxxxxxx | +0.396 |
phabet | +0.390 |
ieth | +0.378 |
Neg logit contributions | |
anamo | -0.837 |
DCS | -0.778 |
Salvador | -0.762 |
abul | -0.762 |
ⓘ | -0.754 |
Token | pro |
Token ID | 386 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
recept | +0.128 |
acht | +0.124 |
xxxxxxxx | +0.119 |
phabet | +0.118 |
ieth | +0.116 |
Neg logit contributions | |
anamo | -0.127 |
DCS | -0.116 |
abul | -0.112 |
Salvador | -0.111 |
ⓘ | -0.110 |
Token | - |
Token ID | 12 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
anamo | +3.027 |
DCS | +2.838 |
Salvador | +2.794 |
abul | +2.752 |
ⓘ | +2.722 |
Neg logit contributions | |
recept | -2.105 |
acht | -2.095 |
xxxxxxxx | -1.972 |
phabet | -1.966 |
ieth | -1.919 |
Token | Sanders |
Token ID | 26747 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
anamo | +0.173 |
DCS | +0.158 |
Salvador | +0.156 |
abul | +0.154 |
ⓘ | +0.154 |
Neg logit contributions | |
recept | -0.173 |
acht | -0.170 |
xxxxxxxx | -0.163 |
phabet | -0.162 |
ieth | -0.158 |
Token | messages |
Token ID | 6218 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
recept | +0.108 |
acht | +0.105 |
xxxxxxxx | +0.101 |
phabet | +0.100 |
ieth | +0.097 |
Neg logit contributions | |
anamo | -0.108 |
DCS | -0.099 |
Salvador | -0.096 |
abul | -0.096 |
ⓘ | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
anamo | +1.111 |
DCS | +1.034 |
Salvador | +1.013 |
abul | +1.007 |
ⓘ | +1.001 |
Neg logit contributions | |
recept | -0.821 |
acht | -0.806 |
xxxxxxxx | -0.766 |
phabet | -0.764 |
ieth | -0.741 |
Token | according |
Token ID | 1864 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
anamo | +0.333 |
DCS | +0.308 |
abul | +0.300 |
Salvador | +0.300 |
ⓘ | +0.297 |
Neg logit contributions | |
recept | -0.269 |
acht | -0.262 |
xxxxxxxx | -0.250 |
phabet | -0.249 |
ieth | -0.242 |
Token | gift |
Token ID | 6979 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
anamo | +1.233 |
DCS | +1.140 |
Salvador | +1.122 |
abul | +1.111 |
ⓘ | +1.105 |
Neg logit contributions | |
recept | -1.081 |
acht | -1.063 |
xxxxxxxx | -1.016 |
phabet | -1.011 |
ieth | -0.984 |
Token | – |
Token ID | 1906 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
recept | +1.286 |
acht | +1.251 |
xxxxxxxx | +1.186 |
phabet | +1.179 |
ieth | +1.148 |
Neg logit contributions | |
anamo | -1.746 |
DCS | -1.617 |
Salvador | -1.575 |
abul | -1.565 |
ⓘ | -1.554 |
Token | be |
Token ID | 1350 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
anamo | +0.460 |
DCS | +0.425 |
Salvador | +0.416 |
abul | +0.413 |
ⓘ | +0.410 |
Neg logit contributions | |
recept | -0.404 |
acht | -0.396 |
xxxxxxxx | -0.378 |
phabet | -0.377 |
ieth | -0.367 |
Token | arer |
Token ID | 11258 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
recept | +0.387 |
acht | +0.380 |
xxxxxxxx | +0.361 |
phabet | +0.358 |
ieth | +0.350 |
Neg logit contributions | |
anamo | -0.446 |
DCS | -0.412 |
Salvador | -0.403 |
abul | -0.399 |
ⓘ | -0.397 |
Token | setting |
Token ID | 4634 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
recept | +1.716 |
acht | +1.662 |
xxxxxxxx | +1.576 |
phabet | +1.550 |
ieth | +1.523 |
Neg logit contributions | |
anamo | -2.365 |
DCS | -2.200 |
abul | -2.132 |
Salvador | -2.128 |
sole | -2.098 |
Token | box |
Token ID | 3091 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
anamo | +0.120 |
DCS | +0.111 |
Salvador | +0.109 |
abul | +0.108 |
ⓘ | +0.107 |
Neg logit contributions | |
recept | -0.092 |
acht | -0.090 |
xxxxxxxx | -0.086 |
phabet | -0.086 |
ieth | -0.083 |
Token | underneath |
Token ID | 14638 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
anamo | +2.375 |
DCS | +2.209 |
Salvador | +2.173 |
ⓘ | +2.166 |
abul | +2.160 |
Neg logit contributions | |
recept | -1.805 |
acht | -1.786 |
phabet | -1.714 |
xxxxxxxx | -1.696 |
ieth | -1.651 |
Token | roughly |
Token ID | 7323 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
anamo | +0.859 |
DCS | +0.799 |
Salvador | +0.783 |
abul | +0.777 |
ⓘ | +0.774 |
Neg logit contributions | |
recept | -0.677 |
acht | -0.667 |
xxxxxxxx | -0.635 |
phabet | -0.634 |
ieth | -0.615 |
Token | ( |
Token ID | 357 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
recept | +0.414 |
acht | +0.402 |
xxxxxxxx | +0.385 |
phabet | +0.381 |
ieth | +0.375 |
Neg logit contributions | |
anamo | -0.477 |
DCS | -0.439 |
Salvador | -0.426 |
abul | -0.425 |
ⓘ | -0.420 |
Token | 6 |
Token ID | 21 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
recept | +0.266 |
acht | +0.262 |
xxxxxxxx | +0.251 |
phabet | +0.248 |
ieth | +0.242 |
Neg logit contributions | |
anamo | -0.316 |
DCS | -0.289 |
Salvador | -0.285 |
abul | -0.282 |
ⓘ | -0.281 |
Token | ) |
Token ID | 8 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
anamo | +0.331 |
DCS | +0.309 |
Salvador | +0.303 |
abul | +0.301 |
ⓘ | +0.299 |
Neg logit contributions | |
recept | -0.235 |
acht | -0.231 |
xxxxxxxx | -0.219 |
phabet | -0.218 |
ieth | -0.212 |
Token | liable |
Token ID | 17583 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
recept | +0.041 |
acht | +0.040 |
xxxxxxxx | +0.038 |
phabet | +0.038 |
ieth | +0.037 |
Neg logit contributions | |
anamo | -0.054 |
DCS | -0.051 |
abul | -0.049 |
Salvador | -0.049 |
ⓘ | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
anamo | +0.946 |
DCS | +0.877 |
Salvador | +0.860 |
abul | +0.855 |
ⓘ | +0.849 |
Neg logit contributions | |
recept | -0.758 |
acht | -0.744 |
xxxxxxxx | -0.709 |
phabet | -0.707 |
ieth | -0.688 |
Token |
|
Token ID | 198 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
recept | +0.199 |
acht | +0.196 |
xxxxxxxx | +0.187 |
phabet | +0.185 |
ieth | +0.180 |
Neg logit contributions | |
anamo | -0.273 |
DCS | -0.254 |
abul | -0.248 |
Salvador | -0.247 |
ⓘ | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
recept | +0.213 |
acht | +0.209 |
xxxxxxxx | +0.198 |
phabet | +0.198 |
ieth | +0.192 |
Neg logit contributions | |
anamo | -0.304 |
DCS | -0.283 |
Salvador | -0.277 |
abul | -0.276 |
ⓘ | -0.274 |
Token | � |
Token ID | 447 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
recept | +0.056 |
acht | +0.055 |
xxxxxxxx | +0.053 |
phabet | +0.053 |
ieth | +0.051 |
Neg logit contributions | |
anamo | -0.059 |
DCS | -0.054 |
Salvador | -0.052 |
abul | -0.052 |
ⓘ | -0.052 |
Token | � |
Token ID | 250 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
anamo | +0.127 |
DCS | +0.115 |
Salvador | +0.112 |
abul | +0.111 |
ⓘ | +0.110 |
Neg logit contributions | |
recept | -0.162 |
acht | -0.159 |
xxxxxxxx | -0.153 |
phabet | -0.152 |
ieth | -0.149 |
Token | The |
Token ID | 464 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
anamo | +0.212 |
DCS | +0.193 |
abul | +0.189 |
Salvador | +0.189 |
ⓘ | +0.188 |
Neg logit contributions | |
recept | -0.181 |
acht | -0.179 |
xxxxxxxx | -0.174 |
phabet | -0.169 |
ieth | -0.167 |
Token | situation |
Token ID | 3074 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
recept | +0.281 |
acht | +0.273 |
xxxxxxxx | +0.263 |
phabet | +0.258 |
ieth | +0.255 |
Neg logit contributions | |
anamo | -0.325 |
DCS | -0.302 |
abul | -0.294 |
Salvador | -0.289 |
ⓘ | -0.288 |
Token | is |
Token ID | 318 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
recept | +0.761 |
acht | +0.746 |
xxxxxxxx | +0.704 |
phabet | +0.694 |
ieth | +0.679 |
Neg logit contributions | |
anamo | -1.149 |
DCS | -1.075 |
abul | -1.040 |
Salvador | -1.038 |
ⓘ | -1.034 |
Token | very |
Token ID | 845 |
Feature activation | +8.76e-01 |
Pos logit contributions | |
anamo | +0.217 |
DCS | +0.200 |
Salvador | +0.195 |
abul | +0.194 |
ⓘ | +0.192 |
Neg logit contributions | |
recept | -0.205 |
acht | -0.201 |
xxxxxxxx | -0.192 |
phabet | -0.191 |
ieth | -0.187 |
Token | different |
Token ID | 1180 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
anamo | +0.586 |
DCS | +0.534 |
Salvador | +0.521 |
abul | +0.516 |
ⓘ | +0.512 |
Neg logit contributions | |
recept | -0.714 |
acht | -0.704 |
xxxxxxxx | -0.678 |
phabet | -0.677 |
ieth | -0.661 |
Token | inspect |
Token ID | 10104 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
anamo | +0.284 |
DCS | +0.264 |
Salvador | +0.258 |
abul | +0.257 |
ⓘ | +0.255 |
Neg logit contributions | |
recept | -0.205 |
acht | -0.201 |
xxxxxxxx | -0.191 |
phabet | -0.190 |
ieth | -0.185 |
Token | s |
Token ID | 82 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
anamo | +1.246 |
DCS | +1.155 |
Salvador | +1.129 |
abul | +1.113 |
ⓘ | +1.110 |
Neg logit contributions | |
recept | -1.160 |
acht | -1.142 |
phabet | -1.096 |
xxxxxxxx | -1.091 |
ieth | -1.056 |
Token | her |
Token ID | 607 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
anamo | +1.320 |
DCS | +1.223 |
Salvador | +1.203 |
abul | +1.186 |
ⓘ | +1.179 |
Neg logit contributions | |
recept | -1.140 |
acht | -1.122 |
phabet | -1.077 |
xxxxxxxx | -1.071 |
ieth | -1.042 |
Token | burned |
Token ID | 11544 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
recept | +0.057 |
acht | +0.056 |
xxxxxxxx | +0.053 |
phabet | +0.053 |
ieth | +0.052 |
Neg logit contributions | |
anamo | -0.054 |
DCS | -0.049 |
abul | -0.048 |
Salvador | -0.047 |
ⓘ | -0.047 |
Token | arm |
Token ID | 3211 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
anamo | +1.242 |
DCS | +1.153 |
Salvador | +1.129 |
abul | +1.122 |
ⓘ | +1.115 |
Neg logit contributions | |
recept | -0.982 |
acht | -0.964 |
xxxxxxxx | -0.918 |
phabet | -0.916 |
ieth | -0.890 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
recept | +0.219 |
acht | +0.214 |
xxxxxxxx | +0.203 |
phabet | +0.202 |
ieth | +0.196 |
Neg logit contributions | |
anamo | -0.309 |
DCS | -0.288 |
Salvador | -0.280 |
abul | -0.280 |
ⓘ | -0.278 |
Token |
|
Token ID | 198 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
anamo | +0.098 |
DCS | +0.091 |
Salvador | +0.089 |
abul | +0.089 |
ⓘ | +0.088 |
Neg logit contributions | |
recept | -0.069 |
acht | -0.067 |
xxxxxxxx | -0.064 |
phabet | -0.064 |
ieth | -0.062 |
Token | T |
Token ID | 51 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
anamo | +0.311 |
DCS | +0.284 |
Salvador | +0.280 |
abul | +0.278 |
ⓘ | +0.277 |
Neg logit contributions | |
recept | -0.267 |
acht | -0.263 |
xxxxxxxx | -0.253 |
phabet | -0.249 |
ieth | -0.243 |
Token | ori |
Token ID | 10145 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
anamo | +0.298 |
DCS | +0.270 |
Salvador | +0.262 |
abul | +0.260 |
ⓘ | +0.257 |
Neg logit contributions | |
recept | -0.398 |
acht | -0.392 |
xxxxxxxx | -0.378 |
phabet | -0.376 |
ieth | -0.368 |
Token | and |
Token ID | 290 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
recept | +0.530 |
acht | +0.517 |
xxxxxxxx | +0.490 |
phabet | +0.483 |
ieth | +0.474 |
Neg logit contributions | |
anamo | -0.773 |
DCS | -0.721 |
abul | -0.702 |
Salvador | -0.696 |
ⓘ | -0.691 |
Token | family |
Token ID | 1641 |
Feature activation | -4.95e-01 |
Pos logit contributions | |
anamo | +0.189 |
DCS | +0.174 |
Salvador | +0.169 |
abul | +0.169 |
ⓘ | +0.167 |
Neg logit contributions | |
recept | -0.179 |
acht | -0.176 |
xxxxxxxx | -0.169 |
phabet | -0.168 |
ieth | -0.164 |
Token | investment |
Token ID | 4896 |
Feature activation | +9.64e-02 |
Pos logit contributions | |
recept | +0.077 |
acht | +0.075 |
xxxxxxxx | +0.071 |
phabet | +0.071 |
ieth | +0.069 |
Neg logit contributions | |
anamo | -0.100 |
DCS | -0.092 |
Salvador | -0.090 |
abul | -0.090 |
ⓘ | -0.089 |
Token | in |
Token ID | 287 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
anamo | +0.082 |
DCS | +0.076 |
Salvador | +0.074 |
abul | +0.074 |
ⓘ | +0.073 |
Neg logit contributions | |
recept | -0.062 |
acht | -0.061 |
xxxxxxxx | -0.058 |
phabet | -0.057 |
ieth | -0.056 |
Token | training |
Token ID | 3047 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
anamo | +0.227 |
DCS | +0.210 |
Salvador | +0.205 |
abul | +0.205 |
ⓘ | +0.203 |
Neg logit contributions | |
recept | -0.178 |
acht | -0.174 |
xxxxxxxx | -0.165 |
phabet | -0.164 |
ieth | -0.160 |
Token | and |
Token ID | 290 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
anamo | +1.795 |
DCS | +1.673 |
Salvador | +1.646 |
abul | +1.624 |
ⓘ | +1.619 |
Neg logit contributions | |
recept | -1.446 |
acht | -1.430 |
phabet | -1.363 |
xxxxxxxx | -1.363 |
ieth | -1.323 |
Token | development |
Token ID | 2478 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
anamo | +0.262 |
DCS | +0.243 |
Salvador | +0.238 |
abul | +0.237 |
ⓘ | +0.235 |
Neg logit contributions | |
recept | -0.203 |
acht | -0.199 |
xxxxxxxx | -0.189 |
phabet | -0.188 |
ieth | -0.183 |
Token | could |
Token ID | 714 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
recept | +0.604 |
acht | +0.589 |
xxxxxxxx | +0.556 |
phabet | +0.551 |
ieth | +0.535 |
Neg logit contributions | |
anamo | -0.844 |
DCS | -0.781 |
abul | -0.760 |
Salvador | -0.756 |
ⓘ | -0.751 |
Token | be |
Token ID | 307 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
anamo | +0.657 |
DCS | +0.608 |
Salvador | +0.594 |
abul | +0.591 |
ⓘ | +0.586 |
Neg logit contributions | |
recept | -0.603 |
acht | -0.593 |
xxxxxxxx | -0.567 |
phabet | -0.566 |
ieth | -0.551 |
Token | effective |
Token ID | 4050 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
recept | +0.202 |
acht | +0.198 |
xxxxxxxx | +0.189 |
phabet | +0.188 |
ieth | +0.183 |
Neg logit contributions | |
anamo | -0.259 |
DCS | -0.240 |
Salvador | -0.234 |
abul | -0.234 |
ⓘ | -0.232 |
Token | ways |
Token ID | 2842 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
recept | +0.209 |
acht | +0.204 |
xxxxxxxx | +0.194 |
phabet | +0.192 |
ieth | +0.187 |
Neg logit contributions | |
anamo | -0.290 |
DCS | -0.269 |
Salvador | -0.263 |
abul | -0.262 |
ⓘ | -0.260 |
Token | to |
Token ID | 284 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
recept | +0.118 |
acht | +0.116 |
phabet | +0.110 |
xxxxxxxx | +0.109 |
ieth | +0.107 |
Neg logit contributions | |
anamo | -0.172 |
DCS | -0.161 |
Salvador | -0.159 |
abul | -0.157 |
ⓘ | -0.157 |
Token | do |
Token ID | 466 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
anamo | +0.121 |
DCS | +0.111 |
Salvador | +0.108 |
abul | +0.108 |
ⓘ | +0.107 |
Neg logit contributions | |
recept | -0.111 |
acht | -0.108 |
xxxxxxxx | -0.103 |
phabet | -0.103 |
ieth | -0.100 |
Token | )). |
Token ID | 29720 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
recept | +0.060 |
acht | +0.059 |
xxxxxxxx | +0.056 |
phabet | +0.056 |
ieth | +0.055 |
Neg logit contributions | |
anamo | -0.076 |
DCS | -0.070 |
Salvador | -0.069 |
abul | -0.068 |
ⓘ | -0.068 |
Token | This |
Token ID | 770 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
anamo | +0.304 |
DCS | +0.279 |
abul | +0.273 |
Salvador | +0.270 |
ⓘ | +0.268 |
Neg logit contributions | |
recept | -0.237 |
acht | -0.232 |
xxxxxxxx | -0.223 |
phabet | -0.219 |
ieth | -0.215 |
Token | comparison |
Token ID | 7208 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
anamo | +0.655 |
DCS | +0.608 |
abul | +0.593 |
Salvador | +0.593 |
ⓘ | +0.588 |
Neg logit contributions | |
recept | -0.438 |
acht | -0.426 |
xxxxxxxx | -0.404 |
phabet | -0.402 |
ieth | -0.391 |
Token | is |
Token ID | 318 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
anamo | +0.734 |
DCS | +0.687 |
Salvador | +0.672 |
abul | +0.670 |
ⓘ | +0.666 |
Neg logit contributions | |
recept | -0.445 |
acht | -0.434 |
xxxxxxxx | -0.410 |
phabet | -0.408 |
ieth | -0.395 |
Token | sensitive |
Token ID | 8564 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
anamo | +0.463 |
DCS | +0.427 |
Salvador | +0.415 |
abul | +0.414 |
ⓘ | +0.411 |
Neg logit contributions | |
recept | -0.416 |
acht | -0.408 |
xxxxxxxx | -0.389 |
phabet | -0.387 |
ieth | -0.379 |
Token | to |
Token ID | 284 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
anamo | +0.207 |
DCS | +0.193 |
Salvador | +0.190 |
abul | +0.189 |
ⓘ | +0.188 |
Neg logit contributions | |
recept | -0.133 |
acht | -0.130 |
xxxxxxxx | -0.123 |
phabet | -0.123 |
ieth | -0.119 |
Token | how |
Token ID | 703 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
anamo | +0.147 |
DCS | +0.136 |
Salvador | +0.133 |
abul | +0.132 |
ⓘ | +0.131 |
Neg logit contributions | |
recept | -0.126 |
acht | -0.123 |
xxxxxxxx | -0.118 |
phabet | -0.117 |
ieth | -0.114 |
Token | occupational |
Token ID | 34266 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
anamo | +1.247 |
DCS | +1.149 |
Salvador | +1.121 |
abul | +1.115 |
ⓘ | +1.107 |
Neg logit contributions | |
recept | -1.152 |
acht | -1.131 |
xxxxxxxx | -1.081 |
phabet | -1.078 |
ieth | -1.051 |
Token | categories |
Token ID | 9376 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
recept | +0.142 |
acht | +0.137 |
phabet | +0.131 |
xxxxxxxx | +0.131 |
ieth | +0.127 |
Neg logit contributions | |
anamo | -0.180 |
DCS | -0.166 |
abul | -0.162 |
Salvador | -0.162 |
ⓘ | -0.161 |
Token | are |
Token ID | 389 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
recept | +0.208 |
acht | +0.204 |
xxxxxxxx | +0.193 |
phabet | +0.192 |
ieth | +0.187 |
Neg logit contributions | |
anamo | -0.281 |
DCS | -0.260 |
Salvador | -0.254 |
abul | -0.252 |
ⓘ | -0.251 |
Token | defined |
Token ID | 5447 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
anamo | +0.269 |
DCS | +0.249 |
Salvador | +0.245 |
abul | +0.242 |
ⓘ | +0.241 |
Neg logit contributions | |
recept | -0.238 |
acht | -0.235 |
xxxxxxxx | -0.224 |
phabet | -0.223 |
ieth | -0.217 |
Token | with |
Token ID | 351 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
recept | +0.334 |
acht | +0.329 |
xxxxxxxx | +0.313 |
phabet | +0.307 |
ieth | +0.302 |
Neg logit contributions | |
anamo | -0.428 |
DCS | -0.391 |
abul | -0.385 |
Salvador | -0.381 |
ⓘ | -0.378 |
Token | his |
Token ID | 465 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
anamo | +0.322 |
DCS | +0.294 |
abul | +0.285 |
Salvador | +0.282 |
ⓘ | +0.280 |
Neg logit contributions | |
recept | -0.320 |
acht | -0.314 |
xxxxxxxx | -0.300 |
phabet | -0.299 |
ieth | -0.292 |
Token | cousin |
Token ID | 16933 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
anamo | +0.294 |
DCS | +0.267 |
abul | +0.260 |
Salvador | +0.257 |
ⓘ | +0.256 |
Neg logit contributions | |
recept | -0.284 |
acht | -0.277 |
xxxxxxxx | -0.264 |
phabet | -0.261 |
ieth | -0.258 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
recept | +0.024 |
acht | +0.023 |
xxxxxxxx | +0.022 |
phabet | +0.022 |
ieth | +0.022 |
Neg logit contributions | |
anamo | -0.025 |
DCS | -0.023 |
Salvador | -0.023 |
abul | -0.023 |
ⓘ | -0.023 |
Token | Nikola |
Token ID | 47817 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
anamo | +0.172 |
DCS | +0.159 |
abul | +0.154 |
Salvador | +0.154 |
ⓘ | +0.152 |
Neg logit contributions | |
recept | -0.154 |
acht | -0.151 |
xxxxxxxx | -0.144 |
phabet | -0.144 |
ieth | -0.140 |
Token | Gr |
Token ID | 1902 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
recept | +0.486 |
acht | +0.480 |
phabet | +0.457 |
xxxxxxxx | +0.456 |
ieth | +0.446 |
Neg logit contributions | |
anamo | -0.532 |
DCS | -0.491 |
Salvador | -0.476 |
abul | -0.473 |
ⓘ | -0.470 |
Token | ue |
Token ID | 518 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
anamo | +1.863 |
DCS | +1.735 |
abul | +1.709 |
Salvador | +1.692 |
ⓘ | +1.677 |
Neg logit contributions | |
recept | -1.259 |
acht | -1.211 |
xxxxxxxx | -1.163 |
phabet | -1.153 |
ieth | -1.111 |
Token | vs |
Token ID | 14259 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
anamo | +0.290 |
DCS | +0.270 |
Salvador | +0.265 |
abul | +0.263 |
ⓘ | +0.262 |
Neg logit contributions | |
recept | -0.201 |
acht | -0.197 |
xxxxxxxx | -0.187 |
phabet | -0.186 |
ieth | -0.181 |
Token | ki |
Token ID | 4106 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
recept | +0.596 |
acht | +0.586 |
xxxxxxxx | +0.547 |
phabet | +0.544 |
ieth | +0.526 |
Neg logit contributions | |
anamo | -1.034 |
DCS | -0.966 |
Salvador | -0.947 |
abul | -0.942 |
ⓘ | -0.931 |
Token | , |
Token ID | 11 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
recept | +0.961 |
acht | +0.945 |
xxxxxxxx | +0.891 |
phabet | +0.888 |
ieth | +0.865 |
Neg logit contributions | |
anamo | -1.315 |
DCS | -1.221 |
Salvador | -1.193 |
abul | -1.186 |
ⓘ | -1.176 |
Token | former |
Token ID | 1966 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
anamo | +0.259 |
DCS | +0.241 |
abul | +0.235 |
Salvador | +0.235 |
ⓘ | +0.232 |
Neg logit contributions | |
recept | -0.180 |
acht | -0.176 |
xxxxxxxx | -0.166 |
phabet | -0.165 |
ieth | -0.161 |
Token | locks |
Token ID | 28860 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
anamo | +0.014 |
DCS | +0.013 |
Salvador | +0.012 |
abul | +0.012 |
ⓘ | +0.012 |
Neg logit contributions | |
recept | -0.022 |
acht | -0.022 |
xxxxxxxx | -0.021 |
phabet | -0.021 |
ieth | -0.020 |
Token | do |
Token ID | 466 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
anamo | +0.669 |
DCS | +0.617 |
Salvador | +0.602 |
abul | +0.599 |
ⓘ | +0.594 |
Neg logit contributions | |
recept | -0.613 |
acht | -0.602 |
xxxxxxxx | -0.576 |
phabet | -0.573 |
ieth | -0.559 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
recept | +0.587 |
acht | +0.576 |
xxxxxxxx | +0.546 |
phabet | +0.542 |
ieth | +0.524 |
Neg logit contributions | |
anamo | -0.883 |
DCS | -0.824 |
Salvador | -0.803 |
abul | -0.802 |
ⓘ | -0.795 |
Token |
|
Token ID | 198 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
recept | +0.360 |
acht | +0.354 |
xxxxxxxx | +0.343 |
phabet | +0.333 |
ieth | +0.328 |
Neg logit contributions | |
anamo | -0.456 |
DCS | -0.417 |
abul | -0.409 |
sole | -0.402 |
Salvador | -0.402 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
recept | +0.422 |
acht | +0.414 |
xxxxxxxx | +0.394 |
phabet | +0.389 |
ieth | +0.379 |
Neg logit contributions | |
anamo | -0.619 |
DCS | -0.574 |
Salvador | -0.563 |
abul | -0.561 |
ⓘ | -0.556 |
Token | So |
Token ID | 2396 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
recept | +0.293 |
acht | +0.289 |
xxxxxxxx | +0.278 |
phabet | +0.275 |
ieth | +0.268 |
Neg logit contributions | |
anamo | -0.337 |
DCS | -0.308 |
Salvador | -0.303 |
abul | -0.301 |
ⓘ | -0.301 |
Token | we |
Token ID | 356 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
recept | +0.293 |
acht | +0.287 |
xxxxxxxx | +0.271 |
phabet | +0.271 |
ieth | +0.263 |
Neg logit contributions | |
anamo | -0.403 |
DCS | -0.374 |
abul | -0.366 |
Salvador | -0.364 |
ⓘ | -0.364 |
Token | had |
Token ID | 550 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
anamo | +0.223 |
DCS | +0.207 |
Salvador | +0.203 |
abul | +0.202 |
ⓘ | +0.201 |
Neg logit contributions | |
recept | -0.141 |
acht | -0.138 |
xxxxxxxx | -0.130 |
phabet | -0.129 |
ieth | -0.125 |
Token | you |
Token ID | 345 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
recept | +0.601 |
acht | +0.586 |
xxxxxxxx | +0.553 |
phabet | +0.547 |
ieth | +0.534 |
Neg logit contributions | |
anamo | -0.820 |
DCS | -0.760 |
abul | -0.740 |
Salvador | -0.735 |
ⓘ | -0.733 |
Token | can |
Token ID | 460 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
recept | +0.456 |
acht | +0.442 |
xxxxxxxx | +0.422 |
phabet | +0.415 |
ieth | +0.407 |
Neg logit contributions | |
anamo | -0.562 |
DCS | -0.519 |
abul | -0.505 |
Salvador | -0.503 |
ⓘ | -0.499 |
Token | summon |
Token ID | 11457 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
anamo | +0.282 |
DCS | +0.260 |
Salvador | +0.254 |
abul | +0.252 |
ⓘ | +0.252 |
Neg logit contributions | |
recept | -0.232 |
acht | -0.227 |
xxxxxxxx | -0.216 |
phabet | -0.215 |
ieth | -0.209 |
Token | Kirby |
Token ID | 23965 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
recept | +0.260 |
acht | +0.256 |
xxxxxxxx | +0.245 |
phabet | +0.243 |
ieth | +0.239 |
Neg logit contributions | |
anamo | -0.264 |
DCS | -0.241 |
abul | -0.236 |
Salvador | -0.233 |
ⓘ | -0.231 |
Token | and |
Token ID | 290 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
anamo | +0.692 |
DCS | +0.640 |
Salvador | +0.626 |
abul | +0.621 |
ⓘ | +0.618 |
Neg logit contributions | |
recept | -0.617 |
acht | -0.606 |
xxxxxxxx | -0.579 |
phabet | -0.578 |
ieth | -0.562 |
Token | Richmond |
Token ID | 16940 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
recept | +0.050 |
acht | +0.050 |
xxxxxxxx | +0.047 |
phabet | +0.047 |
ieth | +0.046 |
Neg logit contributions | |
anamo | -0.050 |
DCS | -0.046 |
abul | -0.045 |
Salvador | -0.045 |
ⓘ | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
anamo | +0.335 |
DCS | +0.311 |
Salvador | +0.305 |
abul | +0.303 |
ⓘ | +0.302 |
Neg logit contributions | |
recept | -0.245 |
acht | -0.240 |
xxxxxxxx | -0.229 |
phabet | -0.228 |
ieth | -0.221 |
Token | Needless |
Token ID | 39114 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
recept | +0.117 |
acht | +0.115 |
xxxxxxxx | +0.110 |
phabet | +0.108 |
ieth | +0.106 |
Neg logit contributions | |
anamo | -0.145 |
DCS | -0.134 |
abul | -0.131 |
Salvador | -0.130 |
ⓘ | -0.129 |
Token | to |
Token ID | 284 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
recept | +0.079 |
acht | +0.077 |
xxxxxxxx | +0.073 |
phabet | +0.072 |
ieth | +0.070 |
Neg logit contributions | |
anamo | -0.126 |
DCS | -0.118 |
Salvador | -0.115 |
abul | -0.115 |
ⓘ | -0.114 |
Token | say |
Token ID | 910 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
recept | +0.197 |
acht | +0.194 |
xxxxxxxx | +0.184 |
phabet | +0.183 |
ieth | +0.179 |
Neg logit contributions | |
anamo | -0.242 |
DCS | -0.224 |
Salvador | -0.217 |
abul | -0.217 |
ⓘ | -0.215 |
Token | , |
Token ID | 11 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
recept | +0.204 |
acht | +0.201 |
phabet | +0.191 |
xxxxxxxx | +0.191 |
ieth | +0.185 |
Neg logit contributions | |
anamo | -0.261 |
DCS | -0.242 |
Salvador | -0.238 |
abul | -0.235 |
ⓘ | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
recept | +0.139 |
acht | +0.136 |
xxxxxxxx | +0.130 |
phabet | +0.129 |
ieth | +0.125 |
Neg logit contributions | |
anamo | -0.178 |
DCS | -0.165 |
abul | -0.161 |
Salvador | -0.161 |
ⓘ | -0.159 |
Token | curse |
Token ID | 17328 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
anamo | +0.004 |
DCS | +0.004 |
Salvador | +0.004 |
abul | +0.004 |
ⓘ | +0.004 |
Neg logit contributions | |
recept | -0.003 |
acht | -0.003 |
xxxxxxxx | -0.003 |
phabet | -0.003 |
ieth | -0.003 |
Token | has |
Token ID | 468 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
recept | +0.206 |
acht | +0.202 |
xxxxxxxx | +0.190 |
phabet | +0.189 |
ieth | +0.183 |
Neg logit contributions | |
anamo | -0.338 |
DCS | -0.316 |
Salvador | -0.309 |
abul | -0.308 |
ⓘ | -0.306 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
recept | +0.101 |
acht | +0.099 |
xxxxxxxx | +0.094 |
phabet | +0.094 |
ieth | +0.091 |
Neg logit contributions | |
anamo | -0.128 |
DCS | -0.119 |
Salvador | -0.116 |
abul | -0.116 |
ⓘ | -0.115 |
Token | 17 |
Token ID | 1596 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
recept | +0.110 |
acht | +0.107 |
xxxxxxxx | +0.102 |
phabet | +0.101 |
ieth | +0.099 |
Neg logit contributions | |
anamo | -0.131 |
DCS | -0.121 |
abul | -0.118 |
Salvador | -0.117 |
ⓘ | -0.116 |
Token | - |
Token ID | 12 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
recept | +0.105 |
acht | +0.102 |
xxxxxxxx | +0.094 |
phabet | +0.094 |
ieth | +0.089 |
Neg logit contributions | |
anamo | -0.286 |
DCS | -0.271 |
Salvador | -0.267 |
abul | -0.265 |
ⓘ | -0.264 |
Token | 40 |
Token ID | 1821 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
recept | +0.203 |
acht | +0.200 |
xxxxxxxx | +0.191 |
phabet | +0.190 |
ieth | +0.185 |
Neg logit contributions | |
anamo | -0.247 |
DCS | -0.228 |
Salvador | -0.223 |
abul | -0.222 |
ⓘ | -0.220 |
Token | f |
Token ID | 277 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
recept | +0.575 |
acht | +0.560 |
xxxxxxxx | +0.527 |
phabet | +0.523 |
ieth | +0.507 |
Neg logit contributions | |
anamo | -1.099 |
DCS | -1.028 |
Salvador | -1.009 |
abul | -1.006 |
ⓘ | -0.998 |
Token | / |
Token ID | 14 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
recept | +0.143 |
acht | +0.140 |
xxxxxxxx | +0.133 |
phabet | +0.132 |
ieth | +0.128 |
Neg logit contributions | |
anamo | -0.200 |
DCS | -0.186 |
Salvador | -0.182 |
abul | -0.181 |
ⓘ | -0.180 |
Token | 4 |
Token ID | 19 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
recept | +1.619 |
acht | +1.599 |
xxxxxxxx | +1.540 |
phabet | +1.499 |
ieth | +1.485 |
Neg logit contributions | |
anamo | -2.173 |
DCS | -1.968 |
Salvador | -1.937 |
abul | -1.925 |
ⓘ | -1.910 |
Token | , |
Token ID | 11 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
recept | +0.034 |
acht | +0.034 |
xxxxxxxx | +0.032 |
phabet | +0.032 |
ieth | +0.031 |
Neg logit contributions | |
anamo | -0.048 |
DCS | -0.045 |
Salvador | -0.044 |
abul | -0.044 |
ⓘ | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | -8.29e-02 |
Pos logit contributions | |
recept | +0.035 |
acht | +0.035 |
xxxxxxxx | +0.033 |
phabet | +0.033 |
ieth | +0.032 |
Neg logit contributions | |
anamo | -0.041 |
DCS | -0.037 |
abul | -0.036 |
Salvador | -0.036 |
ⓘ | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
recept | +0.051 |
acht | +0.050 |
xxxxxxxx | +0.047 |
phabet | +0.047 |
ieth | +0.046 |
Neg logit contributions | |
anamo | -0.073 |
DCS | -0.068 |
Salvador | -0.066 |
abul | -0.066 |
ⓘ | -0.065 |
Token | Four |
Token ID | 15137 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
anamo | +0.089 |
DCS | +0.080 |
Salvador | +0.079 |
abul | +0.078 |
ⓘ | +0.078 |
Neg logit contributions | |
recept | -0.096 |
acht | -0.095 |
xxxxxxxx | -0.092 |
phabet | -0.091 |
ieth | -0.089 |
Token | to |
Token ID | 284 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
recept | +0.673 |
acht | +0.656 |
xxxxxxxx | +0.617 |
phabet | +0.614 |
ieth | +0.598 |
Neg logit contributions | |
anamo | -0.963 |
DCS | -0.896 |
abul | -0.868 |
Salvador | -0.868 |
ⓘ | -0.862 |
Token | minimize |
Token ID | 17775 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
recept | +0.215 |
acht | +0.211 |
xxxxxxxx | +0.199 |
phabet | +0.198 |
ieth | +0.191 |
Neg logit contributions | |
anamo | -0.273 |
DCS | -0.252 |
abul | -0.245 |
Salvador | -0.244 |
ⓘ | -0.243 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
anamo | +1.284 |
DCS | +1.194 |
Salvador | +1.171 |
abul | +1.161 |
ⓘ | +1.158 |
Neg logit contributions | |
recept | -1.041 |
acht | -1.026 |
xxxxxxxx | -0.980 |
phabet | -0.978 |
ieth | -0.948 |
Token | use |
Token ID | 779 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
recept | +0.108 |
acht | +0.105 |
xxxxxxxx | +0.099 |
phabet | +0.099 |
ieth | +0.097 |
Neg logit contributions | |
anamo | -0.119 |
DCS | -0.109 |
abul | -0.106 |
Salvador | -0.105 |
ⓘ | -0.104 |
Token | of |
Token ID | 286 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
recept | +0.862 |
acht | +0.842 |
xxxxxxxx | +0.790 |
phabet | +0.789 |
ieth | +0.761 |
Neg logit contributions | |
anamo | -1.540 |
DCS | -1.445 |
Salvador | -1.415 |
abul | -1.410 |
ⓘ | -1.400 |
Token | L |
Token ID | 406 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
recept | +0.171 |
acht | +0.166 |
xxxxxxxx | +0.157 |
phabet | +0.155 |
ieth | +0.152 |
Neg logit contributions | |
anamo | -0.236 |
DCS | -0.218 |
abul | -0.213 |
Salvador | -0.212 |
ⓘ | -0.210 |
Token | NG |
Token ID | 10503 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
recept | +0.115 |
acht | +0.114 |
xxxxxxxx | +0.107 |
phabet | +0.107 |
ieth | +0.104 |
Neg logit contributions | |
anamo | -0.156 |
DCS | -0.144 |
Salvador | -0.142 |
abul | -0.141 |
ⓘ | -0.140 |
Token | for |
Token ID | 329 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
recept | +0.122 |
acht | +0.119 |
xxxxxxxx | +0.112 |
phabet | +0.112 |
ieth | +0.109 |
Neg logit contributions | |
anamo | -0.163 |
DCS | -0.152 |
Salvador | -0.148 |
abul | -0.147 |
ⓘ | -0.146 |
Token | anything |
Token ID | 1997 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
recept | +0.201 |
acht | +0.196 |
xxxxxxxx | +0.186 |
phabet | +0.185 |
ieth | +0.181 |
Neg logit contributions | |
anamo | -0.244 |
DCS | -0.225 |
abul | -0.219 |
Salvador | -0.219 |
ⓘ | -0.216 |
Token | other |
Token ID | 584 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
anamo | +0.880 |
DCS | +0.810 |
Salvador | +0.791 |
abul | +0.786 |
ⓘ | +0.780 |
Neg logit contributions | |
recept | -0.858 |
acht | -0.844 |
xxxxxxxx | -0.808 |
phabet | -0.805 |
ieth | -0.785 |
Token | than |
Token ID | 621 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
recept | +0.146 |
acht | +0.142 |
xxxxxxxx | +0.135 |
phabet | +0.134 |
ieth | +0.130 |
Neg logit contributions | |
anamo | -0.230 |
DCS | -0.215 |
Salvador | -0.210 |
abul | -0.210 |
ⓘ | -0.208 |
Token |
|
Token ID | 198 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
anamo | +0.163 |
DCS | +0.149 |
Salvador | +0.147 |
abul | +0.147 |
ⓘ | +0.145 |
Neg logit contributions | |
recept | -0.106 |
acht | -0.104 |
xxxxxxxx | -0.100 |
phabet | -0.097 |
ieth | -0.095 |
Token | On |
Token ID | 2202 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
anamo | +0.256 |
DCS | +0.233 |
Salvador | +0.229 |
abul | +0.228 |
ⓘ | +0.227 |
Neg logit contributions | |
recept | -0.227 |
acht | -0.225 |
xxxxxxxx | -0.216 |
phabet | -0.213 |
ieth | -0.209 |
Token | a |
Token ID | 257 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
anamo | +0.224 |
DCS | +0.204 |
abul | +0.198 |
Salvador | +0.198 |
ⓘ | +0.195 |
Neg logit contributions | |
recept | -0.226 |
acht | -0.223 |
xxxxxxxx | -0.213 |
phabet | -0.211 |
ieth | -0.208 |
Token | dramatic |
Token ID | 10092 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
anamo | +0.448 |
DCS | +0.409 |
abul | +0.400 |
Salvador | +0.397 |
ⓘ | +0.394 |
Neg logit contributions | |
recept | -0.392 |
acht | -0.383 |
xxxxxxxx | -0.365 |
phabet | -0.361 |
ieth | -0.355 |
Token | Friday |
Token ID | 3217 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
recept | +0.147 |
acht | +0.144 |
xxxxxxxx | +0.135 |
phabet | +0.133 |
ieth | +0.132 |
Neg logit contributions | |
anamo | -0.204 |
DCS | -0.186 |
abul | -0.183 |
Salvador | -0.181 |
ⓘ | -0.180 |
Token | night |
Token ID | 1755 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
recept | +0.407 |
acht | +0.400 |
xxxxxxxx | +0.372 |
phabet | +0.369 |
ieth | +0.361 |
Neg logit contributions | |
anamo | -0.680 |
DCS | -0.628 |
abul | -0.615 |
Salvador | -0.611 |
ⓘ | -0.606 |
Token | in |
Token ID | 287 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
recept | +0.194 |
acht | +0.191 |
xxxxxxxx | +0.180 |
phabet | +0.179 |
ieth | +0.175 |
Neg logit contributions | |
anamo | -0.266 |
DCS | -0.246 |
abul | -0.240 |
Salvador | -0.240 |
ⓘ | -0.238 |
Token | Macedonia |
Token ID | 36353 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
anamo | +0.307 |
DCS | +0.280 |
abul | +0.271 |
Salvador | +0.267 |
ⓘ | +0.265 |
Neg logit contributions | |
recept | -0.322 |
acht | -0.317 |
xxxxxxxx | -0.302 |
phabet | -0.299 |
ieth | -0.294 |
Token | , |
Token ID | 11 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
anamo | +2.467 |
DCS | +2.297 |
Salvador | +2.271 |
abul | +2.231 |
ⓘ | +2.229 |
Neg logit contributions | |
recept | -1.976 |
acht | -1.920 |
xxxxxxxx | -1.857 |
phabet | -1.843 |
ieth | -1.783 |
Token | Chief |
Token ID | 5953 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
anamo | +0.357 |
DCS | +0.330 |
Salvador | +0.321 |
abul | +0.321 |
ⓘ | +0.317 |
Neg logit contributions | |
recept | -0.316 |
acht | -0.310 |
xxxxxxxx | -0.296 |
phabet | -0.295 |
ieth | -0.287 |
Token | Special |
Token ID | 6093 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
anamo | +0.501 |
DCS | +0.458 |
Salvador | +0.449 |
abul | +0.444 |
ⓘ | +0.442 |
Neg logit contributions | |
recept | -0.544 |
acht | -0.535 |
xxxxxxxx | -0.513 |
phabet | -0.512 |
ieth | -0.500 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
recept | +0.770 |
acht | +0.755 |
xxxxxxxx | +0.715 |
phabet | +0.713 |
ieth | +0.689 |
Neg logit contributions | |
anamo | -1.158 |
DCS | -1.079 |
Salvador | -1.055 |
abul | -1.051 |
ⓘ | -1.044 |
Token |
|
Token ID | 198 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
recept | +0.134 |
acht | +0.131 |
xxxxxxxx | +0.126 |
phabet | +0.124 |
ieth | +0.120 |
Neg logit contributions | |
anamo | -0.191 |
DCS | -0.177 |
Salvador | -0.173 |
abul | -0.173 |
ⓘ | -0.171 |
Token |
|
Token ID | 198 |
Feature activation | -9.20e-03 |
Pos logit contributions | |
recept | +0.096 |
acht | +0.094 |
xxxxxxxx | +0.090 |
phabet | +0.089 |
ieth | +0.087 |
Neg logit contributions | |
anamo | -0.138 |
DCS | -0.128 |
Salvador | -0.126 |
abul | -0.125 |
ⓘ | -0.124 |
Token | A |
Token ID | 32 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
recept | +0.006 |
acht | +0.006 |
xxxxxxxx | +0.006 |
phabet | +0.006 |
ieth | +0.006 |
Neg logit contributions | |
anamo | -0.007 |
DCS | -0.007 |
Salvador | -0.007 |
abul | -0.006 |
ⓘ | -0.006 |
Token | new |
Token ID | 649 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
recept | +0.125 |
acht | +0.123 |
xxxxxxxx | +0.117 |
phabet | +0.117 |
ieth | +0.113 |
Neg logit contributions | |
anamo | -0.154 |
DCS | -0.142 |
Salvador | -0.139 |
abul | -0.139 |
ⓘ | -0.137 |
Token | destiny |
Token ID | 22701 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
recept | +0.214 |
acht | +0.208 |
xxxxxxxx | +0.198 |
phabet | +0.197 |
ieth | +0.192 |
Neg logit contributions | |
anamo | -0.270 |
DCS | -0.250 |
abul | -0.242 |
Salvador | -0.242 |
ⓘ | -0.239 |
Token | awaits |
Token ID | 37180 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
recept | +1.708 |
acht | +1.670 |
xxxxxxxx | +1.581 |
phabet | +1.501 |
ieth | +1.490 |
Neg logit contributions | |
anamo | -3.506 |
DCS | -3.298 |
abul | -3.210 |
Salvador | -3.205 |
ⓘ | -3.168 |
Token | you |
Token ID | 345 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
recept | +0.308 |
acht | +0.301 |
xxxxxxxx | +0.286 |
phabet | +0.284 |
ieth | +0.276 |
Neg logit contributions | |
anamo | -0.461 |
DCS | -0.430 |
Salvador | -0.420 |
abul | -0.419 |
ⓘ | -0.416 |
Token | in |
Token ID | 287 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
recept | +0.274 |
acht | +0.269 |
xxxxxxxx | +0.255 |
phabet | +0.252 |
ieth | +0.245 |
Neg logit contributions | |
anamo | -0.423 |
DCS | -0.395 |
Salvador | -0.386 |
abul | -0.385 |
ⓘ | -0.382 |
Token | the |
Token ID | 262 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
recept | +0.173 |
acht | +0.169 |
xxxxxxxx | +0.161 |
phabet | +0.160 |
ieth | +0.155 |
Neg logit contributions | |
anamo | -0.229 |
DCS | -0.212 |
Salvador | -0.207 |
abul | -0.207 |
ⓘ | -0.204 |
Token | sky |
Token ID | 6766 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
recept | +0.030 |
acht | +0.030 |
xxxxxxxx | +0.028 |
phabet | +0.028 |
ieth | +0.027 |
Neg logit contributions | |
anamo | -0.037 |
DCS | -0.034 |
abul | -0.033 |
Salvador | -0.033 |
ⓘ | -0.033 |
Token | grand |
Token ID | 4490 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
anamo | +0.143 |
DCS | +0.131 |
abul | +0.127 |
Salvador | +0.127 |
ⓘ | +0.125 |
Neg logit contributions | |
recept | -0.140 |
acht | -0.136 |
xxxxxxxx | -0.131 |
phabet | -0.130 |
ieth | -0.127 |
Token | total |
Token ID | 2472 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
recept | +0.469 |
acht | +0.455 |
phabet | +0.423 |
xxxxxxxx | +0.421 |
ieth | +0.416 |
Neg logit contributions | |
anamo | -0.804 |
DCS | -0.751 |
Salvador | -0.735 |
abul | -0.733 |
ⓘ | -0.725 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
recept | +0.685 |
acht | +0.663 |
xxxxxxxx | +0.614 |
phabet | +0.611 |
ieth | +0.598 |
Neg logit contributions | |
anamo | -1.254 |
DCS | -1.163 |
Salvador | -1.139 |
abul | -1.137 |
sole | -1.124 |
Token | zero |
Token ID | 6632 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
recept | +0.129 |
acht | +0.126 |
xxxxxxxx | +0.120 |
phabet | +0.119 |
ieth | +0.117 |
Neg logit contributions | |
anamo | -0.119 |
DCS | -0.108 |
abul | -0.105 |
Salvador | -0.103 |
ⓘ | -0.102 |
Token | gig |
Token ID | 12526 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
recept | +0.371 |
acht | +0.361 |
xxxxxxxx | +0.340 |
phabet | +0.337 |
ieth | +0.332 |
Neg logit contributions | |
anamo | -0.465 |
DCS | -0.426 |
abul | -0.415 |
Salvador | -0.415 |
sole | -0.410 |
Token | awatts |
Token ID | 46684 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
recept | +1.382 |
acht | +1.370 |
xxxxxxxx | +1.296 |
phabet | +1.290 |
ieth | +1.261 |
Neg logit contributions | |
anamo | -1.281 |
DCS | -1.178 |
Salvador | -1.150 |
ⓘ | -1.132 |
sole | -1.122 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
recept | +2.176 |
acht | +2.134 |
xxxxxxxx | +1.950 |
phabet | +1.944 |
ieth | +1.923 |
Neg logit contributions | |
anamo | -3.447 |
DCS | -3.171 |
abul | -3.082 |
Salvador | -3.049 |
sole | -3.047 |
Token | But |
Token ID | 887 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
recept | +0.156 |
acht | +0.154 |
xxxxxxxx | +0.147 |
phabet | +0.145 |
ieth | +0.142 |
Neg logit contributions | |
anamo | -0.191 |
DCS | -0.175 |
abul | -0.172 |
Salvador | -0.169 |
sole | -0.168 |
Token | knowing |
Token ID | 6970 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
anamo | +0.790 |
DCS | +0.732 |
Salvador | +0.718 |
abul | +0.712 |
ⓘ | +0.708 |
Neg logit contributions | |
recept | -0.643 |
acht | -0.632 |
xxxxxxxx | -0.603 |
phabet | -0.601 |
ieth | -0.584 |
Token | that |
Token ID | 326 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
anamo | +1.475 |
DCS | +1.372 |
Salvador | +1.343 |
abul | +1.332 |
ⓘ | +1.325 |
Neg logit contributions | |
recept | -1.186 |
acht | -1.167 |
xxxxxxxx | -1.112 |
phabet | -1.112 |
ieth | -1.079 |
Token | a |
Token ID | 257 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
anamo | +0.139 |
DCS | +0.128 |
abul | +0.125 |
Salvador | +0.124 |
ⓘ | +0.123 |
Neg logit contributions | |
recept | -0.115 |
acht | -0.112 |
xxxxxxxx | -0.106 |
phabet | -0.105 |
ieth | -0.103 |
Token | � |
Token ID | 447 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
recept | +0.333 |
acht | +0.331 |
xxxxxxxx | +0.320 |
phabet | +0.315 |
ieth | +0.311 |
Neg logit contributions | |
anamo | -0.244 |
DCS | -0.217 |
Salvador | -0.211 |
abul | -0.210 |
ⓘ | -0.207 |
Token | � |
Token ID | 247 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
recept | +0.151 |
acht | +0.149 |
xxxxxxxx | +0.142 |
phabet | +0.141 |
ieth | +0.137 |
Neg logit contributions | |
anamo | -0.166 |
DCS | -0.153 |
Salvador | -0.148 |
abul | -0.148 |
ⓘ | -0.146 |
Token | t |
Token ID | 83 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
recept | +0.104 |
acht | +0.102 |
xxxxxxxx | +0.097 |
phabet | +0.096 |
ieth | +0.094 |
Neg logit contributions | |
anamo | -0.145 |
DCS | -0.135 |
Salvador | -0.133 |
abul | -0.132 |
ⓘ | -0.131 |
Token | seen |
Token ID | 1775 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
anamo | +0.652 |
DCS | +0.608 |
Salvador | +0.595 |
abul | +0.592 |
ⓘ | +0.588 |
Neg logit contributions | |
recept | -0.440 |
acht | -0.431 |
xxxxxxxx | -0.408 |
phabet | -0.405 |
ieth | -0.394 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
anamo | +0.484 |
DCS | +0.448 |
Salvador | +0.436 |
abul | +0.435 |
ⓘ | +0.431 |
Neg logit contributions | |
recept | -0.411 |
acht | -0.402 |
xxxxxxxx | -0.384 |
phabet | -0.383 |
ieth | -0.373 |
Token | weapons |
Token ID | 3777 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
anamo | +0.012 |
DCS | +0.011 |
Salvador | +0.011 |
abul | +0.011 |
ⓘ | +0.011 |
Neg logit contributions | |
recept | -0.010 |
acht | -0.010 |
xxxxxxxx | -0.010 |
phabet | -0.010 |
ieth | -0.009 |
Token | viewed |
Token ID | 9569 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
recept | +2.185 |
acht | +2.104 |
xxxxxxxx | +1.973 |
phabet | +1.925 |
ieth | +1.920 |
Neg logit contributions | |
anamo | -2.946 |
DCS | -2.754 |
abul | -2.658 |
Salvador | -2.628 |
ⓘ | -2.625 |
Token | in |
Token ID | 287 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
anamo | +0.478 |
DCS | +0.443 |
Salvador | +0.432 |
abul | +0.430 |
ⓘ | +0.427 |
Neg logit contributions | |
recept | -0.388 |
acht | -0.380 |
xxxxxxxx | -0.362 |
phabet | -0.361 |
ieth | -0.351 |
Token | exactly |
Token ID | 3446 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
anamo | +0.312 |
DCS | +0.290 |
abul | +0.282 |
Salvador | +0.282 |
ⓘ | +0.280 |
Neg logit contributions | |
recept | -0.239 |
acht | -0.233 |
xxxxxxxx | -0.222 |
phabet | -0.221 |
ieth | -0.215 |
Token | this |
Token ID | 428 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
recept | +0.937 |
acht | +0.900 |
phabet | +0.860 |
xxxxxxxx | +0.858 |
ieth | +0.833 |
Neg logit contributions | |
anamo | -1.360 |
DCS | -1.253 |
abul | -1.218 |
ⓘ | -1.213 |
Salvador | -1.208 |
Token | light |
Token ID | 1657 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
anamo | +0.598 |
DCS | +0.556 |
Salvador | +0.544 |
abul | +0.542 |
ⓘ | +0.538 |
Neg logit contributions | |
recept | -0.422 |
acht | -0.413 |
xxxxxxxx | -0.392 |
phabet | -0.390 |
ieth | -0.379 |
Token | mitigation |
Token ID | 33585 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
recept | +0.031 |
acht | +0.030 |
xxxxxxxx | +0.029 |
phabet | +0.029 |
ieth | +0.028 |
Neg logit contributions | |
anamo | -0.038 |
DCS | -0.036 |
Salvador | -0.035 |
abul | -0.035 |
ⓘ | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
recept | +0.461 |
acht | +0.447 |
xxxxxxxx | +0.424 |
phabet | +0.420 |
ieth | +0.411 |
Neg logit contributions | |
anamo | -0.625 |
DCS | -0.578 |
abul | -0.563 |
Salvador | -0.562 |
ⓘ | -0.556 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
recept | +0.038 |
acht | +0.037 |
xxxxxxxx | +0.035 |
phabet | +0.035 |
ieth | +0.034 |
Neg logit contributions | |
anamo | -0.058 |
DCS | -0.054 |
abul | -0.053 |
Salvador | -0.053 |
ⓘ | -0.052 |
Token | greenhouse |
Token ID | 16325 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
recept | +0.148 |
acht | +0.143 |
xxxxxxxx | +0.136 |
phabet | +0.134 |
ieth | +0.133 |
Neg logit contributions | |
anamo | -0.163 |
DCS | -0.150 |
abul | -0.146 |
Salvador | -0.144 |
ⓘ | -0.143 |
Token | gas |
Token ID | 3623 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
recept | +0.300 |
acht | +0.294 |
xxxxxxxx | +0.282 |
phabet | +0.281 |
ieth | +0.273 |
Neg logit contributions | |
anamo | -0.354 |
DCS | -0.326 |
Salvador | -0.321 |
abul | -0.317 |
ⓘ | -0.316 |
Token | emissions |
Token ID | 8971 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
recept | +0.681 |
acht | +0.660 |
xxxxxxxx | +0.619 |
phabet | +0.610 |
ieth | +0.609 |
Neg logit contributions | |
anamo | -0.852 |
DCS | -0.793 |
abul | -0.773 |
Salvador | -0.763 |
ⓘ | -0.757 |
Token | that |
Token ID | 326 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
recept | +2.282 |
acht | +2.207 |
xxxxxxxx | +2.062 |
ieth | +2.031 |
phabet | +1.999 |
Neg logit contributions | |
anamo | -3.168 |
DCS | -2.925 |
abul | -2.846 |
ⓘ | -2.764 |
Salvador | -2.764 |
Token | would |
Token ID | 561 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
recept | +0.362 |
acht | +0.355 |
xxxxxxxx | +0.331 |
phabet | +0.328 |
ieth | +0.322 |
Neg logit contributions | |
anamo | -0.505 |
DCS | -0.467 |
abul | -0.454 |
Salvador | -0.452 |
ⓘ | -0.448 |
Token | make |
Token ID | 787 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
anamo | +0.085 |
DCS | +0.079 |
Salvador | +0.077 |
abul | +0.076 |
ⓘ | +0.076 |
Neg logit contributions | |
recept | -0.072 |
acht | -0.071 |
xxxxxxxx | -0.067 |
phabet | -0.067 |
ieth | -0.065 |
Token | global |
Token ID | 3298 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
recept | +0.022 |
acht | +0.022 |
xxxxxxxx | +0.021 |
phabet | +0.021 |
ieth | +0.020 |
Neg logit contributions | |
anamo | -0.030 |
DCS | -0.028 |
abul | -0.027 |
Salvador | -0.027 |
ⓘ | -0.027 |
Token | warming |
Token ID | 9917 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
recept | +1.607 |
acht | +1.494 |
xxxxxxxx | +1.405 |
ieth | +1.380 |
phabet | +1.371 |
Neg logit contributions | |
anamo | -3.029 |
DCS | -2.821 |
abul | -2.772 |
Salvador | -2.735 |
ⓘ | -2.719 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
recept | +0.107 |
acht | +0.105 |
phabet | +0.100 |
xxxxxxxx | +0.099 |
ieth | +0.096 |
Neg logit contributions | |
anamo | -0.150 |
DCS | -0.140 |
Salvador | -0.137 |
abul | -0.137 |
ⓘ | -0.136 |
Token | AP |
Token ID | 2969 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
anamo | +0.091 |
DCS | +0.082 |
Salvador | +0.081 |
abul | +0.081 |
ⓘ | +0.081 |
Neg logit contributions | |
recept | -0.080 |
acht | -0.079 |
xxxxxxxx | -0.077 |
phabet | -0.075 |
ieth | -0.073 |
Token | Photo |
Token ID | 5555 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
recept | +0.196 |
acht | +0.192 |
xxxxxxxx | +0.185 |
phabet | +0.183 |
ieth | +0.180 |
Neg logit contributions | |
anamo | -0.214 |
DCS | -0.198 |
abul | -0.193 |
Salvador | -0.192 |
ⓘ | -0.191 |
Token | / |
Token ID | 14 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
anamo | +0.301 |
DCS | +0.281 |
Salvador | +0.274 |
abul | +0.273 |
ⓘ | +0.272 |
Neg logit contributions | |
recept | -0.213 |
acht | -0.209 |
xxxxxxxx | -0.198 |
phabet | -0.197 |
ieth | -0.191 |
Token | Rick |
Token ID | 33048 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
recept | +1.297 |
acht | +1.290 |
xxxxxxxx | +1.257 |
phabet | +1.222 |
ieth | +1.196 |
Neg logit contributions | |
anamo | -1.273 |
DCS | -1.146 |
ⓘ | -1.132 |
abul | -1.131 |
Salvador | -1.115 |
Token | Bow |
Token ID | 9740 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
anamo | +0.871 |
DCS | +0.798 |
abul | +0.774 |
Salvador | +0.765 |
ⓘ | +0.763 |
Neg logit contributions | |
recept | -0.975 |
acht | -0.966 |
xxxxxxxx | -0.925 |
phabet | -0.923 |
ieth | -0.900 |
Token | mer |
Token ID | 647 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
acht | +2.770 |
recept | +2.693 |
phabet | +2.617 |
ieth | +2.574 |
xxxxxxxx | +2.559 |
Neg logit contributions | |
anamo | -3.328 |
DCS | -3.072 |
abul | -3.030 |
Jagu | -3.006 |
Salvador | -2.983 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-01 |
Pos logit contributions | |
anamo | +0.927 |
DCS | +0.852 |
Salvador | +0.844 |
abul | +0.830 |
ⓘ | +0.827 |
Neg logit contributions | |
recept | -0.761 |
acht | -0.745 |
xxxxxxxx | -0.713 |
phabet | -0.709 |
ieth | -0.691 |
Token |
|
Token ID | 198 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
anamo | +0.754 |
DCS | +0.712 |
Salvador | +0.697 |
ⓘ | +0.690 |
abul | +0.688 |
Neg logit contributions | |
recept | -0.579 |
acht | -0.564 |
phabet | -0.545 |
xxxxxxxx | -0.531 |
ieth | -0.521 |
Token | I |
Token ID | 40 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
anamo | +0.737 |
DCS | +0.675 |
Salvador | +0.663 |
abul | +0.658 |
ⓘ | +0.657 |
Neg logit contributions | |
recept | -0.648 |
acht | -0.639 |
xxxxxxxx | -0.618 |
phabet | -0.607 |
ieth | -0.593 |
Token | was |
Token ID | 373 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
anamo | +0.276 |
DCS | +0.257 |
Salvador | +0.252 |
abul | +0.251 |
ⓘ | +0.249 |
Neg logit contributions | |
recept | -0.178 |
acht | -0.175 |
xxxxxxxx | -0.166 |
phabet | -0.164 |
ieth | -0.159 |