Token | sun |
Token ID | 4252 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
Zig | +0.061 |
ousel | +0.061 |
girls | +0.057 |
zag | +0.054 |
lights | +0.054 |
Neg logit contributions | |
worry | -0.044 |
She | -0.042 |
herself | -0.042 |
permission | -0.041 |
pick | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
worry | +0.044 |
herself | +0.043 |
permission | +0.039 |
She | +0.039 |
Her | +0.038 |
Neg logit contributions | |
Zig | -0.079 |
ousel | -0.077 |
steep | -0.073 |
arium | -0.070 |
girls | -0.069 |
Token | One |
Token ID | 1881 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
She | +0.014 |
herself | +0.013 |
Her | +0.012 |
pick | +0.010 |
her | +0.010 |
Neg logit contributions | |
lights | -0.026 |
roles | -0.025 |
ousel | -0.025 |
arium | -0.025 |
works | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ousel | +0.074 |
Zig | +0.073 |
girls | +0.072 |
rob | +0.066 |
lights | +0.066 |
Neg logit contributions | |
worry | -0.055 |
permission | -0.047 |
herself | -0.047 |
Her | -0.047 |
She | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ousel | +0.054 |
lights | +0.051 |
arium | +0.050 |
girls | +0.049 |
steep | +0.048 |
Neg logit contributions | |
worry | -0.034 |
herself | -0.033 |
Her | -0.032 |
She | -0.031 |
her | -0.031 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
worry | +0.034 |
herself | +0.034 |
She | +0.033 |
her | +0.032 |
Her | +0.032 |
Neg logit contributions | |
ousel | -0.018 |
lights | -0.017 |
arium | -0.017 |
girls | -0.016 |
steep | -0.015 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
igators | +0.368 |
ousel | +0.357 |
rob | +0.355 |
steep | +0.348 |
floats | +0.338 |
Neg logit contributions | |
worry | -0.764 |
She | -0.754 |
Her | -0.751 |
herself | -0.739 |
M | -0.721 |
Token | 's |
Token ID | 338 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
Zig | +0.544 |
ousel | +0.532 |
girls | +0.511 |
rob | +0.499 |
steep | +0.497 |
Neg logit contributions | |
worry | -0.372 |
permission | -0.331 |
herself | -0.324 |
She | -0.316 |
Her | -0.312 |
Token | owner |
Token ID | 4870 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
worry | +0.104 |
permission | +0.098 |
herself | +0.092 |
Her | +0.090 |
She | +0.089 |
Neg logit contributions | |
ousel | -0.186 |
Zig | -0.182 |
steep | -0.171 |
rob | -0.168 |
arium | -0.168 |
Token | wanted |
Token ID | 2227 |
Feature activation | -8.74e-02 |
Pos logit contributions | |
Zig | +0.085 |
ousel | +0.085 |
steep | +0.079 |
girls | +0.076 |
lights | +0.074 |
Neg logit contributions | |
worry | -0.057 |
permission | -0.053 |
herself | -0.050 |
She | -0.049 |
Her | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | -7.70e-04 |
Pos logit contributions | |
permission | +0.123 |
worry | +0.117 |
herself | +0.112 |
her | +0.107 |
pick | +0.105 |
Neg logit contributions | |
ousel | -0.205 |
Zig | -0.190 |
lights | -0.184 |
steep | -0.183 |
arium | -0.180 |
Token | walking |
Token ID | 6155 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ousel | +0.012 |
Zig | +0.012 |
steep | +0.011 |
arium | +0.011 |
rob | +0.011 |
Neg logit contributions | |
worry | -0.009 |
permission | -0.009 |
herself | -0.008 |
pick | -0.008 |
Her | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
ousel | +0.287 |
rob | +0.275 |
sed | +0.267 |
Zig | +0.267 |
girls | +0.263 |
Neg logit contributions | |
herself | -0.123 |
worry | -0.113 |
her | -0.107 |
She | -0.104 |
permission | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
lights | +0.006 |
arium | +0.006 |
ousel | +0.005 |
rob | +0.005 |
works | +0.005 |
Neg logit contributions | |
She | -0.003 |
herself | -0.003 |
Her | -0.003 |
pick | -0.003 |
worry | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +8.29e-03 |
Pos logit contributions | |
ousel | +0.025 |
lights | +0.023 |
steep | +0.023 |
arium | +0.022 |
floats | +0.022 |
Neg logit contributions | |
She | -0.012 |
Her | -0.012 |
worry | -0.011 |
M | -0.011 |
herself | -0.011 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ousel | +0.018 |
Zig | +0.017 |
steep | +0.016 |
arium | +0.016 |
lights | +0.016 |
Neg logit contributions | |
worry | -0.012 |
Her | -0.011 |
She | -0.011 |
herself | -0.011 |
permission | -0.010 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
worry | +0.030 |
her | +0.025 |
herself | +0.024 |
She | +0.022 |
Her | +0.022 |
Neg logit contributions | |
ousel | -0.070 |
rob | -0.065 |
girls | -0.064 |
arium | -0.063 |
lights | -0.063 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
ousel | +0.287 |
igators | +0.286 |
steep | +0.279 |
rob | +0.273 |
Zig | +0.265 |
Neg logit contributions | |
worry | -0.841 |
Her | -0.823 |
She | -0.822 |
herself | -0.798 |
M | -0.798 |
Token | noticed |
Token ID | 6810 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
Zig | +0.549 |
ousel | +0.538 |
girls | +0.533 |
rob | +0.526 |
steep | +0.497 |
Neg logit contributions | |
worry | -0.358 |
permission | -0.314 |
herself | -0.300 |
She | -0.296 |
Her | -0.294 |
Token | a |
Token ID | 257 |
Feature activation | +3.51e-03 |
Pos logit contributions | |
herself | +0.042 |
worry | +0.041 |
permission | +0.039 |
her | +0.037 |
Her | +0.035 |
Neg logit contributions | |
ousel | -0.125 |
girls | -0.118 |
steep | -0.115 |
arium | -0.114 |
lights | -0.113 |
Token | big |
Token ID | 1263 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
ousel | +0.008 |
Zig | +0.008 |
steep | +0.007 |
girls | +0.007 |
zag | +0.007 |
Neg logit contributions | |
worry | -0.005 |
permission | -0.004 |
herself | -0.004 |
Her | -0.004 |
She | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
worry | +0.046 |
permission | +0.041 |
herself | +0.039 |
She | +0.039 |
pick | +0.039 |
Neg logit contributions | |
Zig | -0.054 |
ousel | -0.054 |
girls | -0.049 |
steep | -0.048 |
zag | -0.047 |
Token | perfect |
Token ID | 2818 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ousel | +0.078 |
Zig | +0.077 |
steep | +0.070 |
girls | +0.068 |
zag | +0.067 |
Neg logit contributions | |
worry | -0.060 |
permission | -0.057 |
herself | -0.054 |
Her | -0.053 |
She | -0.052 |
Token | place |
Token ID | 1295 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
worry | +0.016 |
permission | +0.015 |
pick | +0.014 |
herself | +0.014 |
understanding | +0.013 |
Neg logit contributions | |
Zig | -0.022 |
ousel | -0.021 |
girls | -0.020 |
rob | -0.019 |
steep | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
rob | +0.056 |
ousel | +0.055 |
Zig | +0.054 |
girls | +0.053 |
zag | +0.049 |
Neg logit contributions | |
worry | -0.029 |
permission | -0.027 |
herself | -0.026 |
her | -0.026 |
pick | -0.025 |
Token | play |
Token ID | 711 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
ousel | +0.003 |
Zig | +0.003 |
steep | +0.003 |
girls | +0.003 |
zag | +0.003 |
Neg logit contributions | |
worry | -0.002 |
permission | -0.001 |
herself | -0.001 |
Her | -0.001 |
She | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
herself | +0.003 |
worry | +0.003 |
She | +0.003 |
her | +0.003 |
permission | +0.003 |
Neg logit contributions | |
ousel | -0.006 |
Zig | -0.006 |
steep | -0.006 |
girls | -0.006 |
sed | -0.006 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
ousel | +0.025 |
rob | +0.024 |
Zig | +0.024 |
lights | +0.024 |
arium | +0.023 |
Neg logit contributions | |
worry | -0.016 |
herself | -0.014 |
pick | -0.014 |
permission | -0.013 |
her | -0.013 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ousel | +0.348 |
steep | +0.320 |
igators | +0.312 |
rob | +0.305 |
arium | +0.305 |
Neg logit contributions | |
worry | -0.804 |
herself | -0.779 |
Her | -0.777 |
She | -0.768 |
permission | -0.744 |
Token | couldn |
Token ID | 3521 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ousel | +0.518 |
Zig | +0.510 |
rob | +0.495 |
girls | +0.492 |
arium | +0.464 |
Neg logit contributions | |
worry | -0.384 |
herself | -0.367 |
permission | -0.334 |
her | -0.325 |
She | -0.322 |
Token | 't |
Token ID | 470 |
Feature activation | -7.74e-04 |
Pos logit contributions | |
ousel | +0.090 |
Zig | +0.088 |
arium | +0.088 |
girls | +0.087 |
steep | +0.086 |
Neg logit contributions | |
herself | -0.036 |
worry | -0.035 |
She | -0.034 |
Her | -0.032 |
pick | -0.030 |
Token | help |
Token ID | 1037 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
worry | +0.001 |
permission | +0.001 |
Her | +0.001 |
Daddy | +0.001 |
She | +0.001 |
Neg logit contributions | |
Zig | -0.002 |
ousel | -0.002 |
steep | -0.002 |
zag | -0.002 |
girls | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
worry | +0.127 |
permission | +0.122 |
Her | +0.116 |
Daddy | +0.115 |
She | +0.114 |
Neg logit contributions | |
Zig | -0.181 |
ousel | -0.174 |
steep | -0.160 |
Zoom | -0.153 |
girls | -0.152 |
Token | dog |
Token ID | 3290 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
worry | +0.177 |
permission | +0.146 |
herself | +0.130 |
daughter | +0.124 |
She | +0.122 |
Neg logit contributions | |
ousel | -0.549 |
Zig | -0.544 |
steep | -0.510 |
zag | -0.504 |
girls | -0.496 |
Token | called |
Token ID | 1444 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
lights | +0.057 |
steep | +0.057 |
Zig | +0.056 |
ousel | +0.055 |
ramp | +0.052 |
Neg logit contributions | |
worry | -0.021 |
her | -0.021 |
She | -0.020 |
herself | -0.020 |
pick | -0.020 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ousel | +0.306 |
steep | +0.289 |
lights | +0.278 |
Zig | +0.278 |
rob | +0.272 |
Neg logit contributions | |
permission | -0.275 |
worry | -0.272 |
herself | -0.266 |
her | -0.258 |
pick | -0.246 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
steep | +0.500 |
igators | +0.484 |
floats | +0.478 |
rob | +0.462 |
ousel | +0.456 |
Neg logit contributions | |
worry | -0.661 |
herself | -0.654 |
Her | -0.618 |
permission | -0.608 |
She | -0.602 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Zig | +0.510 |
girls | +0.489 |
ousel | +0.487 |
rob | +0.476 |
steep | +0.469 |
Neg logit contributions | |
worry | -0.373 |
herself | -0.348 |
permission | -0.330 |
pick | -0.327 |
Her | -0.327 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
She | +0.017 |
herself | +0.017 |
Her | +0.016 |
worry | +0.016 |
pick | +0.015 |
Neg logit contributions | |
lights | -0.022 |
arium | -0.022 |
ousel | -0.022 |
steep | -0.021 |
roles | -0.021 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
igators | +0.465 |
steep | +0.461 |
floats | +0.442 |
rob | +0.433 |
lights | +0.432 |
Neg logit contributions | |
herself | -0.643 |
worry | -0.627 |
Her | -0.607 |
She | -0.602 |
M | -0.566 |
Token | was |
Token ID | 373 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
Zig | +0.516 |
girls | +0.506 |
ousel | +0.497 |
steep | +0.480 |
rob | +0.478 |
Neg logit contributions | |
worry | -0.338 |
herself | -0.317 |
She | -0.295 |
pick | -0.285 |
her | -0.283 |
Token | a |
Token ID | 257 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ousel | +0.129 |
girls | +0.127 |
arium | +0.127 |
lights | +0.125 |
rob | +0.122 |
Neg logit contributions | |
herself | -0.060 |
worry | -0.057 |
her | -0.054 |
She | -0.052 |
understanding | -0.046 |
Token | very |
Token ID | 845 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
worry | +0.013 |
pick | +0.010 |
She | +0.010 |
understanding | +0.009 |
gard | +0.009 |
Neg logit contributions | |
lights | -0.028 |
ousel | -0.028 |
girls | -0.028 |
Zig | -0.027 |
roles | -0.027 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
girls | +0.101 |
rob | +0.099 |
Zig | +0.098 |
ousel | +0.098 |
lights | +0.097 |
Neg logit contributions | |
worry | -0.034 |
pick | -0.028 |
understanding | -0.027 |
She | -0.025 |
her | -0.023 |
Token | be |
Token ID | 307 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
Her | +0.003 |
herself | +0.003 |
She | +0.003 |
Neg logit contributions | |
ousel | -0.006 |
Zig | -0.006 |
steep | -0.005 |
girls | -0.005 |
zag | -0.005 |
Token | cow |
Token ID | 9875 |
Feature activation | +9.99e-02 |
Pos logit contributions | |
permission | +0.116 |
worry | +0.115 |
herself | +0.111 |
her | +0.108 |
Her | +0.100 |
Neg logit contributions | |
ousel | -0.238 |
Zig | -0.232 |
steep | -0.222 |
rob | -0.217 |
zag | -0.215 |
Token | boys |
Token ID | 13202 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ousel | +0.149 |
Zig | +0.148 |
steep | +0.147 |
rob | +0.132 |
lights | +0.131 |
Neg logit contributions | |
worry | -0.206 |
permission | -0.191 |
herself | -0.187 |
daughter | -0.179 |
pick | -0.178 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
steep | +0.534 |
Zig | +0.533 |
ousel | +0.513 |
lights | +0.495 |
rob | +0.478 |
Neg logit contributions | |
worry | -0.231 |
herself | -0.216 |
permission | -0.204 |
She | -0.202 |
Her | -0.197 |
Token | cow |
Token ID | 9875 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
worry | +0.002 |
permission | +0.002 |
pick | +0.002 |
herself | +0.002 |
her | +0.002 |
Neg logit contributions | |
ousel | -0.002 |
Zig | -0.002 |
steep | -0.002 |
lights | -0.002 |
zag | -0.002 |
Token | girls |
Token ID | 36960 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
steep | +0.118 |
ousel | +0.109 |
Zig | +0.103 |
lights | +0.102 |
rob | +0.094 |
Neg logit contributions | |
permission | -0.235 |
worry | -0.230 |
herself | -0.227 |
her | -0.221 |
pick | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
steep | +0.862 |
lights | +0.831 |
Zig | +0.828 |
ousel | +0.806 |
rob | +0.793 |
Neg logit contributions | |
herself | -0.348 |
permission | -0.312 |
worry | -0.307 |
pick | -0.297 |
She | -0.279 |
Token | They |
Token ID | 1119 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
worry | +0.047 |
Her | +0.044 |
permission | +0.043 |
herself | +0.043 |
She | +0.043 |
Neg logit contributions | |
ousel | -0.045 |
Zig | -0.043 |
steep | -0.040 |
rob | -0.039 |
zag | -0.038 |
Token | put |
Token ID | 1234 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Zig | +0.043 |
ousel | +0.043 |
steep | +0.040 |
lights | +0.040 |
zag | +0.040 |
Neg logit contributions | |
worry | -0.018 |
permission | -0.016 |
pick | -0.015 |
herself | -0.014 |
She | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
herself | +0.080 |
permission | +0.080 |
worry | +0.079 |
her | +0.078 |
pick | +0.072 |
Neg logit contributions | |
ousel | -0.129 |
Zig | -0.124 |
steep | -0.120 |
zag | -0.119 |
arium | -0.115 |
Token | hats |
Token ID | 23910 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
ousel | +0.179 |
Zig | +0.172 |
steep | +0.162 |
zag | +0.158 |
arium | +0.152 |
Neg logit contributions | |
worry | -0.141 |
permission | -0.137 |
herself | -0.137 |
her | -0.131 |
Her | -0.131 |
Token | ags |
Token ID | 3775 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Zig | +0.179 |
ousel | +0.178 |
steep | +0.161 |
girls | +0.153 |
zag | +0.146 |
Neg logit contributions | |
worry | -0.238 |
permission | -0.231 |
herself | -0.221 |
Her | -0.220 |
She | -0.215 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
ousel | +0.244 |
girls | +0.240 |
Zig | +0.240 |
rob | +0.229 |
arium | +0.221 |
Neg logit contributions | |
herself | -0.125 |
worry | -0.120 |
her | -0.110 |
permission | -0.108 |
She | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
arium | +0.009 |
ousel | +0.009 |
lights | +0.009 |
works | +0.008 |
rob | +0.008 |
Neg logit contributions | |
herself | -0.004 |
She | -0.004 |
Her | -0.004 |
pick | -0.003 |
worry | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
ousel | +0.027 |
lights | +0.024 |
girls | +0.024 |
arium | +0.024 |
steep | +0.024 |
Neg logit contributions | |
She | -0.013 |
Her | -0.012 |
herself | -0.012 |
worry | -0.012 |
M | -0.011 |
Token | When |
Token ID | 2215 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
ousel | +0.019 |
Zig | +0.018 |
arium | +0.018 |
steep | +0.017 |
girls | +0.017 |
Neg logit contributions | |
worry | -0.012 |
She | -0.011 |
Her | -0.011 |
herself | -0.011 |
permission | -0.010 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
worry | +0.080 |
herself | +0.075 |
her | +0.074 |
She | +0.070 |
pick | +0.070 |
Neg logit contributions | |
ousel | -0.058 |
ophone | -0.054 |
arium | -0.054 |
lights | -0.054 |
girls | -0.052 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
igators | +0.314 |
rob | +0.293 |
steep | +0.284 |
ousel | +0.278 |
floats | +0.275 |
Neg logit contributions | |
worry | -0.794 |
Her | -0.788 |
She | -0.781 |
herself | -0.763 |
M | -0.762 |
Token | 's |
Token ID | 338 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
girls | +0.545 |
rob | +0.534 |
Zig | +0.531 |
lights | +0.519 |
ousel | +0.519 |
Neg logit contributions | |
worry | -0.322 |
herself | -0.283 |
pick | -0.278 |
her | -0.276 |
permission | -0.261 |
Token | owner |
Token ID | 4870 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
worry | +0.105 |
permission | +0.096 |
herself | +0.090 |
Her | +0.087 |
She | +0.086 |
Neg logit contributions | |
ousel | -0.174 |
Zig | -0.172 |
rob | -0.163 |
steep | -0.157 |
girls | -0.157 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Zig | +0.094 |
ousel | +0.093 |
steep | +0.089 |
lights | +0.087 |
girls | +0.085 |
Neg logit contributions | |
worry | -0.064 |
permission | -0.058 |
pick | -0.056 |
herself | -0.055 |
She | -0.055 |
Token | him |
Token ID | 683 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
worry | +0.019 |
permission | +0.018 |
herself | +0.018 |
She | +0.017 |
Her | +0.017 |
Neg logit contributions | |
ousel | -0.023 |
steep | -0.021 |
Zig | -0.021 |
lights | -0.020 |
zag | -0.020 |
Token | bouncing |
Token ID | 30713 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
ousel | +0.033 |
lights | +0.033 |
arium | +0.032 |
Zig | +0.030 |
steep | +0.030 |
Neg logit contributions | |
worry | -0.022 |
herself | -0.021 |
pick | -0.019 |
her | -0.018 |
permission | -0.017 |
Token | around |
Token ID | 1088 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ousel | +0.119 |
arium | +0.113 |
sed | +0.112 |
girls | +0.109 |
ophone | +0.108 |
Neg logit contributions | |
herself | -0.068 |
her | -0.065 |
pick | -0.053 |
She | -0.051 |
worry | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -8.17e-03 |
Pos logit contributions | |
ousel | +0.298 |
steep | +0.267 |
ophone | +0.267 |
lights | +0.266 |
zag | +0.266 |
Neg logit contributions | |
herself | -0.133 |
her | -0.124 |
worry | -0.124 |
pick | -0.108 |
permission | -0.105 |
Token | but |
Token ID | 475 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
worry | +0.011 |
herself | +0.011 |
pick | +0.010 |
She | +0.009 |
understanding | +0.009 |
Neg logit contributions | |
ousel | -0.018 |
lights | -0.017 |
Zig | -0.017 |
arium | -0.017 |
girls | -0.017 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
worry | +0.049 |
herself | +0.044 |
her | +0.040 |
permission | +0.040 |
understanding | +0.038 |
Neg logit contributions | |
ousel | -0.066 |
arium | -0.065 |
lights | -0.064 |
rob | -0.064 |
girls | -0.063 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
ousel | +0.279 |
girls | +0.249 |
Zig | +0.245 |
zag | +0.245 |
steep | +0.244 |
Neg logit contributions | |
worry | -0.190 |
permission | -0.171 |
herself | -0.171 |
her | -0.161 |
She | -0.157 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ousel | +0.295 |
igators | +0.288 |
rob | +0.269 |
steep | +0.265 |
Zig | +0.258 |
Neg logit contributions | |
worry | -0.820 |
Her | -0.805 |
herself | -0.804 |
She | -0.796 |
permission | -0.778 |
Token | started |
Token ID | 2067 |
Feature activation | +4.38e-03 |
Pos logit contributions | |
Zig | +0.541 |
ousel | +0.534 |
girls | +0.523 |
rob | +0.513 |
arium | +0.501 |
Neg logit contributions | |
worry | -0.359 |
herself | -0.319 |
permission | -0.299 |
her | -0.288 |
She | -0.285 |
Token | to |
Token ID | 284 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
ousel | +0.009 |
Zig | +0.009 |
girls | +0.008 |
steep | +0.008 |
rob | +0.008 |
Neg logit contributions | |
worry | -0.007 |
permission | -0.006 |
herself | -0.006 |
Her | -0.006 |
She | -0.006 |
Token | get |
Token ID | 651 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ousel | +0.010 |
Zig | +0.010 |
steep | +0.009 |
girls | +0.009 |
arium | +0.009 |
Neg logit contributions | |
worry | -0.003 |
permission | -0.003 |
herself | -0.002 |
Her | -0.002 |
She | -0.002 |
Token | tired |
Token ID | 10032 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
worry | +0.164 |
permission | +0.148 |
herself | +0.142 |
her | +0.131 |
She | +0.131 |
Neg logit contributions | |
ousel | -0.280 |
Zig | -0.270 |
zag | -0.252 |
rob | -0.252 |
arium | -0.250 |
Token | they |
Token ID | 484 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
ousel | +0.033 |
Zig | +0.032 |
steep | +0.030 |
girls | +0.030 |
rob | +0.029 |
Neg logit contributions | |
worry | -0.025 |
permission | -0.023 |
herself | -0.022 |
Her | -0.022 |
She | -0.021 |
Token | should |
Token ID | 815 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
ousel | +0.131 |
Zig | +0.130 |
steep | +0.115 |
girls | +0.111 |
zag | +0.109 |
Neg logit contributions | |
worry | -0.151 |
permission | -0.142 |
herself | -0.136 |
She | -0.134 |
Her | -0.134 |
Token | go |
Token ID | 467 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
ousel | +0.157 |
Zig | +0.156 |
steep | +0.143 |
girls | +0.137 |
zag | +0.137 |
Neg logit contributions | |
worry | -0.091 |
permission | -0.088 |
Her | -0.083 |
herself | -0.080 |
She | -0.079 |
Token | home |
Token ID | 1363 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
worry | +0.058 |
permission | +0.055 |
herself | +0.052 |
She | +0.050 |
pick | +0.050 |
Neg logit contributions | |
Zig | -0.096 |
ousel | -0.095 |
steep | -0.088 |
girls | -0.088 |
lights | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
worry | +0.051 |
herself | +0.047 |
permission | +0.047 |
her | +0.040 |
understanding | +0.040 |
Neg logit contributions | |
Zig | -0.096 |
ousel | -0.093 |
girls | -0.089 |
rob | -0.089 |
floats | -0.088 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Zig | +0.033 |
ousel | +0.033 |
rob | +0.032 |
steep | +0.032 |
lights | +0.031 |
Neg logit contributions | |
worry | -0.018 |
permission | -0.015 |
pick | -0.015 |
herself | -0.014 |
her | -0.013 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ousel | +0.324 |
igators | +0.324 |
floats | +0.318 |
steep | +0.318 |
arium | +0.304 |
Neg logit contributions | |
worry | -0.786 |
Her | -0.761 |
herself | -0.753 |
She | -0.744 |
permission | -0.731 |
Token | bark |
Token ID | 21405 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
ousel | +0.539 |
Zig | +0.534 |
rob | +0.519 |
girls | +0.519 |
steep | +0.492 |
Neg logit contributions | |
worry | -0.372 |
herself | -0.355 |
permission | -0.340 |
her | -0.315 |
Her | -0.294 |
Token | ed |
Token ID | 276 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ousel | +0.041 |
Zig | +0.041 |
girls | +0.038 |
rob | +0.038 |
steep | +0.038 |
Neg logit contributions | |
worry | -0.023 |
permission | -0.022 |
herself | -0.021 |
She | -0.020 |
Her | -0.020 |
Token | happily |
Token ID | 18177 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
worry | +0.066 |
herself | +0.060 |
permission | +0.059 |
her | +0.057 |
understanding | +0.055 |
Neg logit contributions | |
rob | -0.106 |
ousel | -0.104 |
Zig | -0.100 |
girls | -0.097 |
zag | -0.095 |
Token | in |
Token ID | 287 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
Zig | +0.127 |
ousel | +0.123 |
rob | +0.116 |
steep | +0.115 |
girls | +0.115 |
Neg logit contributions | |
worry | -0.074 |
permission | -0.069 |
herself | -0.067 |
Her | -0.062 |
pick | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ousel | +0.113 |
Zig | +0.113 |
steep | +0.104 |
girls | +0.101 |
zag | +0.099 |
Neg logit contributions | |
worry | -0.066 |
permission | -0.061 |
herself | -0.058 |
Her | -0.057 |
She | -0.056 |
Token | powerful |
Token ID | 3665 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
worry | +0.015 |
permission | +0.014 |
herself | +0.013 |
Her | +0.012 |
She | +0.012 |
Neg logit contributions | |
Zig | -0.039 |
ousel | -0.039 |
steep | -0.037 |
girls | -0.035 |
zag | -0.035 |
Token | z |
Token ID | 1976 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Zig | +0.117 |
ousel | +0.114 |
girls | +0.110 |
lights | +0.105 |
steep | +0.104 |
Neg logit contributions | |
worry | -0.073 |
permission | -0.063 |
pick | -0.062 |
gard | -0.061 |
daughter | -0.058 |
Token | ebra |
Token ID | 37052 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Zig | +0.186 |
ousel | +0.174 |
steep | +0.167 |
girls | +0.155 |
lights | +0.144 |
Neg logit contributions | |
worry | -0.362 |
permission | -0.354 |
Her | -0.337 |
herself | -0.329 |
She | -0.328 |
Token | named |
Token ID | 3706 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
steep | +0.360 |
Zig | +0.348 |
ousel | +0.338 |
lights | +0.331 |
girls | +0.328 |
Neg logit contributions | |
Her | -0.254 |
worry | -0.252 |
She | -0.241 |
pick | -0.237 |
herself | -0.236 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
lights | +0.261 |
ousel | +0.258 |
steep | +0.238 |
arium | +0.238 |
girls | +0.228 |
Neg logit contributions | |
herself | -0.373 |
pick | -0.353 |
her | -0.351 |
worry | -0.348 |
Her | -0.345 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
steep | +0.383 |
ousel | +0.367 |
floats | +0.346 |
igators | +0.341 |
Zig | +0.336 |
Neg logit contributions | |
worry | -0.733 |
Her | -0.732 |
herself | -0.722 |
She | -0.700 |
M | -0.689 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
steep | +0.295 |
lights | +0.291 |
Zig | +0.283 |
ousel | +0.282 |
arium | +0.278 |
Neg logit contributions | |
worry | -0.116 |
herself | -0.113 |
pick | -0.107 |
Her | -0.104 |
permission | -0.099 |
Token | He |
Token ID | 679 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
herself | +0.054 |
She | +0.053 |
worry | +0.052 |
her | +0.050 |
Her | +0.050 |
Neg logit contributions | |
lights | -0.013 |
ousel | -0.012 |
arium | -0.012 |
girls | -0.010 |
ophone | -0.009 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
lights | +0.009 |
ousel | +0.008 |
girls | +0.008 |
arium | +0.008 |
steep | +0.008 |
Neg logit contributions | |
She | -0.006 |
M | -0.005 |
Her | -0.005 |
her | -0.005 |
pick | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
ousel | +0.270 |
Zig | +0.264 |
steep | +0.246 |
girls | +0.244 |
lights | +0.241 |
Neg logit contributions | |
worry | -0.181 |
herself | -0.175 |
permission | -0.170 |
Her | -0.169 |
She | -0.169 |
Token | back |
Token ID | 736 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
girls | +0.141 |
rob | +0.140 |
ousel | +0.138 |
works | +0.134 |
sed | +0.133 |
Neg logit contributions | |
herself | -0.059 |
her | -0.057 |
worry | -0.049 |
She | -0.049 |
permission | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +4.23e-04 |
Pos logit contributions | |
ousel | +0.050 |
rob | +0.050 |
girls | +0.050 |
Zig | +0.049 |
lights | +0.049 |
Neg logit contributions | |
worry | -0.018 |
her | -0.017 |
pick | -0.017 |
herself | -0.017 |
permission | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ousel | +0.001 |
lights | +0.001 |
works | +0.001 |
steep | +0.001 |
rob | +0.001 |
Neg logit contributions | |
worry | -0.001 |
permission | -0.001 |
her | -0.001 |
herself | -0.001 |
pick | -0.000 |
Token | house |
Token ID | 2156 |
Feature activation | -6.30e-02 |
Pos logit contributions | |
Zig | +0.077 |
ousel | +0.076 |
girls | +0.069 |
rob | +0.067 |
lights | +0.066 |
Neg logit contributions | |
worry | -0.064 |
permission | -0.060 |
herself | -0.057 |
She | -0.057 |
pick | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
worry | +0.087 |
permission | +0.076 |
herself | +0.074 |
pick | +0.070 |
her | +0.070 |
Neg logit contributions | |
Zig | -0.141 |
ousel | -0.139 |
girls | -0.137 |
rob | -0.137 |
steep | -0.132 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
herself | +0.021 |
worry | +0.021 |
her | +0.020 |
Her | +0.019 |
She | +0.019 |
Neg logit contributions | |
ousel | -0.010 |
rob | -0.010 |
arium | -0.010 |
girls | -0.009 |
igators | -0.009 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
igators | +0.317 |
ousel | +0.308 |
rob | +0.300 |
floats | +0.288 |
steep | +0.285 |
Neg logit contributions | |
worry | -0.795 |
Her | -0.776 |
She | -0.771 |
herself | -0.766 |
M | -0.745 |
Token | 's |
Token ID | 338 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
Zig | +0.519 |
ousel | +0.511 |
rob | +0.503 |
girls | +0.493 |
steep | +0.478 |
Neg logit contributions | |
worry | -0.375 |
permission | -0.339 |
herself | -0.328 |
pick | -0.312 |
She | -0.309 |
Token | owner |
Token ID | 4870 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
worry | +0.110 |
permission | +0.102 |
herself | +0.095 |
Her | +0.094 |
She | +0.092 |
Neg logit contributions | |
ousel | -0.172 |
Zig | -0.171 |
steep | -0.157 |
girls | -0.156 |
rob | -0.155 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
Zig | +0.089 |
ousel | +0.089 |
steep | +0.082 |
girls | +0.079 |
rob | +0.078 |
Neg logit contributions | |
worry | -0.064 |
permission | -0.059 |
herself | -0.056 |
Her | -0.056 |
She | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ousel | +0.054 |
Zig | +0.054 |
steep | +0.050 |
girls | +0.048 |
zag | +0.047 |
Neg logit contributions | |
worry | -0.038 |
permission | -0.036 |
herself | -0.034 |
Her | -0.033 |
She | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ousel | +0.026 |
steep | +0.024 |
Zig | +0.024 |
girls | +0.024 |
arium | +0.023 |
Neg logit contributions | |
worry | -0.018 |
herself | -0.017 |
permission | -0.017 |
Her | -0.016 |
her | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
worry | +0.019 |
permission | +0.018 |
herself | +0.018 |
Her | +0.018 |
She | +0.018 |
Neg logit contributions | |
ousel | -0.025 |
Zig | -0.024 |
steep | -0.023 |
girls | -0.022 |
arium | -0.022 |
Token | I |
Token ID | 40 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Zig | +0.018 |
ousel | +0.018 |
steep | +0.017 |
girls | +0.017 |
Zoom | +0.016 |
Neg logit contributions | |
worry | -0.008 |
permission | -0.008 |
herself | -0.007 |
Her | -0.007 |
She | -0.006 |
Token | love |
Token ID | 1842 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
worry | +0.087 |
permission | +0.071 |
pick | +0.068 |
She | +0.063 |
herself | +0.060 |
Neg logit contributions | |
ousel | -0.206 |
Zig | -0.203 |
lights | -0.197 |
girls | -0.188 |
rob | -0.187 |
Token | you |
Token ID | 345 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
worry | +0.107 |
permission | +0.102 |
herself | +0.096 |
her | +0.084 |
pick | +0.080 |
Neg logit contributions | |
ousel | -0.299 |
Zig | -0.280 |
lights | -0.279 |
steep | -0.279 |
arium | -0.277 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
worry | +0.052 |
permission | +0.047 |
herself | +0.045 |
She | +0.041 |
understanding | +0.041 |
Neg logit contributions | |
Zig | -0.083 |
ousel | -0.082 |
rob | -0.079 |
steep | -0.077 |
lights | -0.076 |
Token | zag |
Token ID | 50183 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
steep | +0.321 |
ousel | +0.304 |
igators | +0.292 |
floats | +0.286 |
Zig | +0.281 |
Neg logit contributions | |
worry | -0.783 |
permission | -0.754 |
Her | -0.741 |
herself | -0.727 |
vel | -0.719 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-03 |
Pos logit contributions | |
ousel | +0.520 |
Zig | +0.520 |
rob | +0.489 |
girls | +0.475 |
steep | +0.471 |
Neg logit contributions | |
worry | -0.377 |
herself | -0.343 |
permission | -0.328 |
understanding | -0.294 |
She | -0.292 |
Token | You |
Token ID | 921 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
worry | +0.008 |
herself | +0.007 |
permission | +0.007 |
She | +0.007 |
pick | +0.007 |
Neg logit contributions | |
ousel | -0.016 |
steep | -0.016 |
lights | -0.016 |
rob | -0.015 |
Zig | -0.015 |
Token | always |
Token ID | 1464 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
worry | +0.018 |
permission | +0.015 |
herself | +0.014 |
pick | +0.014 |
She | +0.014 |
Neg logit contributions | |
Zig | -0.033 |
ousel | -0.033 |
steep | -0.030 |
lights | -0.030 |
girls | -0.030 |
Token | make |
Token ID | 787 |
Feature activation | -8.08e-02 |
Pos logit contributions | |
ousel | +0.205 |
Zig | +0.205 |
steep | +0.190 |
girls | +0.184 |
zag | +0.181 |
Neg logit contributions | |
worry | -0.103 |
permission | -0.096 |
Her | -0.090 |
herself | -0.089 |
She | -0.087 |
Token | forest |
Token ID | 8222 |
Feature activation | +8.40e-02 |
Pos logit contributions | |
worry | +0.073 |
pick | +0.064 |
She | +0.062 |
her | +0.061 |
permission | +0.060 |
Neg logit contributions | |
Zig | -0.076 |
ousel | -0.074 |
girls | -0.071 |
lights | -0.071 |
zag | -0.067 |
Token | with |
Token ID | 351 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
Zig | +0.205 |
ousel | +0.201 |
girls | +0.196 |
rob | +0.189 |
steep | +0.184 |
Neg logit contributions | |
worry | -0.093 |
herself | -0.087 |
She | -0.085 |
Her | -0.083 |
pick | -0.083 |
Token | his |
Token ID | 465 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
worry | +0.031 |
permission | +0.030 |
Her | +0.028 |
herself | +0.028 |
She | +0.027 |
Neg logit contributions | |
Zig | -0.042 |
ousel | -0.042 |
steep | -0.038 |
girls | -0.037 |
Zoom | -0.036 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
worry | +0.050 |
herself | +0.040 |
permission | +0.040 |
pick | +0.036 |
She | +0.036 |
Neg logit contributions | |
ousel | -0.139 |
lights | -0.132 |
Zig | -0.127 |
arium | -0.126 |
rob | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
worry | +0.020 |
permission | +0.019 |
herself | +0.019 |
Her | +0.018 |
She | +0.017 |
Neg logit contributions | |
Zig | -0.042 |
ousel | -0.041 |
steep | -0.040 |
lights | -0.039 |
girls | -0.038 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
herself | +0.029 |
She | +0.028 |
She | +0.027 |
pick | +0.026 |
her | +0.026 |
Neg logit contributions | |
lights | -0.036 |
ousel | -0.035 |
roles | -0.035 |
arium | -0.034 |
mer | -0.034 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
steep | +0.378 |
ousel | +0.372 |
igators | +0.340 |
floats | +0.337 |
roles | +0.335 |
Neg logit contributions | |
worry | -0.682 |
herself | -0.678 |
Her | -0.677 |
She | -0.675 |
M | -0.644 |
Token | was |
Token ID | 373 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
lights | +0.260 |
Zig | +0.245 |
girls | +0.241 |
steep | +0.238 |
ousel | +0.237 |
Neg logit contributions | |
worry | -0.156 |
herself | -0.149 |
She | -0.138 |
pick | -0.138 |
her | -0.133 |
Token | very |
Token ID | 845 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
lights | +0.131 |
ousel | +0.128 |
arium | +0.126 |
girls | +0.126 |
rob | +0.125 |
Neg logit contributions | |
herself | -0.046 |
her | -0.046 |
worry | -0.044 |
She | -0.036 |
pick | -0.036 |
Token | strong |
Token ID | 1913 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
ousel | +0.107 |
rob | +0.103 |
girls | +0.103 |
Zig | +0.102 |
lights | +0.099 |
Neg logit contributions | |
worry | -0.040 |
pick | -0.031 |
Her | -0.031 |
herself | -0.030 |
She | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +2.50e-04 |
Pos logit contributions | |
Zig | +0.126 |
ousel | +0.123 |
lights | +0.115 |
girls | +0.115 |
arium | +0.114 |
Neg logit contributions | |
worry | -0.051 |
herself | -0.045 |
She | -0.040 |
permission | -0.040 |
her | -0.038 |
Token | play |
Token ID | 711 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
Zig | +0.149 |
lights | +0.143 |
ousel | +0.141 |
rob | +0.139 |
zag | +0.131 |
Neg logit contributions | |
worry | -0.073 |
pick | -0.065 |
permission | -0.058 |
realize | -0.054 |
She | -0.053 |
Token | cow |
Token ID | 9875 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
worry | +0.014 |
herself | +0.014 |
her | +0.013 |
She | +0.013 |
Her | +0.013 |
Neg logit contributions | |
ousel | -0.030 |
steep | -0.030 |
Zig | -0.030 |
lights | -0.028 |
sed | -0.027 |
Token | boys |
Token ID | 13202 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
Zig | +0.188 |
steep | +0.186 |
ousel | +0.185 |
lights | +0.179 |
rob | +0.173 |
Neg logit contributions | |
worry | -0.144 |
permission | -0.130 |
herself | -0.129 |
pick | -0.129 |
her | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -9.09e-04 |
Pos logit contributions | |
steep | +0.560 |
Zig | +0.537 |
lights | +0.530 |
ousel | +0.523 |
rob | +0.499 |
Neg logit contributions | |
worry | -0.186 |
her | -0.169 |
herself | -0.164 |
She | -0.147 |
pick | -0.147 |
Token | cow |
Token ID | 9875 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
worry | +0.001 |
permission | +0.001 |
herself | +0.001 |
pick | +0.001 |
She | +0.001 |
Neg logit contributions | |
ousel | -0.002 |
Zig | -0.002 |
steep | -0.002 |
zag | -0.002 |
arium | -0.002 |
Token | girls |
Token ID | 36960 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
steep | +0.155 |
lights | +0.151 |
Zig | +0.148 |
ousel | +0.146 |
rob | +0.139 |
Neg logit contributions | |
worry | -0.170 |
permission | -0.168 |
pick | -0.162 |
herself | -0.159 |
her | -0.158 |
Token | , |
Token ID | 11 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
steep | +0.755 |
Zig | +0.752 |
lights | +0.747 |
ousel | +0.728 |
rob | +0.714 |
Neg logit contributions | |
worry | -0.373 |
herself | -0.361 |
permission | -0.339 |
pick | -0.338 |
She | -0.312 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
worry | +0.027 |
permission | +0.024 |
pick | +0.023 |
herself | +0.022 |
She | +0.021 |
Neg logit contributions | |
ousel | -0.038 |
Zig | -0.037 |
steep | -0.036 |
rob | -0.035 |
zag | -0.035 |
Token | pretend |
Token ID | 16614 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
worry | +0.002 |
permission | +0.002 |
herself | +0.002 |
She | +0.001 |
Her | +0.001 |
Neg logit contributions | |
ousel | -0.002 |
Zig | -0.002 |
steep | -0.002 |
zag | -0.002 |
arium | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
ousel | +0.085 |
rob | +0.079 |
Zig | +0.078 |
zag | +0.076 |
steep | +0.075 |
Neg logit contributions | |
worry | -0.053 |
her | -0.053 |
permission | -0.048 |
herself | -0.047 |
pick | -0.046 |
Token | ride |
Token ID | 6594 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
worry | +0.007 |
permission | +0.006 |
pick | +0.005 |
herself | +0.005 |
She | +0.005 |
Neg logit contributions | |
ousel | -0.014 |
Zig | -0.014 |
lights | -0.013 |
steep | -0.013 |
arium | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -8.76e-03 |
Pos logit contributions | |
herself | +0.015 |
She | +0.014 |
Her | +0.013 |
her | +0.013 |
pick | +0.012 |
Neg logit contributions | |
girls | -0.041 |
ousel | -0.041 |
roles | -0.040 |
works | -0.039 |
lights | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Her | +0.010 |
She | +0.009 |
worry | +0.009 |
herself | +0.009 |
Daddy | +0.008 |
Neg logit contributions | |
ousel | -0.022 |
girls | -0.020 |
steep | -0.020 |
Zig | -0.020 |
sed | -0.019 |
Token | One |
Token ID | 3198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
She | +0.009 |
Her | +0.008 |
M | +0.007 |
worry | +0.007 |
herself | +0.007 |
Neg logit contributions | |
ousel | -0.026 |
sed | -0.026 |
girls | -0.026 |
lights | -0.026 |
roles | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ousel | +0.050 |
Zig | +0.049 |
girls | +0.047 |
rob | +0.044 |
lights | +0.044 |
Neg logit contributions | |
worry | -0.040 |
Her | -0.035 |
permission | -0.035 |
She | -0.034 |
pick | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ousel | +0.048 |
girls | +0.044 |
lights | +0.044 |
steep | +0.043 |
arium | +0.043 |
Neg logit contributions | |
worry | -0.023 |
Her | -0.021 |
herself | -0.020 |
her | -0.020 |
She | -0.019 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
her | +0.055 |
worry | +0.055 |
herself | +0.055 |
Her | +0.053 |
She | +0.053 |
Neg logit contributions | |
ousel | -0.031 |
lights | -0.028 |
arium | -0.028 |
girls | -0.027 |
rob | -0.026 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ousel | +0.371 |
steep | +0.356 |
Zig | +0.345 |
rob | +0.333 |
igators | +0.330 |
Neg logit contributions | |
worry | -0.700 |
Her | -0.694 |
She | -0.688 |
herself | -0.674 |
M | -0.663 |
Token | 's |
Token ID | 338 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
Zig | +0.266 |
lights | +0.261 |
ousel | +0.259 |
steep | +0.255 |
girls | +0.250 |
Neg logit contributions | |
worry | -0.137 |
pick | -0.118 |
herself | -0.115 |
She | -0.111 |
permission | -0.107 |
Token | friend |
Token ID | 1545 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
worry | +0.134 |
permission | +0.127 |
herself | +0.119 |
Her | +0.119 |
She | +0.117 |
Neg logit contributions | |
Zig | -0.198 |
ousel | -0.197 |
steep | -0.180 |
girls | -0.174 |
zag | -0.172 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ousel | +0.021 |
steep | +0.020 |
Zig | +0.020 |
lights | +0.019 |
girls | +0.019 |
Neg logit contributions | |
worry | -0.014 |
permission | -0.012 |
Her | -0.012 |
herself | -0.012 |
her | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
worry | +0.020 |
her | +0.020 |
herself | +0.018 |
Her | +0.018 |
permission | +0.017 |
Neg logit contributions | |
ousel | -0.068 |
lights | -0.067 |
steep | -0.064 |
ramp | -0.061 |
rob | -0.061 |
Token | Blue |
Token ID | 4518 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
ousel | +0.323 |
steep | +0.296 |
lights | +0.291 |
Zig | +0.288 |
girls | +0.272 |
Neg logit contributions | |
worry | -0.356 |
herself | -0.334 |
permission | -0.326 |
Her | -0.314 |
pick | -0.311 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ousel | +0.293 |
Zig | +0.290 |
steep | +0.271 |
girls | +0.256 |
lights | +0.255 |
Neg logit contributions | |
worry | -0.180 |
permission | -0.167 |
herself | -0.156 |
Her | -0.155 |
She | -0.154 |
Token | wanted |
Token ID | 2227 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
worry | +0.032 |
She | +0.028 |
her | +0.028 |
permission | +0.027 |
pick | +0.027 |
Neg logit contributions | |
ousel | -0.060 |
lights | -0.058 |
Zig | -0.056 |
steep | -0.055 |
zag | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
permission | +0.126 |
worry | +0.112 |
herself | +0.108 |
her | +0.104 |
pick | +0.102 |
Neg logit contributions | |
ousel | -0.251 |
lights | -0.235 |
Zig | -0.225 |
zag | -0.223 |
rob | -0.222 |
Token | borrow |
Token ID | 8804 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
worry | +0.015 |
permission | +0.014 |
She | +0.013 |
Her | +0.013 |
herself | +0.013 |
Neg logit contributions | |
Zig | -0.023 |
ousel | -0.023 |
steep | -0.021 |
girls | -0.020 |
zag | -0.020 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
worry | +0.064 |
herself | +0.060 |
permission | +0.059 |
Her | +0.054 |
her | +0.053 |
Neg logit contributions | |
ousel | -0.129 |
Zig | -0.123 |
steep | -0.120 |
zag | -0.119 |
arium | -0.118 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ousel | +0.242 |
Zig | +0.236 |
steep | +0.227 |
lights | +0.178 |
floats | +0.175 |
Neg logit contributions | |
worry | -0.866 |
Her | -0.832 |
permission | -0.821 |
herself | -0.819 |
She | -0.813 |
Token | 's |
Token ID | 338 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
Zig | +0.230 |
ousel | +0.220 |
steep | +0.213 |
lights | +0.208 |
rob | +0.198 |
Neg logit contributions | |
worry | -0.176 |
permission | -0.174 |
herself | -0.163 |
pick | -0.157 |
Her | -0.153 |
Token | favorite |
Token ID | 4004 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
worry | +0.136 |
permission | +0.132 |
herself | +0.120 |
pick | +0.117 |
Her | +0.112 |
Neg logit contributions | |
Zig | -0.192 |
ousel | -0.191 |
steep | -0.179 |
rob | -0.174 |
lights | -0.172 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
Zig | +0.085 |
ousel | +0.083 |
steep | +0.079 |
girls | +0.077 |
lights | +0.074 |
Neg logit contributions | |
worry | -0.051 |
permission | -0.049 |
herself | -0.046 |
pick | -0.044 |
Her | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
permission | +0.042 |
herself | +0.042 |
worry | +0.040 |
Her | +0.037 |
her | +0.036 |
Neg logit contributions | |
steep | -0.099 |
Zig | -0.099 |
ousel | -0.096 |
lights | -0.095 |
rob | -0.091 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
ousel | +0.242 |
Zig | +0.236 |
steep | +0.227 |
lights | +0.178 |
floats | +0.175 |
Neg logit contributions | |
worry | -0.866 |
Her | -0.832 |
permission | -0.821 |
herself | -0.819 |
She | -0.813 |
Token | 's |
Token ID | 338 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
Zig | +0.230 |
ousel | +0.220 |
steep | +0.213 |
lights | +0.208 |
rob | +0.198 |
Neg logit contributions | |
worry | -0.176 |
permission | -0.174 |
herself | -0.163 |
pick | -0.157 |
Her | -0.153 |
Token | favorite |
Token ID | 4004 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
worry | +0.136 |
permission | +0.132 |
herself | +0.120 |
pick | +0.117 |
Her | +0.112 |
Neg logit contributions | |
Zig | -0.192 |
ousel | -0.191 |
steep | -0.179 |
rob | -0.174 |
lights | -0.172 |
Token | toy |
Token ID | 13373 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
Zig | +0.085 |
ousel | +0.083 |
steep | +0.079 |
girls | +0.077 |
lights | +0.074 |
Neg logit contributions | |
worry | -0.051 |
permission | -0.049 |
herself | -0.046 |
pick | -0.044 |
Her | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
permission | +0.042 |
herself | +0.042 |
worry | +0.040 |
Her | +0.037 |
her | +0.036 |
Neg logit contributions | |
steep | -0.099 |
Zig | -0.099 |
ousel | -0.096 |
lights | -0.095 |
rob | -0.091 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
worry | +0.018 |
herself | +0.017 |
her | +0.016 |
She | +0.016 |
pick | +0.016 |
Neg logit contributions | |
lights | -0.025 |
steep | -0.024 |
arium | -0.023 |
rob | -0.023 |
ousel | -0.023 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ousel | +0.397 |
steep | +0.385 |
Zig | +0.368 |
floats | +0.350 |
igators | +0.347 |
Neg logit contributions | |
worry | -0.687 |
Her | -0.661 |
She | -0.652 |
herself | -0.649 |
M | -0.617 |
Token | said |
Token ID | 531 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
lights | +0.276 |
Zig | +0.267 |
ousel | +0.258 |
steep | +0.258 |
girls | +0.255 |
Neg logit contributions | |
worry | -0.134 |
pick | -0.117 |
herself | -0.109 |
her | -0.104 |
permission | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ousel | +0.009 |
steep | +0.009 |
Zig | +0.009 |
lights | +0.009 |
girls | +0.009 |
Neg logit contributions | |
worry | -0.006 |
permission | -0.005 |
Her | -0.005 |
herself | -0.005 |
her | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +4.87e-03 |
Pos logit contributions | |
worry | +0.024 |
herself | +0.023 |
Her | +0.023 |
permission | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.047 |
lights | -0.044 |
steep | -0.044 |
rob | -0.044 |
girls | -0.043 |
Token | No |
Token ID | 2949 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
Zig | +0.011 |
ousel | +0.011 |
steep | +0.010 |
girls | +0.010 |
Zoom | +0.010 |
Neg logit contributions | |
worry | -0.006 |
permission | -0.006 |
herself | -0.005 |
understanding | -0.005 |
Her | -0.005 |
Token | my |
Token ID | 616 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
worry | +0.034 |
permission | +0.031 |
herself | +0.030 |
Her | +0.029 |
She | +0.029 |
Neg logit contributions | |
Zig | -0.053 |
ousel | -0.053 |
steep | -0.049 |
girls | -0.048 |
zag | -0.047 |
Token | cow |
Token ID | 9875 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
worry | +0.018 |
permission | +0.016 |
understanding | +0.014 |
herself | +0.014 |
Daddy | +0.014 |
Neg logit contributions | |
Zig | -0.028 |
ousel | -0.027 |
steep | -0.025 |
zag | -0.024 |
girls | -0.024 |
Token | boys |
Token ID | 13202 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
ousel | +0.185 |
Zig | +0.183 |
steep | +0.175 |
lights | +0.166 |
rob | +0.165 |
Neg logit contributions | |
worry | -0.131 |
permission | -0.124 |
herself | -0.118 |
pick | -0.112 |
her | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
Zig | +0.440 |
ousel | +0.434 |
steep | +0.422 |
lights | +0.395 |
rob | +0.383 |
Neg logit contributions | |
worry | -0.292 |
permission | -0.278 |
herself | -0.259 |
She | -0.248 |
Her | -0.244 |
Token | cow |
Token ID | 9875 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
worry | +0.007 |
permission | +0.007 |
herself | +0.006 |
pick | +0.006 |
her | +0.006 |
Neg logit contributions | |
ousel | -0.008 |
Zig | -0.008 |
steep | -0.008 |
zag | -0.008 |
arium | -0.007 |
Token | girls |
Token ID | 36960 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ousel | +0.202 |
Zig | +0.198 |
steep | +0.193 |
rob | +0.183 |
lights | +0.181 |
Neg logit contributions | |
worry | -0.118 |
permission | -0.117 |
herself | -0.104 |
pick | -0.097 |
her | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Zig | +0.650 |
ousel | +0.648 |
steep | +0.610 |
lights | +0.575 |
rob | +0.570 |
Neg logit contributions | |
worry | -0.480 |
permission | -0.455 |
herself | -0.437 |
She | -0.416 |
pick | -0.409 |
Token | I |
Token ID | 314 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
worry | +0.034 |
permission | +0.032 |
herself | +0.031 |
She | +0.030 |
Her | +0.030 |
Neg logit contributions | |
ousel | -0.033 |
Zig | -0.032 |
steep | -0.030 |
zag | -0.028 |
arium | -0.028 |
Token | love |
Token ID | 1842 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
worry | +0.027 |
permission | +0.025 |
herself | +0.023 |
Her | +0.023 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.052 |
Zig | -0.052 |
steep | -0.048 |
girls | -0.047 |
zag | -0.046 |
Token | you |
Token ID | 345 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
worry | +0.114 |
permission | +0.112 |
herself | +0.103 |
her | +0.091 |
Her | +0.090 |
Neg logit contributions | |
ousel | -0.317 |
Zig | -0.309 |
steep | -0.297 |
zag | -0.288 |
arium | -0.280 |
Token | ." |
Token ID | 526 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
worry | +0.070 |
permission | +0.066 |
herself | +0.064 |
Her | +0.061 |
She | +0.061 |
Neg logit contributions | |
Zig | -0.096 |
ousel | -0.096 |
steep | -0.088 |
rob | -0.083 |
zag | -0.083 |
Token | horn |
Token ID | 12718 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Zig | +0.065 |
ousel | +0.061 |
arium | +0.059 |
girls | +0.057 |
lights | +0.056 |
Neg logit contributions | |
worry | -0.052 |
permission | -0.048 |
herself | -0.042 |
pick | -0.042 |
understanding | -0.042 |
Token | can |
Token ID | 460 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
Zig | +0.339 |
ousel | +0.309 |
girls | +0.302 |
steep | +0.300 |
rob | +0.298 |
Neg logit contributions | |
worry | -0.226 |
permission | -0.202 |
herself | -0.195 |
She | -0.191 |
pick | -0.186 |
Token | get |
Token ID | 651 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Zig | +0.162 |
ousel | +0.161 |
steep | +0.150 |
arium | +0.148 |
girls | +0.148 |
Neg logit contributions | |
worry | -0.075 |
permission | -0.067 |
herself | -0.065 |
She | -0.062 |
Her | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
worry | +0.172 |
permission | +0.164 |
herself | +0.141 |
her | +0.134 |
understanding | +0.133 |
Neg logit contributions | |
Zig | -0.291 |
ousel | -0.289 |
rob | -0.280 |
arium | -0.271 |
girls | -0.266 |
Token | car |
Token ID | 1097 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
Zig | +0.072 |
ousel | +0.068 |
arium | +0.067 |
lights | +0.065 |
girls | +0.064 |
Neg logit contributions | |
worry | -0.057 |
permission | -0.053 |
pick | -0.046 |
herself | -0.045 |
understanding | -0.043 |
Token | ousel |
Token ID | 48355 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Zig | +0.251 |
ousel | +0.230 |
rob | +0.228 |
girls | +0.228 |
arium | +0.221 |
Neg logit contributions | |
worry | -0.153 |
permission | -0.140 |
herself | -0.130 |
pick | -0.124 |
She | -0.122 |
Token | going |
Token ID | 1016 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
Zig | +0.744 |
rob | +0.690 |
girls | +0.668 |
ousel | +0.663 |
arium | +0.637 |
Neg logit contributions | |
worry | -0.411 |
permission | -0.377 |
herself | -0.355 |
pick | -0.332 |
her | -0.306 |
Token | again |
Token ID | 757 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
Zig | +0.049 |
rob | +0.048 |
girls | +0.047 |
sed | +0.047 |
arium | +0.047 |
Neg logit contributions | |
worry | -0.021 |
herself | -0.021 |
permission | -0.021 |
pick | -0.020 |
her | -0.019 |
Token | ." |
Token ID | 526 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
Zig | +0.172 |
ousel | +0.166 |
rob | +0.149 |
girls | +0.149 |
sed | +0.146 |
Neg logit contributions | |
worry | -0.117 |
permission | -0.108 |
herself | -0.104 |
She | -0.099 |
pick | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ousel | +0.141 |
steep | +0.137 |
Zig | +0.136 |
zag | +0.127 |
girls | +0.126 |
Neg logit contributions | |
worry | -0.083 |
Her | -0.083 |
herself | -0.083 |
She | -0.080 |
permission | -0.076 |
Token |
|
Token ID | 198 |
Feature activation | +7.72e-04 |
Pos logit contributions | |
ousel | +0.005 |
Zig | +0.005 |
steep | +0.005 |
girls | +0.005 |
lights | +0.005 |
Neg logit contributions | |
Her | -0.003 |
worry | -0.003 |
She | -0.003 |
herself | -0.003 |
Daddy | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
worry | +0.023 |
herself | +0.020 |
permission | +0.019 |
her | +0.018 |
Her | +0.018 |
Neg logit contributions | |
ousel | -0.044 |
Zig | -0.043 |
girls | -0.042 |
rob | -0.041 |
floats | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | -4.24e-05 |
Pos logit contributions | |
herself | +0.013 |
She | +0.012 |
Her | +0.012 |
worry | +0.010 |
her | +0.010 |
Neg logit contributions | |
lights | -0.032 |
ousel | -0.032 |
steep | -0.032 |
arium | -0.031 |
works | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
Her | +0.000 |
She | +0.000 |
herself | +0.000 |
worry | +0.000 |
M | +0.000 |
Neg logit contributions | |
ousel | -0.000 |
steep | -0.000 |
lights | -0.000 |
girls | -0.000 |
floats | -0.000 |
Token | Later |
Token ID | 18602 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
Her | +0.002 |
worry | +0.002 |
She | +0.002 |
herself | +0.002 |
M | +0.002 |
Neg logit contributions | |
ousel | -0.003 |
Zig | -0.003 |
steep | -0.003 |
lights | -0.003 |
girls | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
worry | +0.075 |
permission | +0.069 |
herself | +0.067 |
Her | +0.067 |
She | +0.066 |
Neg logit contributions | |
ousel | -0.106 |
Zig | -0.105 |
steep | -0.099 |
girls | -0.098 |
zag | -0.092 |
Token | Zig |
Token ID | 24992 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
her | +0.029 |
herself | +0.027 |
worry | +0.027 |
Her | +0.027 |
She | +0.026 |
Neg logit contributions | |
ousel | -0.050 |
lights | -0.048 |
girls | -0.047 |
ramp | -0.046 |
arium | -0.045 |
Token | gy |
Token ID | 1360 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ousel | +0.368 |
Zig | +0.357 |
steep | +0.355 |
rob | +0.325 |
igators | +0.325 |
Neg logit contributions | |
worry | -0.708 |
Her | -0.681 |
She | -0.669 |
herself | -0.657 |
permission | -0.653 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
Zig | +0.267 |
lights | +0.257 |
ousel | +0.254 |
steep | +0.254 |
girls | +0.247 |
Neg logit contributions | |
worry | -0.130 |
pick | -0.110 |
herself | -0.104 |
permission | -0.103 |
She | -0.101 |
Token | Blue |
Token ID | 4518 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
herself | +0.024 |
worry | +0.023 |
her | +0.022 |
Her | +0.022 |
permission | +0.020 |
Neg logit contributions | |
ousel | -0.063 |
steep | -0.059 |
girls | -0.059 |
lights | -0.058 |
zag | -0.058 |
Token | trying |
Token ID | 2111 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
ousel | +0.260 |
Zig | +0.255 |
zag | +0.236 |
steep | +0.226 |
girls | +0.223 |
Neg logit contributions | |
permission | -0.192 |
worry | -0.190 |
Her | -0.177 |
Daddy | -0.175 |
herself | -0.172 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
worry | +0.018 |
permission | +0.017 |
herself | +0.016 |
Her | +0.016 |
She | +0.016 |
Neg logit contributions | |
Zig | -0.019 |
ousel | -0.019 |
steep | -0.017 |
girls | -0.017 |
zag | -0.016 |
Token | try |
Token ID | 1949 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
worry | +0.014 |
permission | +0.014 |
Her | +0.013 |
She | +0.013 |
herself | +0.012 |
Neg logit contributions | |
Zig | -0.026 |
ousel | -0.026 |
steep | -0.023 |
girls | -0.023 |
Zoom | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -6.45e-04 |
Pos logit contributions | |
worry | +0.182 |
herself | +0.172 |
permission | +0.171 |
her | +0.154 |
pick | +0.153 |
Neg logit contributions | |
ousel | -0.294 |
Zig | -0.292 |
girls | -0.263 |
steep | -0.263 |
arium | -0.263 |
Token | get |
Token ID | 651 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
worry | +0.001 |
permission | +0.001 |
herself | +0.001 |
Her | +0.001 |
She | +0.001 |
Neg logit contributions | |
Zig | -0.002 |
ousel | -0.002 |
steep | -0.002 |
girls | -0.001 |
zag | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
worry | +0.171 |
permission | +0.164 |
herself | +0.151 |
Her | +0.141 |
She | +0.139 |
Neg logit contributions | |
ousel | -0.297 |
Zig | -0.297 |
steep | -0.272 |
zag | -0.267 |
girls | -0.266 |
Token | car |
Token ID | 1097 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Zig | +0.061 |
ousel | +0.061 |
steep | +0.056 |
girls | +0.054 |
zag | +0.053 |
Neg logit contributions | |
worry | -0.038 |
permission | -0.036 |
herself | -0.033 |
Her | -0.033 |
She | -0.032 |
Token | ousel |
Token ID | 48355 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Zig | +0.229 |
ousel | +0.213 |
girls | +0.206 |
rob | +0.201 |
arium | +0.200 |
Neg logit contributions | |
worry | -0.165 |
permission | -0.148 |
herself | -0.141 |
She | -0.132 |
pick | -0.131 |
Token | to |
Token ID | 284 |
Feature activation | -5.28e-03 |
Pos logit contributions | |
Zig | +0.686 |
ousel | +0.624 |
girls | +0.614 |
rob | +0.610 |
arium | +0.593 |
Neg logit contributions | |
worry | -0.485 |
permission | -0.425 |
herself | -0.418 |
pick | -0.379 |
her | -0.377 |
Token | move |
Token ID | 1445 |
Feature activation | -9.48e-03 |
Pos logit contributions | |
worry | +0.006 |
permission | +0.006 |
Her | +0.006 |
herself | +0.006 |
She | +0.005 |
Neg logit contributions | |
Zig | -0.013 |
ousel | -0.013 |
steep | -0.012 |
girls | -0.011 |
zag | -0.011 |
Token | ," |
Token ID | 553 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
worry | +0.014 |
herself | +0.013 |
permission | +0.012 |
her | +0.012 |
She | +0.012 |
Neg logit contributions | |
Zig | -0.021 |
ousel | -0.021 |
girls | -0.020 |
zag | -0.019 |
rob | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
ousel | +0.059 |
Zig | +0.059 |
steep | +0.055 |
girls | +0.053 |
zag | +0.052 |
Neg logit contributions | |
worry | -0.037 |
permission | -0.034 |
herself | -0.033 |
Her | -0.033 |
She | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
worry | +0.004 |
permission | +0.004 |
herself | +0.004 |
Her | +0.004 |
She | +0.003 |
Neg logit contributions | |
Zig | -0.005 |
ousel | -0.005 |
steep | -0.005 |
girls | -0.004 |
arium | -0.004 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
worry | +0.022 |
permission | +0.021 |
herself | +0.020 |
Her | +0.019 |
pick | +0.018 |
Neg logit contributions | |
ousel | -0.035 |
Zig | -0.034 |
steep | -0.033 |
arium | -0.031 |
girls | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
Zig | +0.046 |
ousel | +0.046 |
steep | +0.044 |
lights | +0.042 |
rob | +0.042 |
Neg logit contributions | |
worry | -0.025 |
permission | -0.025 |
herself | -0.023 |
She | -0.022 |
pick | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
worry | +0.041 |
permission | +0.038 |
herself | +0.038 |
She | +0.037 |
Her | +0.037 |
Neg logit contributions | |
ousel | -0.062 |
Zig | -0.059 |
rob | -0.057 |
steep | -0.056 |
arium | -0.056 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
worry | +0.010 |
permission | +0.009 |
herself | +0.008 |
understanding | +0.007 |
spit | +0.007 |
Neg logit contributions | |
Zig | -0.018 |
ousel | -0.018 |
steep | -0.016 |
girls | -0.016 |
rob | -0.016 |
Token | 't |
Token ID | 470 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
worry | +0.113 |
permission | +0.107 |
herself | +0.100 |
Her | +0.100 |
She | +0.098 |
Neg logit contributions | |
Zig | -0.161 |
ousel | -0.161 |
steep | -0.147 |
girls | -0.142 |
zag | -0.140 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
vel | +0.024 |
permission | +0.024 |
illy | +0.022 |
M | +0.022 |
moderation | +0.021 |
Neg logit contributions | |
Zig | -0.064 |
ousel | -0.061 |
Zoom | -0.058 |
steep | -0.057 |
zag | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
worry | +0.394 |
permission | +0.361 |
herself | +0.347 |
Her | +0.337 |
She | +0.333 |
Neg logit contributions | |
ousel | -0.507 |
Zig | -0.496 |
steep | -0.454 |
girls | -0.452 |
rob | -0.445 |
Token | honey |
Token ID | 12498 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
worry | +0.041 |
permission | +0.038 |
herself | +0.036 |
Her | +0.036 |
She | +0.035 |
Neg logit contributions | |
ousel | -0.051 |
Zig | -0.051 |
steep | -0.046 |
girls | -0.045 |
zag | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
worry | +0.086 |
permission | +0.080 |
herself | +0.076 |
She | +0.071 |
Her | +0.070 |
Neg logit contributions | |
ousel | -0.125 |
Zig | -0.124 |
steep | -0.115 |
rob | -0.109 |
arium | -0.109 |
Token | We |
Token ID | 775 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
worry | +0.005 |
permission | +0.005 |
herself | +0.005 |
Her | +0.004 |
She | +0.004 |
Neg logit contributions | |
ousel | -0.007 |
Zig | -0.007 |
steep | -0.006 |
girls | -0.006 |
zag | -0.006 |
Token | will |
Token ID | 481 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
Zig | +0.042 |
ousel | +0.042 |
steep | +0.038 |
girls | +0.036 |
zag | +0.035 |
Neg logit contributions | |
worry | -0.046 |
permission | -0.044 |
herself | -0.042 |
Her | -0.042 |
She | -0.041 |
Token | replied |
Token ID | 8712 |
Feature activation | -7.47e-04 |
Pos logit contributions | |
worry | +0.140 |
herself | +0.127 |
permission | +0.126 |
She | +0.120 |
pick | +0.117 |
Neg logit contributions | |
Zig | -0.202 |
ousel | -0.201 |
steep | -0.191 |
lights | -0.186 |
arium | -0.183 |
Token | , |
Token ID | 11 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
worry | +0.001 |
herself | +0.001 |
permission | +0.001 |
Her | +0.001 |
her | +0.001 |
Neg logit contributions | |
ousel | -0.002 |
Zig | -0.002 |
steep | -0.002 |
girls | -0.001 |
rob | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
worry | +0.049 |
permission | +0.045 |
herself | +0.045 |
Her | +0.045 |
She | +0.043 |
Neg logit contributions | |
ousel | -0.071 |
Zig | -0.068 |
steep | -0.066 |
rob | -0.065 |
girls | -0.063 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
permission | +0.009 |
worry | +0.008 |
herself | +0.007 |
daughter | +0.006 |
spit | +0.006 |
Neg logit contributions | |
Zig | -0.016 |
ousel | -0.015 |
steep | -0.014 |
zag | -0.014 |
Zoom | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
worry | +0.115 |
permission | +0.109 |
herself | +0.101 |
Her | +0.100 |
She | +0.098 |
Neg logit contributions | |
Zig | -0.157 |
ousel | -0.156 |
steep | -0.141 |
girls | -0.137 |
zag | -0.135 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
permission | +0.030 |
vel | +0.029 |
M | +0.028 |
Daddy | +0.027 |
She | +0.026 |
Neg logit contributions | |
Zig | -0.061 |
ousel | -0.058 |
Zoom | -0.054 |
steep | -0.052 |
Spe | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
worry | +0.376 |
permission | +0.325 |
herself | +0.325 |
Her | +0.302 |
She | +0.297 |
Neg logit contributions | |
ousel | -0.531 |
Zig | -0.509 |
rob | -0.498 |
girls | -0.483 |
steep | -0.476 |
Token | I |
Token ID | 314 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
worry | +0.056 |
permission | +0.053 |
herself | +0.050 |
Her | +0.050 |
She | +0.049 |
Neg logit contributions | |
ousel | -0.052 |
Zig | -0.051 |
steep | -0.046 |
girls | -0.045 |
zag | -0.044 |
Token | will |
Token ID | 481 |
Feature activation | +9.59e-02 |
Pos logit contributions | |
worry | +0.025 |
permission | +0.023 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
Zig | -0.025 |
ousel | -0.025 |
steep | -0.022 |
girls | -0.021 |
arium | -0.021 |
Token | get |
Token ID | 651 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Zig | +0.228 |
ousel | +0.227 |
steep | +0.207 |
zag | +0.205 |
girls | +0.205 |
Neg logit contributions | |
worry | -0.104 |
permission | -0.101 |
Her | -0.097 |
Daddy | -0.093 |
She | -0.093 |
Token | you |
Token ID | 345 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
worry | +0.176 |
permission | +0.170 |
herself | +0.157 |
pick | +0.143 |
Her | +0.142 |
Neg logit contributions | |
ousel | -0.324 |
Zig | -0.319 |
steep | -0.298 |
zag | -0.293 |
girls | -0.289 |
Token | said |
Token ID | 531 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
worry | +0.090 |
permission | +0.081 |
herself | +0.081 |
She | +0.079 |
Her | +0.077 |
Neg logit contributions | |
Zig | -0.136 |
ousel | -0.132 |
steep | -0.124 |
lights | -0.118 |
rob | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ousel | +0.023 |
Zig | +0.022 |
steep | +0.022 |
rob | +0.021 |
girls | +0.021 |
Neg logit contributions | |
worry | -0.015 |
permission | -0.014 |
herself | -0.013 |
Her | -0.013 |
her | -0.013 |
Token | " |
Token ID | 366 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.036 |
herself | +0.036 |
Her | +0.035 |
She | +0.034 |
Neg logit contributions | |
ousel | -0.058 |
Zig | -0.056 |
rob | -0.055 |
steep | -0.054 |
girls | -0.052 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
permission | +0.014 |
worry | +0.014 |
herself | +0.011 |
understanding | +0.010 |
vel | +0.010 |
Neg logit contributions | |
Zig | -0.023 |
ousel | -0.023 |
Zoom | -0.021 |
girls | -0.020 |
steep | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
worry | +0.126 |
permission | +0.123 |
herself | +0.111 |
Her | +0.110 |
She | +0.107 |
Neg logit contributions | |
Zig | -0.156 |
ousel | -0.155 |
steep | -0.137 |
girls | -0.134 |
zag | -0.134 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
permission | +0.025 |
vel | +0.024 |
M | +0.022 |
illy | +0.022 |
She | +0.021 |
Neg logit contributions | |
Zig | -0.068 |
ousel | -0.066 |
Zoom | -0.062 |
steep | -0.060 |
zag | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
worry | +0.405 |
permission | +0.375 |
herself | +0.359 |
Her | +0.354 |
She | +0.348 |
Neg logit contributions | |
ousel | -0.485 |
Zig | -0.480 |
steep | -0.436 |
girls | -0.426 |
rob | -0.416 |
Token | little |
Token ID | 1310 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.037 |
herself | +0.035 |
Her | +0.034 |
She | +0.034 |
Neg logit contributions | |
ousel | -0.057 |
Zig | -0.057 |
steep | -0.052 |
girls | -0.051 |
zag | -0.050 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.80e-03 |
Pos logit contributions | |
worry | +0.175 |
permission | +0.168 |
Her | +0.164 |
herself | +0.156 |
She | +0.155 |
Neg logit contributions | |
Zig | -0.454 |
ousel | -0.454 |
steep | -0.429 |
girls | -0.410 |
arium | -0.404 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
Zig | +0.016 |
ousel | +0.016 |
steep | +0.015 |
rob | +0.014 |
girls | +0.014 |
Neg logit contributions | |
worry | -0.009 |
permission | -0.008 |
herself | -0.007 |
Her | -0.007 |
She | -0.007 |
Token | I |
Token ID | 314 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
worry | +0.009 |
She | +0.007 |
Her | +0.007 |
permission | +0.007 |
herself | +0.007 |
Neg logit contributions | |
ousel | -0.014 |
rob | -0.013 |
Zig | -0.013 |
steep | -0.013 |
arium | -0.012 |
Token | Don |
Token ID | 3987 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
worry | +0.011 |
permission | +0.010 |
Her | +0.010 |
herself | +0.010 |
She | +0.010 |
Neg logit contributions | |
ousel | -0.012 |
Zig | -0.012 |
steep | -0.012 |
girls | -0.011 |
zag | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
worry | +0.135 |
permission | +0.126 |
herself | +0.119 |
Her | +0.119 |
She | +0.117 |
Neg logit contributions | |
ousel | -0.199 |
Zig | -0.199 |
steep | -0.183 |
girls | -0.177 |
zag | -0.173 |
Token | € |
Token ID | 26391 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
worry | +0.008 |
permission | +0.008 |
herself | +0.007 |
Her | +0.007 |
She | +0.007 |
Neg logit contributions | |
ousel | -0.008 |
Zig | -0.008 |
steep | -0.007 |
girls | -0.006 |
zag | -0.006 |
Token | ™ |
Token ID | 8151 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
Zig | +0.273 |
ousel | +0.268 |
igators | +0.268 |
lights | +0.265 |
arium | +0.264 |
Neg logit contributions | |
worry | -0.188 |
She | -0.164 |
Her | -0.164 |
herself | -0.157 |
Daddy | -0.153 |
Token | t |
Token ID | 83 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
Zig | +0.126 |
ousel | +0.121 |
girls | +0.115 |
arium | +0.114 |
lights | +0.114 |
Neg logit contributions | |
worry | -0.063 |
She | -0.056 |
Her | -0.055 |
herself | -0.054 |
permission | -0.051 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
worry | +0.047 |
permission | +0.047 |
Her | +0.045 |
She | +0.044 |
Daddy | +0.043 |
Neg logit contributions | |
Zig | -0.110 |
ousel | -0.110 |
steep | -0.101 |
zag | -0.097 |
Zoom | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
worry | +0.373 |
permission | +0.341 |
herself | +0.332 |
Her | +0.313 |
She | +0.313 |
Neg logit contributions | |
ousel | -0.514 |
Zig | -0.510 |
girls | -0.468 |
steep | -0.463 |
rob | -0.459 |
Token | Sam |
Token ID | 3409 |
Feature activation | +7.05e-02 |
Pos logit contributions | |
worry | +0.047 |
permission | +0.043 |
herself | +0.041 |
pick | +0.039 |
She | +0.039 |
Neg logit contributions | |
ousel | -0.079 |
Zig | -0.076 |
rob | -0.074 |
girls | -0.074 |
steep | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Zig | +0.164 |
ousel | +0.158 |
lights | +0.156 |
rob | +0.149 |
girls | +0.149 |
Neg logit contributions | |
worry | -0.098 |
permission | -0.088 |
herself | -0.084 |
pick | -0.082 |
her | -0.080 |
Token | I |
Token ID | 314 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
worry | +0.041 |
She | +0.036 |
herself | +0.036 |
permission | +0.036 |
Her | +0.035 |
Neg logit contributions | |
ousel | -0.069 |
Zig | -0.067 |
rob | -0.067 |
steep | -0.065 |
arium | -0.064 |
Token | can |
Token ID | 460 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.034 |
pick | +0.033 |
She | +0.033 |
herself | +0.032 |
Neg logit contributions | |
Zig | -0.058 |
ousel | -0.057 |
steep | -0.052 |
girls | -0.051 |
rob | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
worry | +0.034 |
Her | +0.034 |
She | +0.034 |
herself | +0.033 |
Daddy | +0.030 |
Neg logit contributions | |
ousel | -0.086 |
Zig | -0.085 |
steep | -0.084 |
rob | -0.082 |
zag | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
worry | +0.052 |
permission | +0.049 |
herself | +0.047 |
Her | +0.047 |
She | +0.047 |
Neg logit contributions | |
ousel | -0.065 |
Zig | -0.065 |
steep | -0.059 |
girls | -0.057 |
zag | -0.056 |
Token | " |
Token ID | 1 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
worry | +0.037 |
permission | +0.035 |
herself | +0.028 |
spit | +0.027 |
pick | +0.026 |
Neg logit contributions | |
Zig | -0.067 |
ousel | -0.067 |
steep | -0.061 |
zag | -0.059 |
Zoom | -0.058 |
Token | Don |
Token ID | 3987 |
Feature activation | -8.98e-02 |
Pos logit contributions | |
worry | +0.192 |
permission | +0.183 |
herself | +0.160 |
Her | +0.149 |
She | +0.146 |
Neg logit contributions | |
ousel | -0.317 |
Zig | -0.315 |
steep | -0.287 |
girls | -0.280 |
Zoom | -0.279 |
Token | 't |
Token ID | 470 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
worry | +0.133 |
permission | +0.126 |
herself | +0.118 |
Her | +0.117 |
She | +0.115 |
Neg logit contributions | |
Zig | -0.191 |
ousel | -0.191 |
steep | -0.174 |
girls | -0.169 |
zag | -0.165 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
vel | +0.024 |
illy | +0.023 |
permission | +0.023 |
moderation | +0.023 |
M | +0.023 |
Neg logit contributions | |
Zig | -0.058 |
ousel | -0.055 |
steep | -0.052 |
Zoom | -0.052 |
zag | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
worry | +0.394 |
permission | +0.347 |
herself | +0.338 |
Her | +0.322 |
She | +0.320 |
Neg logit contributions | |
ousel | -0.506 |
Zig | -0.494 |
girls | -0.456 |
steep | -0.453 |
rob | -0.453 |
Token | I |
Token ID | 314 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
worry | +0.047 |
permission | +0.043 |
herself | +0.041 |
Her | +0.040 |
She | +0.040 |
Neg logit contributions | |
ousel | -0.061 |
Zig | -0.060 |
steep | -0.055 |
girls | -0.054 |
zag | -0.053 |
Token | 'll |
Token ID | 1183 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
worry | +0.044 |
permission | +0.041 |
herself | +0.038 |
She | +0.038 |
pick | +0.038 |
Neg logit contributions | |
Zig | -0.047 |
ousel | -0.047 |
steep | -0.042 |
girls | -0.040 |
lights | -0.040 |
Token | help |
Token ID | 1037 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
Zig | +0.043 |
ousel | +0.043 |
steep | +0.038 |
girls | +0.038 |
zag | +0.038 |
Neg logit contributions | |
permission | -0.018 |
worry | -0.018 |
Her | -0.017 |
Daddy | -0.017 |
She | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
worry | +0.127 |
permission | +0.120 |
Her | +0.117 |
She | +0.114 |
Daddy | +0.108 |
Neg logit contributions | |
Zig | -0.202 |
ousel | -0.197 |
girls | -0.181 |
Zoom | -0.179 |
steep | -0.178 |
Token | said |
Token ID | 531 |
Feature activation | +8.20e-03 |
Pos logit contributions | |
worry | +0.045 |
She | +0.040 |
herself | +0.040 |
pick | +0.039 |
permission | +0.037 |
Neg logit contributions | |
Zig | -0.081 |
ousel | -0.077 |
steep | -0.074 |
lights | -0.073 |
girls | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
ousel | +0.016 |
Zig | +0.016 |
steep | +0.015 |
girls | +0.015 |
arium | +0.014 |
Neg logit contributions | |
worry | -0.013 |
permission | -0.013 |
Her | -0.012 |
herself | -0.012 |
She | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -5.18e-03 |
Pos logit contributions | |
worry | +0.041 |
permission | +0.038 |
herself | +0.037 |
Her | +0.037 |
She | +0.036 |
Neg logit contributions | |
ousel | -0.056 |
Zig | -0.055 |
steep | -0.052 |
rob | -0.050 |
girls | -0.050 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.46e-02 |
Pos logit contributions | |
permission | +0.008 |
worry | +0.008 |
herself | +0.006 |
vel | +0.006 |
spit | +0.006 |
Neg logit contributions | |
Zig | -0.011 |
ousel | -0.011 |
rob | -0.010 |
steep | -0.010 |
Zoom | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
worry | +0.120 |
permission | +0.117 |
herself | +0.105 |
Her | +0.104 |
She | +0.101 |
Neg logit contributions | |
Zig | -0.150 |
ousel | -0.149 |
steep | -0.134 |
zag | -0.129 |
girls | -0.129 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
vel | +0.019 |
permission | +0.019 |
illy | +0.017 |
M | +0.016 |
gard | +0.016 |
Neg logit contributions | |
Zig | -0.058 |
ousel | -0.055 |
Zoom | -0.053 |
steep | -0.052 |
Spe | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
worry | +0.396 |
permission | +0.366 |
herself | +0.352 |
Her | +0.346 |
She | +0.341 |
Neg logit contributions | |
ousel | -0.485 |
Zig | -0.480 |
steep | -0.436 |
girls | -0.428 |
rob | -0.419 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
worry | +0.040 |
permission | +0.037 |
herself | +0.035 |
Her | +0.034 |
She | +0.034 |
Neg logit contributions | |
ousel | -0.057 |
Zig | -0.056 |
steep | -0.052 |
girls | -0.051 |
zag | -0.050 |
Token | my |
Token ID | 1820 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
worry | +0.059 |
permission | +0.057 |
Her | +0.055 |
herself | +0.052 |
She | +0.050 |
Neg logit contributions | |
ousel | -0.144 |
Zig | -0.141 |
steep | -0.132 |
girls | -0.130 |
zag | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
worry | +0.177 |
permission | +0.161 |
herself | +0.151 |
pick | +0.145 |
She | +0.144 |
Neg logit contributions | |
Zig | -0.280 |
ousel | -0.278 |
steep | -0.256 |
girls | -0.246 |
lights | -0.245 |
Token | I |
Token ID | 314 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
worry | +0.026 |
permission | +0.023 |
She | +0.023 |
herself | +0.023 |
Her | +0.023 |
Neg logit contributions | |
ousel | -0.043 |
Zig | -0.041 |
steep | -0.039 |
rob | -0.039 |
girls | -0.038 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
ousel | +0.395 |
rob | +0.365 |
steep | +0.363 |
ramp | +0.351 |
zag | +0.351 |
Neg logit contributions | |
her | -0.235 |
herself | -0.229 |
worry | -0.211 |
Her | -0.202 |
permission | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
lights | +0.101 |
steep | +0.100 |
Zig | +0.099 |
ousel | +0.099 |
ramp | +0.096 |
Neg logit contributions | |
worry | -0.037 |
her | -0.037 |
herself | -0.036 |
She | -0.035 |
pick | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
worry | +0.034 |
She | +0.033 |
herself | +0.032 |
Her | +0.032 |
Daddy | +0.031 |
Neg logit contributions | |
ousel | -0.045 |
Zig | -0.044 |
steep | -0.043 |
lights | -0.043 |
rob | -0.042 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
worry | +0.006 |
her | +0.006 |
pick | +0.006 |
She | +0.006 |
spit | +0.006 |
Neg logit contributions | |
lights | -0.016 |
Zig | -0.014 |
roles | -0.014 |
steep | -0.014 |
ousel | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ousel | +0.032 |
Zig | +0.030 |
zag | +0.029 |
steep | +0.029 |
rob | +0.028 |
Neg logit contributions | |
worry | -0.016 |
permission | -0.016 |
her | -0.015 |
herself | -0.014 |
pick | -0.014 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
worry | +0.025 |
permission | +0.024 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.038 |
Zig | -0.038 |
steep | -0.035 |
girls | -0.034 |
zag | -0.033 |
Token | flowers |
Token ID | 12734 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
worry | +0.342 |
permission | +0.321 |
herself | +0.302 |
Her | +0.300 |
She | +0.294 |
Neg logit contributions | |
ousel | -0.528 |
Zig | -0.527 |
steep | -0.484 |
girls | -0.469 |
zag | -0.460 |
Token | every |
Token ID | 790 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
worry | +0.014 |
herself | +0.013 |
permission | +0.013 |
She | +0.013 |
Her | +0.012 |
Neg logit contributions | |
ousel | -0.022 |
Zig | -0.022 |
steep | -0.020 |
girls | -0.020 |
zag | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Zig | +0.021 |
ousel | +0.021 |
steep | +0.019 |
girls | +0.019 |
rob | +0.018 |
Neg logit contributions | |
worry | -0.018 |
permission | -0.017 |
herself | -0.017 |
Her | -0.016 |
pick | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
Zig | +0.057 |
ousel | +0.057 |
steep | +0.052 |
girls | +0.051 |
zag | +0.050 |
Neg logit contributions | |
worry | -0.031 |
permission | -0.030 |
herself | -0.030 |
Her | -0.028 |
She | -0.028 |
Token | One |
Token ID | 1881 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
She | +0.023 |
herself | +0.022 |
worry | +0.022 |
Her | +0.021 |
pick | +0.021 |
Neg logit contributions | |
ousel | -0.034 |
Zig | -0.033 |
zag | -0.032 |
lights | -0.032 |
rob | -0.031 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
worry | +0.068 |
permission | +0.062 |
She | +0.061 |
Her | +0.061 |
herself | +0.061 |
Neg logit contributions | |
ousel | -0.103 |
Zig | -0.102 |
steep | -0.098 |
arium | -0.093 |
rob | -0.092 |
Token | â |
Token ID | 22940 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
worry | +0.032 |
permission | +0.030 |
Her | +0.028 |
herself | +0.028 |
She | +0.027 |
Neg logit contributions | |
ousel | -0.059 |
Zig | -0.059 |
steep | -0.054 |
girls | -0.053 |
zag | -0.052 |
Token | € |
Token ID | 26391 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ousel | +0.057 |
Zig | +0.054 |
steep | +0.048 |
girls | +0.047 |
zag | +0.046 |
Neg logit contributions | |
worry | -0.062 |
permission | -0.059 |
Her | -0.056 |
herself | -0.056 |
She | -0.056 |
Token | ™ |
Token ID | 8151 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
ousel | +0.263 |
Zig | +0.261 |
lights | +0.258 |
steep | +0.256 |
arium | +0.250 |
Neg logit contributions | |
worry | -0.209 |
She | -0.184 |
Her | -0.176 |
pick | -0.173 |
Daddy | -0.172 |
Token | s |
Token ID | 82 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
Zig | +0.149 |
ousel | +0.145 |
steep | +0.138 |
arium | +0.136 |
lights | +0.135 |
Neg logit contributions | |
worry | -0.083 |
She | -0.081 |
Her | -0.079 |
herself | -0.075 |
m | -0.073 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
worry | +0.068 |
permission | +0.061 |
herself | +0.058 |
She | +0.055 |
Her | +0.055 |
Neg logit contributions | |
Zig | -0.136 |
ousel | -0.134 |
steep | -0.125 |
girls | -0.124 |
rob | -0.123 |
Token | some |
Token ID | 617 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
worry | +0.328 |
permission | +0.326 |
herself | +0.316 |
Her | +0.295 |
She | +0.293 |
Neg logit contributions | |
ousel | -0.524 |
Zig | -0.521 |
steep | -0.489 |
girls | -0.472 |
zag | -0.466 |
Token | flowers |
Token ID | 12734 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
worry | +0.050 |
permission | +0.048 |
herself | +0.045 |
Her | +0.043 |
She | +0.043 |
Neg logit contributions | |
Zig | -0.084 |
ousel | -0.083 |
steep | -0.076 |
girls | -0.074 |
zag | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
herself | +0.029 |
worry | +0.028 |
permission | +0.028 |
She | +0.027 |
pick | +0.026 |
Neg logit contributions | |
Zig | -0.049 |
ousel | -0.048 |
steep | -0.045 |
girls | -0.043 |
rob | -0.043 |
Token | take |
Token ID | 1011 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
worry | +0.016 |
permission | +0.015 |
Her | +0.013 |
She | +0.013 |
herself | +0.013 |
Neg logit contributions | |
Zig | -0.034 |
ousel | -0.033 |
steep | -0.031 |
girls | -0.030 |
Zoom | -0.029 |
Token | home |
Token ID | 1363 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
permission | +0.203 |
worry | +0.196 |
herself | +0.190 |
pick | +0.175 |
Her | +0.173 |
Neg logit contributions | |
ousel | -0.367 |
Zig | -0.357 |
steep | -0.341 |
zag | -0.330 |
girls | -0.325 |
Token |
|
Token ID | 198 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
Her | +0.041 |
herself | +0.041 |
She | +0.040 |
worry | +0.040 |
permission | +0.038 |
Neg logit contributions | |
ousel | -0.075 |
Zig | -0.072 |
steep | -0.070 |
girls | -0.066 |
arium | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
worry | +0.008 |
Her | +0.008 |
She | +0.008 |
herself | +0.008 |
permission | +0.007 |
Neg logit contributions | |
ousel | -0.013 |
Zig | -0.013 |
steep | -0.012 |
girls | -0.011 |
arium | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
worry | +0.007 |
permission | +0.007 |
herself | +0.005 |
pick | +0.005 |
gard | +0.005 |
Neg logit contributions | |
ousel | -0.015 |
Zig | -0.014 |
steep | -0.013 |
zag | -0.013 |
girls | -0.013 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
permission | +0.148 |
worry | +0.142 |
herself | +0.113 |
vel | +0.107 |
pick | +0.107 |
Neg logit contributions | |
Zig | -0.290 |
ousel | -0.287 |
steep | -0.267 |
Zoom | -0.261 |
rob | -0.254 |
Token | 't |
Token ID | 470 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
worry | +0.115 |
permission | +0.111 |
herself | +0.100 |
Her | +0.099 |
She | +0.097 |
Neg logit contributions | |
Zig | -0.144 |
ousel | -0.144 |
steep | -0.129 |
girls | -0.125 |
zag | -0.125 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
permission | +0.013 |
illy | +0.012 |
moderation | +0.012 |
vel | +0.011 |
illian | +0.011 |
Neg logit contributions | |
Zig | -0.037 |
ousel | -0.035 |
steep | -0.033 |
Zoom | -0.033 |
zag | -0.032 |
Token | ," |
Token ID | 553 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
worry | +0.395 |
permission | +0.352 |
herself | +0.342 |
Her | +0.330 |
She | +0.326 |
Neg logit contributions | |
ousel | -0.497 |
Zig | -0.489 |
girls | -0.445 |
steep | -0.444 |
rob | -0.440 |
Token | said |
Token ID | 531 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
Zig | +0.050 |
ousel | +0.049 |
steep | +0.041 |
Zoom | +0.041 |
girls | +0.040 |
Neg logit contributions | |
permission | -0.069 |
worry | -0.069 |
She | -0.063 |
herself | -0.063 |
Her | -0.061 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
ousel | +0.045 |
Zig | +0.044 |
steep | +0.042 |
girls | +0.040 |
zag | +0.039 |
Neg logit contributions | |
worry | -0.027 |
permission | -0.026 |
Her | -0.025 |
herself | -0.025 |
her | -0.023 |
Token | my |
Token ID | 1820 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ousel | +0.081 |
Zig | +0.075 |
zag | +0.073 |
steep | +0.070 |
girls | +0.069 |
Neg logit contributions | |
Who | -0.047 |
permission | -0.047 |
Daddy | -0.046 |
worry | -0.046 |
moderation | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
worry | +0.225 |
permission | +0.219 |
Daddy | +0.217 |
She | +0.215 |
What | +0.213 |
Neg logit contributions | |
ousel | -0.196 |
Zig | -0.186 |
zag | -0.164 |
steep | -0.157 |
girls | -0.154 |
Token | said |
Token ID | 531 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
Zig | +0.031 |
ousel | +0.030 |
lights | +0.030 |
zag | +0.029 |
arium | +0.028 |
Neg logit contributions | |
worry | -0.015 |
pick | -0.014 |
herself | -0.013 |
She | -0.012 |
permission | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ousel | +0.030 |
rob | +0.029 |
zag | +0.028 |
ramp | +0.027 |
arium | +0.027 |
Neg logit contributions | |
worry | -0.022 |
permission | -0.020 |
her | -0.020 |
herself | -0.020 |
Her | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
worry | +0.020 |
Her | +0.019 |
She | +0.018 |
permission | +0.018 |
pick | +0.018 |
Neg logit contributions | |
ousel | -0.040 |
rob | -0.039 |
Zig | -0.038 |
steep | -0.037 |
arium | -0.036 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
ousel | +0.010 |
Zig | +0.009 |
steep | +0.009 |
girls | +0.009 |
Zoom | +0.008 |
Neg logit contributions | |
worry | -0.006 |
permission | -0.005 |
herself | -0.005 |
Her | -0.005 |
She | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
worry | +0.085 |
Her | +0.075 |
She | +0.075 |
herself | +0.075 |
permission | +0.073 |
Neg logit contributions | |
ousel | -0.163 |
Zig | -0.161 |
steep | -0.154 |
arium | -0.148 |
girls | -0.147 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
vel | +0.015 |
illy | +0.014 |
permission | +0.014 |
She | +0.013 |
hire | +0.013 |
Neg logit contributions | |
Zig | -0.034 |
ousel | -0.034 |
Zoom | -0.031 |
steep | -0.031 |
floats | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
worry | +0.356 |
permission | +0.309 |
herself | +0.296 |
Her | +0.284 |
She | +0.279 |
Neg logit contributions | |
ousel | -0.539 |
Zig | -0.521 |
rob | -0.504 |
girls | -0.483 |
steep | -0.483 |
Token | kids |
Token ID | 3988 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
worry | +0.030 |
permission | +0.027 |
pick | +0.025 |
herself | +0.025 |
understanding | +0.024 |
Neg logit contributions | |
ousel | -0.037 |
Zig | -0.036 |
rob | -0.035 |
zag | -0.034 |
steep | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.28e-05 |
Pos logit contributions | |
worry | +0.073 |
permission | +0.067 |
pick | +0.059 |
herself | +0.059 |
She | +0.056 |
Neg logit contributions | |
Zig | -0.135 |
ousel | -0.133 |
steep | -0.125 |
lights | -0.123 |
rob | -0.120 |
Token | He |
Token ID | 679 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
worry | +0.000 |
permission | +0.000 |
pick | +0.000 |
herself | +0.000 |
Her | +0.000 |
Neg logit contributions | |
ousel | -0.000 |
steep | -0.000 |
rob | -0.000 |
Zig | -0.000 |
zag | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
Zig | +0.036 |
lights | +0.035 |
ousel | +0.034 |
steep | +0.034 |
rob | +0.031 |
Neg logit contributions | |
worry | -0.030 |
pick | -0.027 |
permission | -0.027 |
spit | -0.026 |
herself | -0.025 |
Token | said |
Token ID | 531 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Zig | +0.172 |
steep | +0.167 |
rob | +0.158 |
lights | +0.157 |
ousel | +0.156 |
Neg logit contributions | |
worry | -0.098 |
spit | -0.088 |
pick | -0.079 |
face | -0.072 |
permission | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
ousel | +0.041 |
Zig | +0.039 |
steep | +0.037 |
girls | +0.036 |
zag | +0.036 |
Neg logit contributions | |
worry | -0.028 |
permission | -0.026 |
herself | -0.025 |
Her | -0.024 |
She | -0.023 |
Token | " |
Token ID | 366 |
Feature activation | +4.89e-03 |
Pos logit contributions | |
worry | +0.017 |
permission | +0.015 |
Her | +0.015 |
herself | +0.015 |
She | +0.015 |
Neg logit contributions | |
ousel | -0.024 |
Zig | -0.024 |
steep | -0.022 |
rob | -0.022 |
arium | -0.022 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
Zig | +0.012 |
ousel | +0.012 |
steep | +0.011 |
girls | +0.011 |
Zoom | +0.011 |
Neg logit contributions | |
worry | -0.005 |
permission | -0.005 |
herself | -0.005 |
pick | -0.004 |
Her | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
worry | +0.092 |
permission | +0.083 |
Her | +0.082 |
She | +0.082 |
herself | +0.082 |
Neg logit contributions | |
ousel | -0.157 |
Zig | -0.155 |
steep | -0.146 |
girls | -0.141 |
arium | -0.139 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
permission | +0.013 |
vel | +0.012 |
illy | +0.012 |
Her | +0.011 |
herself | +0.011 |
Neg logit contributions | |
Zig | -0.041 |
ousel | -0.039 |
steep | -0.038 |
Zoom | -0.037 |
hon | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
worry | +0.375 |
permission | +0.337 |
herself | +0.324 |
Her | +0.313 |
She | +0.310 |
Neg logit contributions | |
ousel | -0.515 |
Zig | -0.501 |
rob | -0.464 |
girls | -0.459 |
steep | -0.459 |
Token | I |
Token ID | 314 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
worry | +0.028 |
permission | +0.026 |
herself | +0.024 |
She | +0.023 |
pick | +0.023 |
Neg logit contributions | |
ousel | -0.040 |
Zig | -0.039 |
steep | -0.036 |
zag | -0.036 |
rob | -0.036 |
Token | 'll |
Token ID | 1183 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
worry | +0.018 |
permission | +0.016 |
pick | +0.015 |
She | +0.015 |
herself | +0.015 |
Neg logit contributions | |
ousel | -0.021 |
Zig | -0.021 |
steep | -0.019 |
lights | -0.019 |
rob | -0.019 |
Token | buy |
Token ID | 2822 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Zig | +0.097 |
ousel | +0.096 |
steep | +0.087 |
girls | +0.087 |
zag | +0.086 |
Neg logit contributions | |
worry | -0.037 |
permission | -0.036 |
Her | -0.034 |
herself | -0.032 |
Daddy | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
permission | +0.153 |
herself | +0.148 |
worry | +0.147 |
her | +0.128 |
Her | +0.117 |
Neg logit contributions | |
ousel | -0.421 |
Zig | -0.405 |
steep | -0.398 |
zag | -0.395 |
arium | -0.375 |
Token | said |
Token ID | 531 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
worry | +0.112 |
permission | +0.105 |
herself | +0.098 |
Her | +0.096 |
She | +0.096 |
Neg logit contributions | |
Zig | -0.174 |
ousel | -0.173 |
steep | -0.160 |
girls | -0.153 |
zag | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ousel | +0.055 |
Zig | +0.054 |
steep | +0.051 |
rob | +0.050 |
girls | +0.049 |
Neg logit contributions | |
worry | -0.036 |
permission | -0.034 |
herself | -0.032 |
Her | -0.031 |
her | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
worry | +0.024 |
permission | +0.023 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.030 |
Zig | -0.030 |
steep | -0.027 |
rob | -0.027 |
girls | -0.027 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
herself | +0.003 |
Her | +0.002 |
pick | +0.002 |
Neg logit contributions | |
Zig | -0.006 |
ousel | -0.006 |
steep | -0.006 |
girls | -0.005 |
Zoom | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
worry | +0.108 |
permission | +0.102 |
herself | +0.095 |
Her | +0.095 |
She | +0.093 |
Neg logit contributions | |
Zig | -0.154 |
ousel | -0.154 |
steep | -0.140 |
girls | -0.136 |
zag | -0.133 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
vel | +0.015 |
permission | +0.015 |
M | +0.014 |
Her | +0.014 |
She | +0.014 |
Neg logit contributions | |
Zig | -0.059 |
ousel | -0.058 |
Zoom | -0.054 |
steep | -0.054 |
zag | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
worry | +0.383 |
permission | +0.345 |
herself | +0.332 |
Her | +0.317 |
She | +0.314 |
Neg logit contributions | |
ousel | -0.504 |
Zig | -0.492 |
rob | -0.455 |
steep | -0.449 |
girls | -0.448 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
worry | +0.033 |
permission | +0.031 |
herself | +0.029 |
Her | +0.028 |
She | +0.028 |
Neg logit contributions | |
ousel | -0.051 |
Zig | -0.050 |
steep | -0.046 |
girls | -0.045 |
zag | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ousel | +0.071 |
Zig | +0.070 |
steep | +0.065 |
girls | +0.063 |
zag | +0.062 |
Neg logit contributions | |
worry | -0.047 |
permission | -0.046 |
Her | -0.044 |
herself | -0.043 |
She | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
worry | +0.168 |
permission | +0.151 |
herself | +0.140 |
pick | +0.134 |
She | +0.130 |
Neg logit contributions | |
Zig | -0.295 |
ousel | -0.293 |
steep | -0.269 |
rob | -0.264 |
arium | -0.263 |
Token | I |
Token ID | 314 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
worry | +0.021 |
permission | +0.018 |
She | +0.018 |
herself | +0.018 |
Her | +0.017 |
Neg logit contributions | |
ousel | -0.033 |
Zig | -0.031 |
rob | -0.031 |
steep | -0.031 |
arium | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
worry | +0.112 |
permission | +0.105 |
herself | +0.098 |
Her | +0.096 |
She | +0.096 |
Neg logit contributions | |
Zig | -0.174 |
ousel | -0.173 |
steep | -0.160 |
girls | -0.153 |
zag | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ousel | +0.055 |
Zig | +0.054 |
steep | +0.051 |
rob | +0.050 |
girls | +0.049 |
Neg logit contributions | |
worry | -0.036 |
permission | -0.034 |
herself | -0.032 |
Her | -0.031 |
her | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
worry | +0.024 |
permission | +0.023 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.030 |
Zig | -0.030 |
steep | -0.027 |
rob | -0.027 |
girls | -0.027 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
herself | +0.003 |
Her | +0.002 |
pick | +0.002 |
Neg logit contributions | |
Zig | -0.006 |
ousel | -0.006 |
steep | -0.006 |
girls | -0.005 |
Zoom | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
worry | +0.108 |
permission | +0.102 |
herself | +0.095 |
Her | +0.095 |
She | +0.093 |
Neg logit contributions | |
Zig | -0.154 |
ousel | -0.154 |
steep | -0.140 |
girls | -0.136 |
zag | -0.133 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
vel | +0.015 |
permission | +0.015 |
M | +0.014 |
Her | +0.014 |
She | +0.014 |
Neg logit contributions | |
Zig | -0.059 |
ousel | -0.058 |
Zoom | -0.054 |
steep | -0.054 |
zag | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
worry | +0.383 |
permission | +0.345 |
herself | +0.332 |
Her | +0.317 |
She | +0.314 |
Neg logit contributions | |
ousel | -0.504 |
Zig | -0.492 |
rob | -0.455 |
steep | -0.449 |
girls | -0.448 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
worry | +0.033 |
permission | +0.031 |
herself | +0.029 |
Her | +0.028 |
She | +0.028 |
Neg logit contributions | |
ousel | -0.051 |
Zig | -0.050 |
steep | -0.046 |
girls | -0.045 |
zag | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
ousel | +0.071 |
Zig | +0.070 |
steep | +0.065 |
girls | +0.063 |
zag | +0.062 |
Neg logit contributions | |
worry | -0.047 |
permission | -0.046 |
Her | -0.044 |
herself | -0.043 |
She | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
worry | +0.168 |
permission | +0.151 |
herself | +0.140 |
pick | +0.134 |
She | +0.130 |
Neg logit contributions | |
Zig | -0.295 |
ousel | -0.293 |
steep | -0.269 |
rob | -0.264 |
arium | -0.263 |
Token | The |
Token ID | 383 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
worry | +0.021 |
permission | +0.018 |
She | +0.018 |
herself | +0.018 |
Her | +0.017 |
Neg logit contributions | |
ousel | -0.033 |
Zig | -0.031 |
rob | -0.031 |
steep | -0.031 |
arium | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
worry | +0.112 |
permission | +0.105 |
herself | +0.098 |
Her | +0.096 |
She | +0.096 |
Neg logit contributions | |
Zig | -0.174 |
ousel | -0.173 |
steep | -0.160 |
girls | -0.153 |
zag | -0.151 |
Token | , |
Token ID | 11 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ousel | +0.055 |
Zig | +0.054 |
steep | +0.051 |
rob | +0.050 |
girls | +0.049 |
Neg logit contributions | |
worry | -0.036 |
permission | -0.034 |
herself | -0.032 |
Her | -0.031 |
her | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
worry | +0.024 |
permission | +0.023 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.030 |
Zig | -0.030 |
steep | -0.027 |
rob | -0.027 |
girls | -0.027 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
herself | +0.003 |
Her | +0.002 |
pick | +0.002 |
Neg logit contributions | |
Zig | -0.006 |
ousel | -0.006 |
steep | -0.006 |
girls | -0.005 |
Zoom | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
worry | +0.108 |
permission | +0.102 |
herself | +0.095 |
Her | +0.095 |
She | +0.093 |
Neg logit contributions | |
Zig | -0.154 |
ousel | -0.154 |
steep | -0.140 |
girls | -0.136 |
zag | -0.133 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
vel | +0.015 |
permission | +0.015 |
M | +0.014 |
Her | +0.014 |
She | +0.014 |
Neg logit contributions | |
Zig | -0.059 |
ousel | -0.058 |
Zoom | -0.054 |
steep | -0.054 |
zag | -0.052 |
Token | about |
Token ID | 546 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
worry | +0.383 |
permission | +0.345 |
herself | +0.332 |
Her | +0.317 |
She | +0.314 |
Neg logit contributions | |
ousel | -0.504 |
Zig | -0.492 |
rob | -0.455 |
steep | -0.449 |
girls | -0.448 |
Token | it |
Token ID | 340 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
ousel | +0.283 |
Zig | +0.276 |
steep | +0.259 |
zag | +0.252 |
girls | +0.250 |
Neg logit contributions | |
worry | -0.180 |
permission | -0.166 |
herself | -0.159 |
pick | -0.148 |
understanding | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.94e-03 |
Pos logit contributions | |
worry | +0.057 |
herself | +0.052 |
permission | +0.050 |
She | +0.046 |
her | +0.046 |
Neg logit contributions | |
Zig | -0.095 |
ousel | -0.092 |
steep | -0.087 |
rob | -0.085 |
girls | -0.085 |
Token | You |
Token ID | 921 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
worry | +0.004 |
herself | +0.004 |
She | +0.004 |
Her | +0.003 |
permission | +0.003 |
Neg logit contributions | |
ousel | -0.007 |
rob | -0.006 |
Zig | -0.006 |
steep | -0.006 |
zag | -0.006 |
Token | can |
Token ID | 460 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
worry | +0.033 |
permission | +0.030 |
herself | +0.028 |
pick | +0.027 |
She | +0.027 |
Neg logit contributions | |
Zig | -0.042 |
ousel | -0.042 |
steep | -0.038 |
rob | -0.037 |
girls | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
ousel | +0.183 |
Zig | +0.182 |
steep | +0.165 |
girls | +0.164 |
zag | +0.163 |
Neg logit contributions | |
worry | -0.091 |
permission | -0.089 |
herself | -0.079 |
She | -0.074 |
pick | -0.073 |
Token | big |
Token ID | 1263 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
worry | +0.042 |
permission | +0.037 |
pick | +0.034 |
understanding | +0.033 |
She | +0.033 |
Neg logit contributions | |
Zig | -0.066 |
ousel | -0.066 |
girls | -0.060 |
rob | -0.058 |
lights | -0.058 |
Token | smile |
Token ID | 8212 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
worry | +0.099 |
permission | +0.089 |
pick | +0.080 |
herself | +0.080 |
She | +0.078 |
Neg logit contributions | |
Zig | -0.146 |
ousel | -0.143 |
girls | -0.131 |
steep | -0.129 |
zag | -0.125 |
Token | on |
Token ID | 319 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
worry | +0.096 |
permission | +0.090 |
herself | +0.085 |
Her | +0.084 |
She | +0.083 |
Neg logit contributions | |
Zig | -0.140 |
ousel | -0.138 |
steep | -0.129 |
girls | -0.124 |
arium | -0.121 |
Token | his |
Token ID | 465 |
Feature activation | -5.38e-02 |
Pos logit contributions | |
Zig | +0.123 |
ousel | +0.118 |
Zoom | +0.106 |
steep | +0.104 |
girls | +0.102 |
Neg logit contributions | |
worry | -0.111 |
permission | -0.106 |
She | -0.092 |
Daddy | -0.091 |
herself | -0.091 |
Token | face |
Token ID | 1986 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
worry | +0.031 |
permission | +0.026 |
Her | +0.021 |
herself | +0.021 |
She | +0.020 |
Neg logit contributions | |
ousel | -0.163 |
Zig | -0.162 |
steep | -0.153 |
girls | -0.149 |
zag | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
worry | +0.296 |
permission | +0.282 |
herself | +0.280 |
Her | +0.261 |
She | +0.260 |
Neg logit contributions | |
Zig | -0.568 |
ousel | -0.550 |
steep | -0.522 |
girls | -0.505 |
rob | -0.501 |
Token |
|
Token ID | 198 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
She | +0.045 |
Her | +0.044 |
herself | +0.044 |
worry | +0.043 |
Daddy | +0.041 |
Neg logit contributions | |
ousel | -0.080 |
Zig | -0.075 |
steep | -0.075 |
zag | -0.074 |
rob | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
She | +0.023 |
worry | +0.023 |
Her | +0.022 |
herself | +0.022 |
Daddy | +0.021 |
Neg logit contributions | |
ousel | -0.038 |
Zig | -0.037 |
steep | -0.035 |
girls | -0.034 |
zag | -0.033 |
Token | They |
Token ID | 2990 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
worry | +0.017 |
permission | +0.016 |
herself | +0.014 |
Her | +0.013 |
pick | +0.013 |
Neg logit contributions | |
Zig | -0.037 |
ousel | -0.037 |
steep | -0.034 |
girls | -0.033 |
zag | -0.033 |
Token | take |
Token ID | 1011 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
worry | +0.022 |
pick | +0.019 |
permission | +0.019 |
herself | +0.018 |
She | +0.018 |
Neg logit contributions | |
Zig | -0.051 |
ousel | -0.050 |
steep | -0.047 |
rob | -0.047 |
lights | -0.047 |
Token | said |
Token ID | 531 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
worry | +0.043 |
pick | +0.041 |
spit | +0.040 |
her | +0.038 |
permission | +0.037 |
Neg logit contributions | |
Zig | -0.079 |
rob | -0.077 |
lights | -0.074 |
ousel | -0.072 |
girls | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ousel | +0.038 |
rob | +0.037 |
steep | +0.036 |
lights | +0.035 |
girls | +0.035 |
Neg logit contributions | |
worry | -0.022 |
permission | -0.021 |
her | -0.020 |
herself | -0.019 |
understanding | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -4.67e-03 |
Pos logit contributions | |
worry | +0.031 |
permission | +0.028 |
herself | +0.028 |
Her | +0.027 |
pick | +0.027 |
Neg logit contributions | |
ousel | -0.051 |
rob | -0.050 |
Zig | -0.049 |
steep | -0.048 |
girls | -0.046 |
Token | Don |
Token ID | 3987 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
worry | +0.006 |
permission | +0.006 |
herself | +0.005 |
Her | +0.005 |
She | +0.004 |
Neg logit contributions | |
ousel | -0.011 |
Zig | -0.011 |
steep | -0.010 |
girls | -0.010 |
Zoom | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
worry | +0.097 |
permission | +0.088 |
Her | +0.085 |
herself | +0.085 |
She | +0.084 |
Neg logit contributions | |
ousel | -0.157 |
Zig | -0.156 |
steep | -0.146 |
girls | -0.141 |
arium | -0.139 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
permission | +0.018 |
Her | +0.016 |
vel | +0.016 |
She | +0.015 |
herself | +0.015 |
Neg logit contributions | |
Zig | -0.061 |
ousel | -0.060 |
steep | -0.055 |
Zoom | -0.055 |
zag | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
worry | +0.362 |
permission | +0.304 |
herself | +0.292 |
her | +0.272 |
pick | +0.268 |
Neg logit contributions | |
ousel | -0.537 |
rob | -0.515 |
Zig | -0.512 |
girls | -0.484 |
arium | -0.475 |
Token | this |
Token ID | 428 |
Feature activation | -3.85e-03 |
Pos logit contributions | |
worry | +0.036 |
permission | +0.031 |
herself | +0.029 |
pick | +0.028 |
understanding | +0.028 |
Neg logit contributions | |
ousel | -0.053 |
Zig | -0.051 |
rob | -0.050 |
zag | -0.049 |
steep | -0.048 |
Token | is |
Token ID | 318 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
worry | +0.007 |
pick | +0.005 |
permission | +0.005 |
spit | +0.005 |
understanding | +0.005 |
Neg logit contributions | |
Zig | -0.008 |
ousel | -0.008 |
girls | -0.007 |
rob | -0.007 |
lights | -0.007 |
Token | R |
Token ID | 371 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
ousel | +0.169 |
rob | +0.166 |
Zig | +0.161 |
zag | +0.157 |
lights | +0.155 |
Neg logit contributions | |
worry | -0.085 |
permission | -0.070 |
her | -0.064 |
herself | -0.061 |
understanding | -0.060 |
Token | uf |
Token ID | 3046 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
Zig | +0.206 |
ousel | +0.200 |
steep | +0.197 |
lights | +0.182 |
Zoom | +0.179 |
Neg logit contributions | |
permission | -0.144 |
worry | -0.141 |
illy | -0.128 |
vel | -0.120 |
Daddy | -0.118 |
Token | said |
Token ID | 531 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Zig | +0.087 |
rob | +0.084 |
ousel | +0.082 |
steep | +0.082 |
lights | +0.079 |
Neg logit contributions | |
worry | -0.050 |
spit | -0.045 |
herself | -0.042 |
understanding | -0.042 |
pick | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ousel | +0.060 |
Zig | +0.058 |
rob | +0.055 |
girls | +0.055 |
steep | +0.055 |
Neg logit contributions | |
worry | -0.039 |
permission | -0.037 |
herself | -0.036 |
Her | -0.035 |
understanding | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
worry | +0.025 |
permission | +0.024 |
herself | +0.023 |
Her | +0.023 |
She | +0.023 |
Neg logit contributions | |
ousel | -0.035 |
Zig | -0.035 |
steep | -0.032 |
rob | -0.032 |
girls | -0.032 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
Zig | +0.042 |
ousel | +0.042 |
steep | +0.039 |
girls | +0.038 |
zag | +0.038 |
Neg logit contributions | |
worry | -0.018 |
permission | -0.016 |
herself | -0.015 |
Her | -0.015 |
She | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
worry | +0.069 |
She | +0.064 |
Her | +0.063 |
herself | +0.061 |
permission | +0.058 |
Neg logit contributions | |
ousel | -0.149 |
Zig | -0.147 |
steep | -0.142 |
arium | -0.138 |
girls | -0.137 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
permission | +0.008 |
illy | +0.007 |
vel | +0.007 |
Her | +0.006 |
herself | +0.006 |
Neg logit contributions | |
Zig | -0.028 |
ousel | -0.027 |
steep | -0.026 |
Zoom | -0.025 |
zag | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
worry | +0.357 |
permission | +0.296 |
herself | +0.293 |
her | +0.279 |
Her | +0.272 |
Neg logit contributions | |
ousel | -0.539 |
rob | -0.520 |
Zig | -0.514 |
girls | -0.491 |
arium | -0.482 |
Token | I |
Token ID | 314 |
Feature activation | -3.94e-04 |
Pos logit contributions | |
worry | +0.029 |
permission | +0.025 |
herself | +0.024 |
pick | +0.023 |
She | +0.023 |
Neg logit contributions | |
ousel | -0.037 |
Zig | -0.035 |
rob | -0.034 |
zag | -0.033 |
girls | -0.033 |
Token | can |
Token ID | 460 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
worry | +0.001 |
permission | +0.001 |
pick | +0.001 |
She | +0.001 |
herself | +0.001 |
Neg logit contributions | |
ousel | -0.001 |
Zig | -0.001 |
steep | -0.001 |
lights | -0.001 |
rob | -0.001 |
Token | help |
Token ID | 1037 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
ousel | +0.183 |
Zig | +0.183 |
zag | +0.167 |
girls | +0.166 |
steep | +0.165 |
Neg logit contributions | |
worry | -0.074 |
permission | -0.071 |
Her | -0.063 |
herself | -0.061 |
Daddy | -0.061 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
worry | +0.111 |
permission | +0.103 |
Her | +0.096 |
herself | +0.095 |
She | +0.094 |
Neg logit contributions | |
Zig | -0.214 |
ousel | -0.213 |
steep | -0.196 |
girls | -0.192 |
Zoom | -0.188 |
Token | said |
Token ID | 531 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
worry | +0.017 |
She | +0.015 |
pick | +0.015 |
herself | +0.015 |
spit | +0.014 |
Neg logit contributions | |
Zig | -0.031 |
lights | -0.029 |
ousel | -0.029 |
steep | -0.028 |
rob | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
ousel | +0.033 |
rob | +0.032 |
Zig | +0.032 |
girls | +0.031 |
steep | +0.030 |
Neg logit contributions | |
worry | -0.022 |
permission | -0.019 |
herself | -0.018 |
Her | -0.018 |
understanding | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
worry | +0.021 |
herself | +0.019 |
permission | +0.019 |
Her | +0.018 |
She | +0.018 |
Neg logit contributions | |
ousel | -0.036 |
Zig | -0.034 |
rob | -0.034 |
steep | -0.033 |
girls | -0.033 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
ousel | +0.007 |
Zig | +0.007 |
steep | +0.006 |
Zoom | +0.006 |
girls | +0.006 |
Neg logit contributions | |
permission | -0.003 |
worry | -0.003 |
herself | -0.003 |
pick | -0.002 |
Her | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
worry | +0.090 |
permission | +0.081 |
Her | +0.079 |
herself | +0.079 |
She | +0.079 |
Neg logit contributions | |
ousel | -0.150 |
Zig | -0.149 |
steep | -0.140 |
girls | -0.135 |
arium | -0.134 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
permission | +0.014 |
illy | +0.013 |
vel | +0.013 |
Her | +0.012 |
M | +0.012 |
Neg logit contributions | |
Zig | -0.049 |
ousel | -0.048 |
steep | -0.045 |
Zoom | -0.045 |
hon | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
worry | +0.372 |
permission | +0.331 |
herself | +0.316 |
Her | +0.303 |
She | +0.301 |
Neg logit contributions | |
ousel | -0.511 |
Zig | -0.501 |
rob | -0.465 |
girls | -0.461 |
steep | -0.458 |
Token | we |
Token ID | 356 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
worry | +0.032 |
permission | +0.030 |
herself | +0.028 |
Her | +0.028 |
She | +0.028 |
Neg logit contributions | |
ousel | -0.040 |
Zig | -0.040 |
steep | -0.036 |
girls | -0.035 |
zag | -0.034 |
Token | can |
Token ID | 460 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
Zig | +0.020 |
ousel | +0.020 |
steep | +0.018 |
girls | +0.017 |
zag | +0.016 |
Neg logit contributions | |
worry | -0.023 |
permission | -0.021 |
herself | -0.021 |
Her | -0.020 |
She | -0.020 |
Token | play |
Token ID | 711 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ousel | +0.146 |
Zig | +0.145 |
girls | +0.131 |
zag | +0.130 |
steep | +0.130 |
Neg logit contributions | |
worry | -0.075 |
permission | -0.074 |
Her | -0.067 |
herself | -0.065 |
She | -0.063 |
Token | together |
Token ID | 1978 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
worry | +0.017 |
herself | +0.016 |
permission | +0.015 |
pick | +0.015 |
She | +0.015 |
Neg logit contributions | |
Zig | -0.031 |
ousel | -0.031 |
steep | -0.030 |
lights | -0.028 |
zag | -0.028 |
Token | said |
Token ID | 531 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
ousel | +0.029 |
Zig | +0.029 |
steep | +0.026 |
girls | +0.025 |
zag | +0.024 |
Neg logit contributions | |
worry | -0.025 |
permission | -0.024 |
herself | -0.023 |
Her | -0.023 |
She | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Zig | +0.025 |
ousel | +0.023 |
Zoom | +0.020 |
steep | +0.020 |
zag | +0.019 |
Neg logit contributions | |
worry | -0.029 |
permission | -0.029 |
She | -0.028 |
Daddy | -0.027 |
herself | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.038 |
herself | +0.035 |
Her | +0.035 |
She | +0.035 |
Neg logit contributions | |
Zig | -0.039 |
ousel | -0.039 |
steep | -0.035 |
girls | -0.033 |
zag | -0.032 |
Token | Don |
Token ID | 3987 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
Zig | +0.025 |
ousel | +0.025 |
steep | +0.023 |
Zoom | +0.022 |
zag | +0.022 |
Neg logit contributions | |
permission | -0.013 |
worry | -0.013 |
understanding | -0.010 |
gard | -0.010 |
herself | -0.010 |
Token | 't |
Token ID | 470 |
Feature activation | -9.34e-03 |
Pos logit contributions | |
worry | +0.096 |
permission | +0.090 |
herself | +0.085 |
Her | +0.084 |
She | +0.083 |
Neg logit contributions | |
Zig | -0.137 |
ousel | -0.137 |
steep | -0.125 |
girls | -0.121 |
zag | -0.119 |
Token | worry |
Token ID | 5490 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
permission | +0.010 |
vel | +0.009 |
illy | +0.009 |
register | +0.008 |
M | +0.008 |
Neg logit contributions | |
Zig | -0.022 |
ousel | -0.020 |
Zoom | -0.020 |
steep | -0.019 |
Spike | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
worry | +0.392 |
permission | +0.357 |
herself | +0.345 |
Her | +0.338 |
She | +0.333 |
Neg logit contributions | |
ousel | -0.484 |
Zig | -0.475 |
steep | -0.435 |
girls | -0.429 |
rob | -0.422 |
Token | I |
Token ID | 314 |
Feature activation | -7.48e-03 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.037 |
herself | +0.035 |
Her | +0.035 |
She | +0.035 |
Neg logit contributions | |
ousel | -0.039 |
Zig | -0.038 |
steep | -0.035 |
girls | -0.034 |
zag | -0.033 |
Token | will |
Token ID | 481 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
worry | +0.014 |
permission | +0.013 |
herself | +0.012 |
She | +0.012 |
Her | +0.012 |
Neg logit contributions | |
ousel | -0.014 |
Zig | -0.014 |
steep | -0.012 |
girls | -0.012 |
rob | -0.012 |
Token | help |
Token ID | 1037 |
Feature activation | -9.29e-02 |
Pos logit contributions | |
Zig | +0.236 |
ousel | +0.228 |
Zoom | +0.210 |
zag | +0.205 |
girls | +0.201 |
Neg logit contributions | |
permission | -0.105 |
Daddy | -0.102 |
worry | -0.100 |
Her | -0.099 |
She | -0.097 |
Token | you |
Token ID | 345 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
worry | +0.140 |
permission | +0.132 |
She | +0.129 |
Her | +0.129 |
gard | +0.128 |
Neg logit contributions | |
Zig | -0.185 |
ousel | -0.171 |
Zoom | -0.167 |
girls | -0.158 |
steep | -0.146 |
Token | ashes |
Token ID | 7465 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
Zig | +0.109 |
ousel | +0.103 |
steep | +0.094 |
arium | +0.093 |
rob | +0.091 |
Neg logit contributions | |
worry | -0.094 |
herself | -0.092 |
permission | -0.091 |
spit | -0.089 |
Her | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
worry | +0.021 |
permission | +0.020 |
herself | +0.019 |
Her | +0.019 |
She | +0.019 |
Neg logit contributions | |
ousel | -0.030 |
Zig | -0.030 |
steep | -0.028 |
girls | -0.027 |
zag | -0.026 |
Token | water |
Token ID | 1660 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
Zig | +0.056 |
ousel | +0.055 |
arium | +0.049 |
steep | +0.048 |
girls | +0.048 |
Neg logit contributions | |
worry | -0.036 |
permission | -0.032 |
pick | -0.031 |
herself | -0.030 |
spit | -0.028 |
Token | on |
Token ID | 319 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
worry | +0.081 |
permission | +0.072 |
herself | +0.071 |
pick | +0.071 |
She | +0.067 |
Neg logit contributions | |
Zig | -0.141 |
ousel | -0.135 |
rob | -0.124 |
girls | -0.124 |
steep | -0.121 |
Token | her |
Token ID | 607 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
Zig | +0.133 |
ousel | +0.130 |
steep | +0.120 |
girls | +0.116 |
Zoom | +0.115 |
Neg logit contributions | |
worry | -0.089 |
permission | -0.084 |
Her | -0.075 |
She | -0.074 |
Daddy | -0.073 |
Token | face |
Token ID | 1986 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
worry | +0.104 |
permission | +0.095 |
herself | +0.089 |
pick | +0.083 |
finger | +0.082 |
Neg logit contributions | |
Zig | -0.286 |
ousel | -0.284 |
rob | -0.269 |
steep | -0.267 |
arium | -0.263 |
Token | and |
Token ID | 290 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
worry | +0.328 |
permission | +0.304 |
herself | +0.301 |
Her | +0.292 |
She | +0.288 |
Neg logit contributions | |
Zig | -0.538 |
ousel | -0.532 |
steep | -0.485 |
girls | -0.478 |
rob | -0.472 |
Token | laughs |
Token ID | 22051 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
worry | +0.010 |
herself | +0.009 |
permission | +0.009 |
her | +0.009 |
pick | +0.009 |
Neg logit contributions | |
ousel | -0.014 |
Zig | -0.014 |
steep | -0.013 |
zag | -0.013 |
arium | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ousel | +0.190 |
Zig | +0.188 |
steep | +0.175 |
girls | +0.168 |
rob | +0.167 |
Neg logit contributions | |
worry | -0.111 |
herself | -0.104 |
permission | -0.103 |
Her | -0.100 |
She | -0.098 |
Token | She |
Token ID | 1375 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
worry | +0.022 |
herself | +0.022 |
Her | +0.022 |
She | +0.021 |
permission | +0.020 |
Neg logit contributions | |
ousel | -0.059 |
Zig | -0.057 |
steep | -0.054 |
girls | -0.053 |
zag | -0.053 |
Token | likes |
Token ID | 7832 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
spit | +0.087 |
pick | +0.081 |
worry | +0.080 |
She | +0.076 |
her | +0.075 |
Neg logit contributions | |
Zig | -0.122 |
ousel | -0.113 |
zag | -0.108 |
steep | -0.105 |
arium | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
worry | +0.104 |
permission | +0.102 |
herself | +0.094 |
her | +0.092 |
pick | +0.091 |
Neg logit contributions | |
ousel | -0.231 |
Zig | -0.223 |
steep | -0.220 |
lights | -0.216 |
arium | -0.214 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ousel | +0.067 |
Zig | +0.067 |
arium | +0.062 |
steep | +0.062 |
girls | +0.061 |
Neg logit contributions | |
worry | -0.047 |
permission | -0.041 |
pick | -0.040 |
herself | -0.038 |
daughter | -0.038 |
Token | lift |
Token ID | 10303 |
Feature activation | -7.76e-02 |
Pos logit contributions | |
worry | +0.021 |
permission | +0.019 |
herself | +0.018 |
pick | +0.018 |
She | +0.017 |
Neg logit contributions | |
Zig | -0.034 |
ousel | -0.033 |
steep | -0.032 |
rob | -0.031 |
girls | -0.031 |
Token | their |
Token ID | 511 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
herself | +0.093 |
worry | +0.090 |
her | +0.088 |
permission | +0.087 |
pick | +0.077 |
Neg logit contributions | |
ousel | -0.191 |
Zig | -0.182 |
arium | -0.179 |
zag | -0.178 |
rob | -0.177 |
Token | k |
Token ID | 479 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Zig | +0.071 |
ousel | +0.069 |
rob | +0.068 |
arium | +0.066 |
zag | +0.063 |
Neg logit contributions | |
worry | -0.045 |
permission | -0.043 |
pick | -0.039 |
herself | -0.038 |
finger | -0.037 |
Token | ites |
Token ID | 2737 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Zig | +0.183 |
ousel | +0.178 |
steep | +0.158 |
arium | +0.143 |
girls | +0.141 |
Neg logit contributions | |
worry | -0.317 |
permission | -0.301 |
She | -0.292 |
Her | -0.292 |
herself | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Zig | +0.453 |
ousel | +0.432 |
rob | +0.421 |
girls | +0.405 |
steep | +0.401 |
Neg logit contributions | |
worry | -0.262 |
herself | -0.258 |
permission | -0.237 |
pick | -0.232 |
She | -0.228 |
Token | They |
Token ID | 1119 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
She | +0.022 |
Her | +0.022 |
herself | +0.021 |
worry | +0.021 |
Daddy | +0.020 |
Neg logit contributions | |
ousel | -0.032 |
rob | -0.031 |
zag | -0.030 |
steep | -0.029 |
Zig | -0.028 |
Token | watch |
Token ID | 2342 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Zig | +0.044 |
ousel | +0.043 |
arium | +0.040 |
lights | +0.040 |
rob | +0.040 |
Neg logit contributions | |
worry | -0.019 |
pick | -0.017 |
permission | -0.015 |
herself | -0.015 |
She | -0.015 |
Token | them |
Token ID | 606 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
her | +0.048 |
worry | +0.047 |
herself | +0.047 |
pick | +0.042 |
permission | +0.041 |
Neg logit contributions | |
rob | -0.115 |
ousel | -0.115 |
arium | -0.112 |
zag | -0.111 |
Zig | -0.110 |
Token | soar |
Token ID | 48701 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Zig | +0.047 |
ousel | +0.047 |
rob | +0.045 |
arium | +0.044 |
steep | +0.043 |
Neg logit contributions | |
worry | -0.030 |
herself | -0.027 |
permission | -0.026 |
pick | -0.026 |
She | -0.025 |
Token | c |
Token ID | 269 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ousel | +0.016 |
Zig | +0.015 |
steep | +0.014 |
zag | +0.014 |
girls | +0.014 |
Neg logit contributions | |
worry | -0.011 |
permission | -0.010 |
herself | -0.010 |
Her | -0.009 |
She | -0.009 |
Token | udd |
Token ID | 4185 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
permission | +0.023 |
worry | +0.023 |
herself | +0.023 |
Her | +0.023 |
She | +0.023 |
Neg logit contributions | |
Zig | -0.020 |
ousel | -0.020 |
steep | -0.018 |
girls | -0.017 |
arium | -0.016 |
Token | les |
Token ID | 829 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
ousel | +0.070 |
Zig | +0.070 |
steep | +0.064 |
girls | +0.062 |
zag | +0.061 |
Neg logit contributions | |
worry | -0.050 |
permission | -0.049 |
herself | -0.048 |
Her | -0.046 |
She | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
worry | +0.042 |
permission | +0.041 |
herself | +0.040 |
She | +0.037 |
Her | +0.037 |
Neg logit contributions | |
ousel | -0.067 |
Zig | -0.067 |
steep | -0.062 |
girls | -0.059 |
rob | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
worry | +0.014 |
permission | +0.013 |
herself | +0.013 |
She | +0.012 |
Her | +0.012 |
Neg logit contributions | |
ousel | -0.023 |
Zig | -0.023 |
steep | -0.021 |
girls | -0.021 |
zag | -0.021 |
Token | Flash |
Token ID | 9973 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ousel | +0.020 |
Zig | +0.020 |
steep | +0.018 |
girls | +0.018 |
zag | +0.018 |
Neg logit contributions | |
worry | -0.013 |
permission | -0.012 |
herself | -0.011 |
Her | -0.011 |
She | -0.011 |
Token | y |
Token ID | 88 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
ousel | +0.556 |
Zig | +0.548 |
steep | +0.528 |
rob | +0.518 |
ramp | +0.504 |
Neg logit contributions | |
worry | -0.231 |
permission | -0.193 |
herself | -0.176 |
Her | -0.170 |
her | -0.164 |
Token | was |
Token ID | 373 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
worry | +0.132 |
permission | +0.118 |
herself | +0.115 |
pick | +0.109 |
her | +0.109 |
Neg logit contributions | |
Zig | -0.175 |
ousel | -0.170 |
steep | -0.158 |
rob | -0.156 |
girls | -0.150 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ousel | +0.156 |
Zig | +0.156 |
girls | +0.143 |
rob | +0.140 |
steep | +0.140 |
Neg logit contributions | |
worry | -0.089 |
herself | -0.082 |
permission | -0.081 |
Her | -0.076 |
She | -0.076 |
Token | for |
Token ID | 329 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
worry | +0.031 |
permission | +0.029 |
herself | +0.028 |
Her | +0.027 |
She | +0.027 |
Neg logit contributions | |
ousel | -0.045 |
Zig | -0.044 |
steep | -0.041 |
girls | -0.040 |
zag | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ousel | +0.135 |
Zig | +0.134 |
steep | +0.126 |
girls | +0.122 |
zag | +0.121 |
Neg logit contributions | |
worry | -0.042 |
permission | -0.037 |
herself | -0.034 |
Her | -0.033 |
She | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
ousel | +0.029 |
Zig | +0.027 |
steep | +0.027 |
lights | +0.026 |
zag | +0.025 |
Neg logit contributions | |
worry | -0.018 |
herself | -0.017 |
permission | -0.016 |
her | -0.016 |
pick | -0.015 |
Token | snail |
Token ID | 47374 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
ousel | +0.080 |
Zig | +0.079 |
steep | +0.072 |
girls | +0.070 |
lights | +0.069 |
Neg logit contributions | |
worry | -0.063 |
permission | -0.057 |
herself | -0.056 |
pick | -0.054 |
She | -0.053 |
Token | kept |
Token ID | 4030 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
worry | +0.033 |
pick | +0.031 |
herself | +0.029 |
She | +0.028 |
permission | +0.028 |
Neg logit contributions | |
Zig | -0.054 |
lights | -0.050 |
ousel | -0.050 |
steep | -0.050 |
arium | -0.049 |
Token | running |
Token ID | 2491 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ousel | +0.055 |
Zig | +0.055 |
arium | +0.055 |
lights | +0.054 |
steep | +0.051 |
Neg logit contributions | |
worry | -0.037 |
herself | -0.036 |
permission | -0.035 |
her | -0.035 |
understanding | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
arium | +0.183 |
Zig | +0.181 |
ousel | +0.181 |
rob | +0.180 |
sed | +0.177 |
Neg logit contributions | |
herself | -0.089 |
worry | -0.082 |
pick | -0.075 |
her | -0.074 |
permission | -0.073 |
Token | faster |
Token ID | 5443 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
worry | +0.010 |
herself | +0.010 |
permission | +0.009 |
pick | +0.009 |
understanding | +0.009 |
Neg logit contributions | |
Zig | -0.017 |
ousel | -0.016 |
rob | -0.015 |
arium | -0.015 |
lights | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Zig | +0.555 |
ousel | +0.547 |
girls | +0.503 |
arium | +0.502 |
steep | +0.493 |
Neg logit contributions | |
worry | -0.309 |
permission | -0.290 |
herself | -0.288 |
She | -0.261 |
understanding | -0.253 |
Token | faster |
Token ID | 5443 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
arium | +0.024 |
ousel | +0.024 |
Zig | +0.023 |
lights | +0.023 |
rob | +0.022 |
Neg logit contributions | |
herself | -0.022 |
worry | -0.022 |
understanding | -0.020 |
her | -0.019 |
pick | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
Zig | +0.543 |
ousel | +0.543 |
arium | +0.499 |
girls | +0.493 |
steep | +0.487 |
Neg logit contributions | |
worry | -0.318 |
permission | -0.300 |
herself | -0.299 |
She | -0.266 |
understanding | -0.261 |
Token | The |
Token ID | 383 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
herself | +0.005 |
She | +0.004 |
pick | +0.004 |
Her | +0.004 |
permission | +0.004 |
Neg logit contributions | |
ousel | -0.006 |
rob | -0.006 |
lights | -0.006 |
Zig | -0.006 |
zag | -0.006 |
Token | frog |
Token ID | 21264 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
Zig | +0.109 |
ousel | +0.108 |
steep | +0.097 |
girls | +0.094 |
arium | +0.092 |
Neg logit contributions | |
worry | -0.094 |
permission | -0.088 |
herself | -0.084 |
Her | -0.082 |
She | -0.082 |
Token | storm |
Token ID | 6388 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
worry | +0.015 |
permission | +0.012 |
Daddy | +0.011 |
understanding | +0.011 |
pick | +0.011 |
Neg logit contributions | |
ousel | -0.040 |
Zig | -0.039 |
girls | -0.037 |
steep | -0.036 |
rob | -0.036 |
Token | came |
Token ID | 1625 |
Feature activation | +2.32e-03 |
Pos logit contributions | |
Zig | +0.185 |
ousel | +0.182 |
steep | +0.178 |
girls | +0.177 |
arium | +0.168 |
Neg logit contributions | |
worry | -0.091 |
pick | -0.077 |
She | -0.071 |
Who | -0.070 |
spit | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
ousel | +0.006 |
rob | +0.006 |
Zig | +0.006 |
lights | +0.006 |
girls | +0.006 |
Neg logit contributions | |
worry | -0.002 |
permission | -0.002 |
herself | -0.002 |
She | -0.002 |
pick | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
worry | +0.006 |
permission | +0.005 |
pick | +0.005 |
her | +0.005 |
Who | +0.004 |
Neg logit contributions | |
ousel | -0.009 |
Zig | -0.008 |
rob | -0.008 |
girls | -0.008 |
zag | -0.008 |
Token | r |
Token ID | 374 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
worry | +0.061 |
spit | +0.049 |
pick | +0.047 |
She | +0.043 |
M | +0.043 |
Neg logit contributions | |
Zig | -0.117 |
rob | -0.115 |
ousel | -0.114 |
girls | -0.114 |
arium | -0.105 |
Token | ained |
Token ID | 1328 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Zig | +0.007 |
ousel | +0.007 |
steep | +0.006 |
arium | +0.006 |
girls | +0.006 |
Neg logit contributions | |
worry | -0.011 |
herself | -0.011 |
permission | -0.011 |
She | -0.011 |
Her | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ousel | +0.521 |
girls | +0.505 |
rob | +0.494 |
Zig | +0.483 |
arium | +0.466 |
Neg logit contributions | |
herself | -0.211 |
her | -0.189 |
She | -0.180 |
worry | -0.170 |
Her | -0.151 |
Token | night |
Token ID | 1755 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
worry | +0.021 |
her | +0.019 |
herself | +0.019 |
pick | +0.016 |
care | +0.016 |
Neg logit contributions | |
girls | -0.032 |
ousel | -0.032 |
Zig | -0.031 |
sed | -0.030 |
arium | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
ousel | +0.082 |
Zig | +0.081 |
girls | +0.077 |
rob | +0.074 |
steep | +0.073 |
Neg logit contributions | |
worry | -0.034 |
herself | -0.032 |
She | -0.030 |
permission | -0.029 |
pick | -0.029 |
Token | When |
Token ID | 1649 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
worry | +0.019 |
herself | +0.018 |
Her | +0.017 |
She | +0.016 |
permission | +0.016 |
Neg logit contributions | |
ousel | -0.030 |
rob | -0.030 |
girls | -0.029 |
zag | -0.028 |
steep | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ousel | +0.003 |
girls | +0.003 |
zag | +0.003 |
Zig | +0.003 |
rob | +0.003 |
Neg logit contributions | |
worry | -0.002 |
her | -0.001 |
herself | -0.001 |
permission | -0.001 |
Daddy | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
Zig | +0.168 |
rob | +0.167 |
ousel | +0.166 |
girls | +0.166 |
arium | +0.162 |
Neg logit contributions | |
worry | -0.084 |
herself | -0.081 |
her | -0.075 |
permission | -0.074 |
understanding | -0.074 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Zig | +0.130 |
ousel | +0.128 |
girls | +0.124 |
rob | +0.122 |
arium | +0.118 |
Neg logit contributions | |
worry | -0.056 |
understanding | -0.044 |
herself | -0.044 |
permission | -0.043 |
Her | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
Zig | +0.093 |
ousel | +0.092 |
steep | +0.085 |
girls | +0.084 |
zag | +0.082 |
Neg logit contributions | |
worry | -0.042 |
permission | -0.039 |
herself | -0.037 |
She | -0.035 |
Her | -0.035 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
She | +0.006 |
Her | +0.006 |
herself | +0.006 |
Daddy | +0.005 |
worry | +0.005 |
Neg logit contributions | |
ousel | -0.011 |
steep | -0.010 |
Zig | -0.010 |
rob | -0.010 |
zag | -0.010 |
Token | asked |
Token ID | 1965 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
lights | +0.326 |
Zig | +0.313 |
steep | +0.305 |
ousel | +0.298 |
rob | +0.293 |
Neg logit contributions | |
worry | -0.164 |
pick | -0.158 |
herself | -0.155 |
She | -0.145 |
her | -0.144 |
Token | Dash |
Token ID | 16189 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
herself | +0.003 |
Her | +0.003 |
She | +0.003 |
Neg logit contributions | |
ousel | -0.005 |
Zig | -0.005 |
steep | -0.004 |
zag | -0.004 |
girls | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
Zig | +0.477 |
ousel | +0.475 |
steep | +0.453 |
rob | +0.439 |
lights | +0.435 |
Neg logit contributions | |
worry | -0.281 |
permission | -0.279 |
herself | -0.259 |
pick | -0.245 |
Her | -0.244 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
her | +0.104 |
worry | +0.101 |
herself | +0.095 |
permission | +0.093 |
understanding | +0.092 |
Neg logit contributions | |
ousel | -0.194 |
lights | -0.181 |
Zig | -0.178 |
zag | -0.176 |
steep | -0.175 |
Token | result |
Token ID | 1255 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Zig | +0.065 |
ousel | +0.062 |
lights | +0.060 |
arium | +0.059 |
girls | +0.058 |
Neg logit contributions | |
worry | -0.060 |
permission | -0.056 |
pick | -0.054 |
herself | -0.050 |
gard | -0.050 |
Token | was |
Token ID | 373 |
Feature activation | +6.52e-02 |
Pos logit contributions | |
worry | +0.199 |
herself | +0.188 |
her | +0.180 |
permission | +0.177 |
pick | +0.170 |
Neg logit contributions | |
Zig | -0.335 |
ousel | -0.320 |
steep | -0.305 |
girls | -0.304 |
sed | -0.294 |
Token | and |
Token ID | 290 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
Zig | +0.161 |
ousel | +0.153 |
girls | +0.146 |
rob | +0.142 |
steep | +0.141 |
Neg logit contributions | |
permission | -0.083 |
worry | -0.080 |
herself | -0.076 |
pick | -0.071 |
understanding | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
Zig | +0.114 |
ousel | +0.114 |
girls | +0.104 |
steep | +0.103 |
arium | +0.102 |
Neg logit contributions | |
worry | -0.061 |
herself | -0.061 |
permission | -0.058 |
She | -0.057 |
Her | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-04 |
Pos logit contributions | |
She | +0.004 |
Her | +0.004 |
herself | +0.003 |
Daddy | +0.003 |
worry | +0.003 |
Neg logit contributions | |
ousel | -0.007 |
zag | -0.006 |
rob | -0.006 |
Zig | -0.006 |
steep | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
ousel | +0.002 |
Zig | +0.002 |
girls | +0.002 |
steep | +0.002 |
sed | +0.002 |
Neg logit contributions | |
She | -0.001 |
Her | -0.001 |
Daddy | -0.001 |
herself | -0.001 |
M | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
worry | +0.001 |
She | +0.001 |
Her | +0.001 |
permission | +0.001 |
herself | +0.001 |
Neg logit contributions | |
Zig | -0.003 |
ousel | -0.003 |
steep | -0.003 |
girls | -0.003 |
zag | -0.003 |
Token | z |
Token ID | 1976 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
Zig | +0.026 |
ousel | +0.026 |
steep | +0.024 |
girls | +0.024 |
arium | +0.024 |
Neg logit contributions | |
worry | -0.016 |
permission | -0.016 |
pick | -0.014 |
herself | -0.014 |
She | -0.014 |
Token | ebra |
Token ID | 37052 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
steep | +0.221 |
Zig | +0.219 |
ousel | +0.192 |
girls | +0.186 |
igators | +0.176 |
Neg logit contributions | |
permission | -0.329 |
Her | -0.313 |
worry | -0.304 |
She | -0.299 |
herself | -0.299 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
Zig | +0.426 |
steep | +0.425 |
lights | +0.416 |
rob | +0.415 |
girls | +0.413 |
Neg logit contributions | |
worry | -0.197 |
pick | -0.192 |
spit | -0.181 |
her | -0.174 |
herself | -0.167 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
herself | +0.021 |
her | +0.020 |
worry | +0.019 |
permission | +0.019 |
Her | +0.018 |
Neg logit contributions | |
ousel | -0.049 |
steep | -0.046 |
zag | -0.046 |
Zig | -0.046 |
girls | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-03 |
Pos logit contributions | |
ousel | +0.149 |
Zig | +0.149 |
steep | +0.136 |
girls | +0.132 |
zag | +0.129 |
Neg logit contributions | |
worry | -0.101 |
permission | -0.095 |
herself | -0.089 |
Her | -0.089 |
She | -0.087 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
ousel | +0.010 |
Zig | +0.010 |
steep | +0.010 |
girls | +0.010 |
zag | +0.010 |
Neg logit contributions | |
worry | -0.006 |
her | -0.005 |
herself | -0.005 |
Her | -0.005 |
pick | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +5.10e-03 |
Pos logit contributions | |
ousel | +0.037 |
Zig | +0.036 |
steep | +0.033 |
girls | +0.032 |
zag | +0.031 |
Neg logit contributions | |
worry | -0.031 |
permission | -0.030 |
Daddy | -0.029 |
Her | -0.029 |
She | -0.028 |
Token | there |
Token ID | 612 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
worry | +0.038 |
She | +0.033 |
Her | +0.033 |
herself | +0.033 |
pick | +0.031 |
Neg logit contributions | |
ousel | -0.076 |
Zig | -0.073 |
girls | -0.072 |
rob | -0.069 |
steep | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
ousel | +0.099 |
Zig | +0.093 |
girls | +0.090 |
steep | +0.089 |
lights | +0.085 |
Neg logit contributions | |
worry | -0.073 |
herself | -0.065 |
Her | -0.062 |
pick | -0.062 |
She | -0.061 |
Token | a |
Token ID | 257 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ousel | +0.108 |
Zig | +0.107 |
steep | +0.099 |
girls | +0.097 |
zag | +0.095 |
Neg logit contributions | |
worry | -0.057 |
permission | -0.052 |
herself | -0.051 |
Her | -0.050 |
She | -0.049 |
Token | friendly |
Token ID | 8030 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
worry | +0.014 |
permission | +0.013 |
herself | +0.012 |
Her | +0.012 |
She | +0.011 |
Neg logit contributions | |
Zig | -0.039 |
ousel | -0.039 |
steep | -0.037 |
girls | -0.036 |
zag | -0.035 |
Token | cat |
Token ID | 3797 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ousel | +0.093 |
Zig | +0.090 |
steep | +0.087 |
girls | +0.086 |
lights | +0.083 |
Neg logit contributions | |
worry | -0.051 |
permission | -0.044 |
pick | -0.043 |
Daddy | -0.041 |
herself | -0.041 |
Token | named |
Token ID | 3706 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Zig | +0.043 |
ousel | +0.043 |
steep | +0.042 |
girls | +0.039 |
lights | +0.038 |
Neg logit contributions | |
worry | -0.048 |
Her | -0.047 |
She | -0.046 |
herself | -0.046 |
pick | -0.045 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
ousel | +0.306 |
Zig | +0.294 |
steep | +0.270 |
girls | +0.257 |
zag | +0.255 |
Neg logit contributions | |
worry | -0.340 |
permission | -0.320 |
herself | -0.314 |
Her | -0.312 |
She | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
ousel | +0.130 |
Zig | +0.130 |
steep | +0.119 |
girls | +0.115 |
zag | +0.113 |
Neg logit contributions | |
worry | -0.091 |
permission | -0.086 |
herself | -0.081 |
Her | -0.081 |
She | -0.080 |
Token | He |
Token ID | 679 |
Feature activation | +9.57e-04 |
Pos logit contributions | |
worry | +0.037 |
herself | +0.034 |
She | +0.034 |
Her | +0.034 |
permission | +0.033 |
Neg logit contributions | |
ousel | -0.038 |
Zig | -0.037 |
steep | -0.033 |
arium | -0.033 |
girls | -0.032 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ousel | +0.002 |
lights | +0.002 |
steep | +0.002 |
Zig | +0.002 |
arium | +0.002 |
Neg logit contributions | |
Her | -0.001 |
worry | -0.001 |
She | -0.001 |
her | -0.001 |
herself | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
Zig | +0.221 |
ousel | +0.218 |
steep | +0.197 |
girls | +0.188 |
zag | +0.186 |
Neg logit contributions | |
worry | -0.222 |
permission | -0.211 |
Her | -0.195 |
herself | -0.193 |
She | -0.191 |
Token | they |
Token ID | 484 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
ousel | +0.214 |
Zig | +0.213 |
steep | +0.201 |
girls | +0.195 |
rob | +0.194 |
Neg logit contributions | |
worry | -0.209 |
permission | -0.195 |
herself | -0.194 |
her | -0.186 |
pick | -0.184 |
Token | continued |
Token ID | 3767 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
ousel | +0.175 |
Zig | +0.172 |
steep | +0.165 |
rob | +0.163 |
zag | +0.160 |
Neg logit contributions | |
worry | -0.098 |
permission | -0.093 |
herself | -0.089 |
pick | -0.089 |
her | -0.086 |
Token | dancing |
Token ID | 15360 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
ousel | +0.132 |
Zig | +0.126 |
steep | +0.121 |
rob | +0.118 |
girls | +0.115 |
Neg logit contributions | |
worry | -0.091 |
permission | -0.090 |
her | -0.089 |
herself | -0.087 |
pick | -0.086 |
Token | in |
Token ID | 287 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
ousel | +0.293 |
Zig | +0.279 |
steep | +0.272 |
girls | +0.268 |
rob | +0.267 |
Neg logit contributions | |
herself | -0.171 |
her | -0.166 |
worry | -0.136 |
permission | -0.136 |
pick | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ousel | +0.210 |
Zig | +0.200 |
zag | +0.191 |
rob | +0.187 |
steep | +0.185 |
Neg logit contributions | |
worry | -0.118 |
herself | -0.107 |
permission | -0.106 |
her | -0.105 |
pick | -0.098 |
Token | rain |
Token ID | 6290 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ousel | +0.085 |
Zig | +0.084 |
girls | +0.080 |
zag | +0.077 |
rob | +0.077 |
Neg logit contributions | |
worry | -0.052 |
She | -0.045 |
pick | -0.043 |
herself | -0.043 |
permission | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-04 |
Pos logit contributions | |
Zig | +0.141 |
ousel | +0.137 |
girls | +0.128 |
sed | +0.125 |
Skip | +0.125 |
Neg logit contributions | |
worry | -0.068 |
herself | -0.065 |
She | -0.058 |
pick | -0.057 |
permission | -0.055 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ousel | +0.001 |
Zig | +0.001 |
steep | +0.001 |
girls | +0.001 |
zag | +0.001 |
Neg logit contributions | |
worry | -0.001 |
herself | -0.001 |
permission | -0.001 |
Her | -0.001 |
She | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
ousel | +0.037 |
steep | +0.034 |
Zig | +0.034 |
sed | +0.033 |
lights | +0.032 |
Neg logit contributions | |
She | -0.018 |
herself | -0.017 |
M | -0.017 |
Daddy | -0.016 |
her | -0.015 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
worry | +0.099 |
herself | +0.085 |
permission | +0.085 |
Her | +0.084 |
her | +0.083 |
Neg logit contributions | |
ousel | -0.171 |
Zig | -0.165 |
girls | -0.161 |
rob | -0.157 |
steep | -0.150 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
worry | +0.009 |
permission | +0.009 |
Her | +0.008 |
herself | +0.008 |
Daddy | +0.007 |
Neg logit contributions | |
Zig | -0.012 |
ousel | -0.011 |
steep | -0.011 |
Zoom | -0.010 |
girls | -0.010 |
Token | ily |
Token ID | 813 |
Feature activation | -1.17e-03 |
Pos logit contributions | |
worry | +0.115 |
permission | +0.097 |
understanding | +0.095 |
Her | +0.093 |
She | +0.092 |
Neg logit contributions | |
Zig | -0.149 |
ousel | -0.148 |
arium | -0.135 |
steep | -0.128 |
girls | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | -2.21e-03 |
Pos logit contributions | |
pick | +0.001 |
worry | +0.001 |
her | +0.001 |
herself | +0.001 |
She | +0.001 |
Neg logit contributions | |
Zig | -0.003 |
lights | -0.003 |
ousel | -0.003 |
steep | -0.003 |
girls | -0.003 |
Token | Ben |
Token ID | 3932 |
Feature activation | +8.28e-03 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
Her | +0.002 |
herself | +0.002 |
She | +0.002 |
Neg logit contributions | |
Zig | -0.005 |
ousel | -0.005 |
steep | -0.004 |
Zoom | -0.004 |
girls | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
Zig | +0.017 |
ousel | +0.017 |
steep | +0.016 |
girls | +0.015 |
zag | +0.015 |
Neg logit contributions | |
worry | -0.013 |
permission | -0.012 |
herself | -0.011 |
She | -0.011 |
Her | -0.011 |
Token | playing |
Token ID | 2712 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
worry | +0.088 |
permission | +0.083 |
herself | +0.079 |
She | +0.077 |
Her | +0.077 |
Neg logit contributions | |
Zig | -0.130 |
ousel | -0.128 |
steep | -0.119 |
girls | -0.115 |
zag | -0.114 |
Token | in |
Token ID | 287 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
Zig | +0.070 |
ousel | +0.070 |
steep | +0.067 |
girls | +0.063 |
lights | +0.062 |
Neg logit contributions | |
worry | -0.043 |
herself | -0.042 |
permission | -0.041 |
Her | -0.040 |
She | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
Zig | +0.150 |
ousel | +0.149 |
steep | +0.134 |
girls | +0.129 |
Zoom | +0.128 |
Neg logit contributions | |
worry | -0.126 |
permission | -0.120 |
Her | -0.112 |
herself | -0.110 |
She | -0.110 |
Token | park |
Token ID | 3952 |
Feature activation | +7.39e-02 |
Pos logit contributions | |
Zig | +0.041 |
ousel | +0.041 |
steep | +0.037 |
girls | +0.036 |
zag | +0.035 |
Neg logit contributions | |
worry | -0.036 |
permission | -0.034 |
herself | -0.033 |
Her | -0.033 |
She | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Zig | +0.171 |
ousel | +0.168 |
steep | +0.156 |
girls | +0.153 |
rob | +0.150 |
Neg logit contributions | |
worry | -0.097 |
herself | -0.090 |
permission | -0.089 |
Her | -0.087 |
She | -0.085 |
Token | They |
Token ID | 1119 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
worry | +0.052 |
permission | +0.050 |
herself | +0.048 |
Her | +0.048 |
She | +0.048 |
Neg logit contributions | |
ousel | -0.041 |
Zig | -0.040 |
steep | -0.035 |
girls | -0.034 |
zag | -0.034 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ousel | +0.039 |
Zig | +0.039 |
girls | +0.035 |
steep | +0.035 |
zag | +0.035 |
Neg logit contributions | |
worry | -0.028 |
herself | -0.025 |
permission | -0.025 |
She | -0.025 |
pick | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
worry | +0.062 |
permission | +0.058 |
Her | +0.058 |
herself | +0.058 |
She | +0.058 |
Neg logit contributions | |
ousel | -0.054 |
Zig | -0.052 |
steep | -0.047 |
girls | -0.046 |
rob | -0.045 |
Token | found |
Token ID | 1043 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
ousel | +0.027 |
Zig | +0.027 |
steep | +0.024 |
girls | +0.023 |
zag | +0.023 |
Neg logit contributions | |
worry | -0.023 |
permission | -0.021 |
herself | -0.021 |
Her | -0.020 |
She | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
worry | +0.104 |
permission | +0.098 |
herself | +0.093 |
Her | +0.090 |
She | +0.088 |
Neg logit contributions | |
ousel | -0.199 |
Zig | -0.195 |
steep | -0.181 |
girls | -0.177 |
zag | -0.175 |
Token | shiny |
Token ID | 22441 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
worry | +0.023 |
permission | +0.022 |
Her | +0.020 |
herself | +0.020 |
She | +0.020 |
Neg logit contributions | |
Zig | -0.035 |
ousel | -0.035 |
steep | -0.032 |
girls | -0.032 |
zag | -0.031 |
Token | ring |
Token ID | 5858 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
Zig | +0.009 |
ousel | +0.009 |
girls | +0.008 |
steep | +0.008 |
zag | +0.008 |
Neg logit contributions | |
worry | -0.006 |
permission | -0.006 |
herself | -0.006 |
Her | -0.005 |
She | -0.005 |
Token | under |
Token ID | 739 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Zig | +0.100 |
ousel | +0.095 |
steep | +0.092 |
girls | +0.092 |
arium | +0.088 |
Neg logit contributions | |
worry | -0.058 |
herself | -0.054 |
permission | -0.053 |
pick | -0.053 |
She | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
Zig | +0.287 |
ousel | +0.278 |
steep | +0.254 |
Zoom | +0.248 |
girls | +0.244 |
Neg logit contributions | |
worry | -0.210 |
permission | -0.197 |
Her | -0.180 |
She | -0.178 |
herself | -0.176 |
Token | big |
Token ID | 1263 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
worry | +0.024 |
permission | +0.023 |
herself | +0.021 |
Her | +0.021 |
understanding | +0.020 |
Neg logit contributions | |
Zig | -0.026 |
ousel | -0.026 |
steep | -0.024 |
zag | -0.022 |
girls | -0.022 |
Token | rock |
Token ID | 3881 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
worry | +0.078 |
permission | +0.078 |
Her | +0.072 |
herself | +0.071 |
She | +0.070 |
Neg logit contributions | |
ousel | -0.080 |
Zig | -0.079 |
steep | -0.073 |
ramp | -0.066 |
arium | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
worry | +0.039 |
permission | +0.036 |
herself | +0.035 |
She | +0.034 |
pick | +0.034 |
Neg logit contributions | |
Zig | -0.073 |
ousel | -0.070 |
steep | -0.067 |
girls | -0.066 |
Zoom | -0.064 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
Her | +0.037 |
herself | +0.037 |
pick | +0.037 |
She | +0.037 |
worry | +0.036 |
Neg logit contributions | |
ousel | -0.057 |
rob | -0.054 |
Zig | -0.054 |
zag | -0.053 |
girls | -0.053 |
Token | face |
Token ID | 1986 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
Zig | +0.004 |
ousel | +0.004 |
steep | +0.004 |
girls | +0.004 |
zag | +0.004 |
Neg logit contributions | |
worry | -0.003 |
permission | -0.002 |
herself | -0.002 |
Her | -0.002 |
She | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
worry | +0.339 |
permission | +0.321 |
herself | +0.307 |
Her | +0.300 |
She | +0.297 |
Neg logit contributions | |
Zig | -0.455 |
ousel | -0.452 |
steep | -0.412 |
girls | -0.402 |
arium | -0.391 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
worry | +0.028 |
permission | +0.025 |
herself | +0.024 |
She | +0.023 |
Her | +0.023 |
Neg logit contributions | |
ousel | -0.045 |
Zig | -0.045 |
rob | -0.041 |
zag | -0.041 |
girls | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
Zig | +0.043 |
ousel | +0.041 |
steep | +0.040 |
lights | +0.039 |
rob | +0.039 |
Neg logit contributions | |
worry | -0.028 |
herself | -0.026 |
permission | -0.025 |
She | -0.024 |
pick | -0.024 |
Token | That |
Token ID | 1320 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
worry | +0.028 |
permission | +0.026 |
herself | +0.025 |
Her | +0.025 |
She | +0.024 |
Neg logit contributions | |
ousel | -0.032 |
Zig | -0.032 |
steep | -0.029 |
girls | -0.028 |
zag | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
worry | +0.149 |
permission | +0.137 |
herself | +0.133 |
pick | +0.129 |
She | +0.129 |
Neg logit contributions | |
Zig | -0.138 |
ousel | -0.136 |
steep | -0.118 |
girls | -0.118 |
Zoom | -0.113 |
Token | just |
Token ID | 655 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
worry | +0.098 |
permission | +0.088 |
herself | +0.087 |
pick | +0.077 |
her | +0.077 |
Neg logit contributions | |
ousel | -0.205 |
Zig | -0.200 |
rob | -0.191 |
girls | -0.184 |
zag | -0.184 |
Token | your |
Token ID | 534 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
ousel | +0.196 |
Zig | +0.193 |
rob | +0.179 |
girls | +0.179 |
zag | +0.178 |
Neg logit contributions | |
worry | -0.104 |
permission | -0.099 |
herself | -0.095 |
pick | -0.088 |
her | -0.085 |
Token | imagination |
Token ID | 13843 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
ousel | +0.022 |
Zig | +0.021 |
steep | +0.019 |
rob | +0.019 |
girls | +0.019 |
Neg logit contributions | |
worry | -0.014 |
permission | -0.013 |
herself | -0.012 |
Her | -0.012 |
pick | -0.012 |
Token | ." |
Token ID | 526 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
worry | +0.005 |
herself | +0.005 |
permission | +0.004 |
She | +0.004 |
pick | +0.004 |
Neg logit contributions | |
Zig | -0.008 |
ousel | -0.007 |
steep | -0.007 |
rob | -0.007 |
girls | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
ousel | +0.135 |
steep | +0.129 |
Zig | +0.129 |
zag | +0.123 |
lights | +0.119 |
Neg logit contributions | |
worry | -0.069 |
She | -0.068 |
Her | -0.067 |
herself | -0.066 |
Daddy | -0.063 |
Token | ." |
Token ID | 526 |
Feature activation | +8.03e-02 |
Pos logit contributions | |
worry | +0.065 |
herself | +0.062 |
permission | +0.060 |
She | +0.057 |
pick | +0.056 |
Neg logit contributions | |
Zig | -0.090 |
ousel | -0.085 |
girls | -0.079 |
rob | -0.078 |
steep | -0.077 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ousel | +0.164 |
Zig | +0.158 |
steep | +0.150 |
zag | +0.140 |
rob | +0.139 |
Neg logit contributions | |
worry | -0.128 |
permission | -0.122 |
herself | -0.119 |
Her | -0.115 |
She | -0.115 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
Zig | +0.038 |
ousel | +0.037 |
steep | +0.035 |
girls | +0.034 |
rob | +0.033 |
Neg logit contributions | |
worry | -0.031 |
permission | -0.028 |
herself | -0.028 |
Her | -0.027 |
She | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ousel | +0.087 |
Zig | +0.085 |
steep | +0.079 |
girls | +0.077 |
zag | +0.076 |
Neg logit contributions | |
worry | -0.060 |
permission | -0.056 |
herself | -0.053 |
Her | -0.050 |
understanding | -0.049 |
Token | idea |
Token ID | 2126 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
ousel | +0.064 |
Zig | +0.063 |
steep | +0.058 |
zag | +0.053 |
arium | +0.053 |
Neg logit contributions | |
worry | -0.054 |
permission | -0.054 |
Her | -0.053 |
She | -0.051 |
Daddy | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
worry | +0.082 |
permission | +0.078 |
Her | +0.075 |
herself | +0.074 |
She | +0.073 |
Neg logit contributions | |
ousel | -0.108 |
Zig | -0.106 |
steep | -0.098 |
girls | -0.093 |
zag | -0.092 |
Token | so |
Token ID | 523 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
worry | +0.012 |
permission | +0.011 |
herself | +0.010 |
Her | +0.010 |
She | +0.010 |
Neg logit contributions | |
Zig | -0.019 |
ousel | -0.019 |
steep | -0.017 |
girls | -0.017 |
zag | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ousel | +0.053 |
Zig | +0.052 |
rob | +0.050 |
girls | +0.049 |
steep | +0.047 |
Neg logit contributions | |
worry | -0.043 |
permission | -0.039 |
understanding | -0.039 |
herself | -0.038 |
Her | -0.036 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
Zig | +0.064 |
ousel | +0.060 |
rob | +0.059 |
steep | +0.059 |
girls | +0.058 |
Neg logit contributions | |
worry | -0.031 |
pick | -0.029 |
permission | -0.027 |
spit | -0.027 |
She | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
worry | +0.012 |
permission | +0.011 |
herself | +0.010 |
Her | +0.010 |
She | +0.010 |
Neg logit contributions | |
Zig | -0.015 |
ousel | -0.015 |
steep | -0.014 |
girls | -0.013 |
zag | -0.013 |
Token | lady |
Token ID | 10846 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
Zig | +0.014 |
ousel | +0.014 |
steep | +0.013 |
girls | +0.012 |
zag | +0.012 |
Neg logit contributions | |
worry | -0.007 |
permission | -0.007 |
herself | -0.007 |
Her | -0.006 |
She | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -8.97e-03 |
Pos logit contributions | |
worry | +0.054 |
permission | +0.049 |
herself | +0.046 |
pick | +0.046 |
She | +0.044 |
Neg logit contributions | |
Zig | -0.088 |
ousel | -0.086 |
rob | -0.078 |
girls | -0.078 |
Zoom | -0.076 |
Token | And |
Token ID | 843 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
worry | +0.016 |
permission | +0.015 |
herself | +0.014 |
Her | +0.014 |
She | +0.014 |
Neg logit contributions | |
ousel | -0.017 |
Zig | -0.016 |
steep | -0.015 |
zag | -0.014 |
rob | -0.014 |
Token | we |
Token ID | 356 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ousel | +0.141 |
Zig | +0.140 |
steep | +0.128 |
girls | +0.124 |
zag | +0.123 |
Neg logit contributions | |
worry | -0.118 |
permission | -0.111 |
herself | -0.106 |
Her | -0.102 |
She | -0.101 |
Token | can |
Token ID | 460 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
ousel | +0.028 |
Zig | +0.028 |
steep | +0.025 |
girls | +0.024 |
zag | +0.023 |
Neg logit contributions | |
worry | -0.032 |
permission | -0.030 |
herself | -0.029 |
Her | -0.029 |
She | -0.028 |
Token | make |
Token ID | 787 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
ousel | +0.137 |
Zig | +0.136 |
girls | +0.126 |
zag | +0.125 |
steep | +0.122 |
Neg logit contributions | |
permission | -0.092 |
worry | -0.088 |
Daddy | -0.081 |
Her | -0.080 |
Who | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | +3.06e-03 |
Pos logit contributions | |
worry | +0.124 |
permission | +0.115 |
Her | +0.111 |
She | +0.108 |
Daddy | +0.106 |
Neg logit contributions | |
Zig | -0.180 |
ousel | -0.175 |
steep | -0.160 |
girls | -0.157 |
Zoom | -0.153 |
Token | fence |
Token ID | 13990 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
Zig | +0.006 |
ousel | +0.006 |
steep | +0.006 |
girls | +0.005 |
zag | +0.005 |
Neg logit contributions | |
worry | -0.005 |
permission | -0.004 |
herself | -0.004 |
Her | -0.004 |
She | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e-03 |
Pos logit contributions | |
Zig | +0.014 |
ousel | +0.013 |
rob | +0.012 |
steep | +0.012 |
girls | +0.012 |
Neg logit contributions | |
worry | -0.009 |
permission | -0.008 |
herself | -0.008 |
She | -0.008 |
pick | -0.008 |
Token | keep |
Token ID | 1394 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
worry | +0.001 |
permission | +0.001 |
herself | +0.001 |
Her | +0.001 |
She | +0.001 |
Neg logit contributions | |
ousel | -0.003 |
Zig | -0.003 |
steep | -0.003 |
girls | -0.003 |
zag | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
worry | +0.106 |
permission | +0.101 |
herself | +0.096 |
Her | +0.090 |
She | +0.089 |
Neg logit contributions | |
ousel | -0.162 |
Zig | -0.159 |
steep | -0.147 |
zag | -0.142 |
girls | -0.141 |
Token | rabbits |
Token ID | 33043 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
Zig | +0.096 |
ousel | +0.096 |
steep | +0.088 |
girls | +0.085 |
zag | +0.084 |
Neg logit contributions | |
worry | -0.059 |
permission | -0.055 |
herself | -0.051 |
Her | -0.051 |
She | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
worry | +0.043 |
permission | +0.040 |
herself | +0.037 |
Her | +0.037 |
She | +0.036 |
Neg logit contributions | |
ousel | -0.080 |
Zig | -0.080 |
steep | -0.074 |
girls | -0.072 |
zag | -0.071 |
Token | perfect |
Token ID | 2818 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
Zig | +0.075 |
ousel | +0.075 |
steep | +0.068 |
girls | +0.066 |
zag | +0.065 |
Neg logit contributions | |
worry | -0.058 |
permission | -0.055 |
herself | -0.052 |
Her | -0.051 |
She | -0.051 |
Token | pony |
Token ID | 26902 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
worry | +0.017 |
permission | +0.016 |
herself | +0.015 |
Her | +0.014 |
pick | +0.014 |
Neg logit contributions | |
Zig | -0.025 |
ousel | -0.024 |
steep | -0.022 |
girls | -0.022 |
zag | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -2.67e-03 |
Pos logit contributions | |
Zig | +0.268 |
ousel | +0.258 |
steep | +0.252 |
lights | +0.248 |
rob | +0.240 |
Neg logit contributions | |
worry | -0.136 |
permission | -0.134 |
herself | -0.130 |
pick | -0.119 |
She | -0.117 |
Token | She |
Token ID | 1375 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
worry | +0.003 |
permission | +0.003 |
herself | +0.003 |
Her | +0.003 |
She | +0.003 |
Neg logit contributions | |
Zig | -0.006 |
ousel | -0.006 |
steep | -0.006 |
girls | -0.006 |
Zoom | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
worry | +0.049 |
permission | +0.043 |
pick | +0.043 |
herself | +0.042 |
Her | +0.042 |
Neg logit contributions | |
Zig | -0.084 |
ousel | -0.082 |
steep | -0.078 |
girls | -0.077 |
lights | -0.076 |
Token | a |
Token ID | 257 |
Feature activation | +6.59e-04 |
Pos logit contributions | |
worry | +0.019 |
permission | +0.018 |
herself | +0.017 |
Her | +0.017 |
She | +0.017 |
Neg logit contributions | |
ousel | -0.032 |
Zig | -0.031 |
steep | -0.029 |
girls | -0.028 |
zag | -0.028 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
Zig | +0.001 |
ousel | +0.001 |
steep | +0.001 |
girls | +0.001 |
zag | +0.001 |
Neg logit contributions | |
worry | -0.001 |
permission | -0.001 |
herself | -0.001 |
Her | -0.001 |
She | -0.001 |
Token | pony |
Token ID | 26902 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Zig | +0.076 |
ousel | +0.074 |
girls | +0.073 |
steep | +0.069 |
lights | +0.066 |
Neg logit contributions | |
worry | -0.048 |
pick | -0.042 |
permission | -0.041 |
herself | -0.041 |
Her | -0.040 |
Token | that |
Token ID | 326 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
Zig | +0.235 |
ousel | +0.228 |
steep | +0.218 |
lights | +0.211 |
girls | +0.209 |
Neg logit contributions | |
worry | -0.161 |
permission | -0.148 |
herself | -0.147 |
She | -0.144 |
pick | -0.141 |
Token | was |
Token ID | 373 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
worry | +0.022 |
herself | +0.021 |
her | +0.021 |
Her | +0.020 |
She | +0.020 |
Neg logit contributions | |
ousel | -0.039 |
Zig | -0.038 |
girls | -0.037 |
steep | -0.035 |
zag | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
worry | +0.011 |
permission | +0.010 |
Her | +0.010 |
herself | +0.009 |
She | +0.009 |
Neg logit contributions | |
Zig | -0.015 |
ousel | -0.015 |
steep | -0.013 |
girls | -0.013 |
arium | -0.013 |
Token | park |
Token ID | 3952 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
Zig | +0.050 |
ousel | +0.050 |
steep | +0.045 |
girls | +0.043 |
zag | +0.042 |
Neg logit contributions | |
worry | -0.047 |
permission | -0.045 |
herself | -0.043 |
Her | -0.043 |
She | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
Zig | +0.157 |
ousel | +0.152 |
girls | +0.145 |
steep | +0.145 |
rob | +0.140 |
Neg logit contributions | |
worry | -0.090 |
herself | -0.083 |
permission | -0.083 |
pick | -0.081 |
Her | -0.080 |
Token | play |
Token ID | 711 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
worry | +0.011 |
permission | +0.010 |
Her | +0.010 |
herself | +0.010 |
She | +0.010 |
Neg logit contributions | |
ousel | -0.014 |
Zig | -0.014 |
steep | -0.013 |
girls | -0.012 |
arium | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
herself | +0.010 |
worry | +0.010 |
Her | +0.010 |
She | +0.010 |
permission | +0.010 |
Neg logit contributions | |
Zig | -0.020 |
ousel | -0.020 |
steep | -0.019 |
girls | -0.019 |
zag | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
worry | +0.004 |
permission | +0.003 |
herself | +0.003 |
Her | +0.002 |
She | +0.002 |
Neg logit contributions | |
ousel | -0.047 |
Zig | -0.046 |
steep | -0.045 |
girls | -0.043 |
zag | -0.043 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
worry | +0.102 |
herself | +0.101 |
permission | +0.101 |
Her | +0.096 |
pick | +0.092 |
Neg logit contributions | |
Zig | -0.227 |
ousel | -0.226 |
steep | -0.216 |
arium | -0.209 |
encl | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
permission | +0.014 |
worry | +0.014 |
herself | +0.013 |
pick | +0.013 |
Her | +0.012 |
Neg logit contributions | |
Zig | -0.031 |
ousel | -0.030 |
steep | -0.029 |
rob | -0.028 |
lights | -0.028 |
Token | When |
Token ID | 1649 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
worry | +0.024 |
permission | +0.022 |
herself | +0.022 |
Her | +0.022 |
She | +0.022 |
Neg logit contributions | |
ousel | -0.037 |
Zig | -0.037 |
steep | -0.035 |
rob | -0.034 |
girls | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ousel | +0.006 |
Zig | +0.006 |
steep | +0.005 |
girls | +0.005 |
zag | +0.005 |
Neg logit contributions | |
worry | -0.005 |
herself | -0.005 |
Her | -0.005 |
her | -0.005 |
She | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
worry | +0.065 |
pick | +0.057 |
Her | +0.057 |
her | +0.055 |
She | +0.055 |
Neg logit contributions | |
girls | -0.099 |
Zig | -0.099 |
ousel | -0.097 |
steep | -0.093 |
lights | -0.089 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ousel | +0.027 |
Zig | +0.026 |
steep | +0.025 |
girls | +0.024 |
zag | +0.023 |
Neg logit contributions | |
worry | -0.017 |
Her | -0.017 |
She | -0.016 |
herself | -0.016 |
permission | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ousel | +0.024 |
Zig | +0.024 |
steep | +0.022 |
arium | +0.021 |
zag | +0.021 |
Neg logit contributions | |
worry | -0.013 |
permission | -0.012 |
herself | -0.010 |
pick | -0.009 |
gard | -0.009 |
Token | I |
Token ID | 40 |
Feature activation | -8.21e-02 |
Pos logit contributions | |
worry | +0.169 |
permission | +0.163 |
herself | +0.134 |
vel | +0.127 |
pick | +0.126 |
Neg logit contributions | |
ousel | -0.241 |
Zig | -0.239 |
steep | -0.225 |
Zoom | -0.221 |
rob | -0.215 |
Token | don |
Token ID | 836 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
worry | +0.116 |
permission | +0.115 |
Her | +0.114 |
herself | +0.114 |
She | +0.108 |
Neg logit contributions | |
ousel | -0.166 |
Zig | -0.164 |
steep | -0.158 |
zag | -0.147 |
girls | -0.146 |
Token | 't |
Token ID | 470 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
permission | +0.141 |
worry | +0.139 |
daughter | +0.124 |
gard | +0.121 |
understanding | +0.119 |
Neg logit contributions | |
ousel | -0.110 |
Zig | -0.104 |
Zoom | -0.095 |
zag | -0.089 |
steep | -0.087 |
Token | want |
Token ID | 765 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Her | +0.014 |
Who | +0.012 |
what | +0.012 |
She | +0.012 |
Sweet | +0.011 |
Neg logit contributions | |
steep | -0.013 |
ousel | -0.012 |
Zig | -0.010 |
Zoom | -0.010 |
wins | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -9.23e-04 |
Pos logit contributions | |
worry | +0.207 |
permission | +0.199 |
herself | +0.189 |
Her | +0.177 |
pick | +0.174 |
Neg logit contributions | |
ousel | -0.292 |
Zig | -0.290 |
steep | -0.264 |
girls | -0.258 |
zag | -0.258 |
Token | ," |
Token ID | 553 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
permission | +0.001 |
Her | +0.001 |
hire | +0.001 |
gard | +0.001 |
She | +0.001 |
Neg logit contributions | |
ousel | -0.002 |
Zig | -0.002 |
Zoom | -0.002 |
steep | -0.002 |
zag | -0.002 |
Token | replied |
Token ID | 8712 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
Zig | +0.074 |
ousel | +0.074 |
steep | +0.066 |
girls | +0.064 |
Zoom | +0.062 |
Neg logit contributions | |
worry | -0.070 |
permission | -0.068 |
herself | -0.063 |
Her | -0.063 |
She | -0.063 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
ousel | +0.021 |
Zig | +0.021 |
steep | +0.020 |
girls | +0.019 |
zag | +0.019 |
Neg logit contributions | |
worry | -0.011 |
permission | -0.010 |
herself | -0.010 |
Her | -0.010 |
She | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +9.52e-03 |
Pos logit contributions | |
ousel | +0.043 |
Zig | +0.041 |
steep | +0.036 |
zag | +0.036 |
girls | +0.036 |
Neg logit contributions | |
worry | -0.042 |
permission | -0.041 |
Daddy | -0.040 |
She | -0.039 |
Her | -0.039 |
Token | then |
Token ID | 788 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ousel | +0.062 |
rob | +0.060 |
Zig | +0.059 |
girls | +0.059 |
steep | +0.059 |
Neg logit contributions | |
worry | -0.044 |
herself | -0.041 |
her | -0.039 |
permission | -0.039 |
Her | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
ousel | +0.259 |
Zig | +0.247 |
steep | +0.239 |
girls | +0.233 |
zag | +0.230 |
Neg logit contributions | |
worry | -0.178 |
permission | -0.159 |
herself | -0.157 |
Her | -0.151 |
She | -0.148 |
Token | remembered |
Token ID | 12086 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
worry | +0.005 |
permission | +0.004 |
She | +0.004 |
Daddy | +0.004 |
Her | +0.004 |
Neg logit contributions | |
Zig | -0.011 |
ousel | -0.011 |
rob | -0.010 |
steep | -0.010 |
lights | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
worry | +0.037 |
permission | +0.034 |
herself | +0.032 |
Her | +0.031 |
She | +0.030 |
Neg logit contributions | |
ousel | -0.075 |
Zig | -0.075 |
steep | -0.070 |
girls | -0.068 |
zag | -0.067 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
worry | +0.095 |
permission | +0.084 |
daughter | +0.069 |
understanding | +0.069 |
pick | +0.068 |
Neg logit contributions | |
Zig | -0.208 |
ousel | -0.208 |
rob | -0.203 |
girls | -0.193 |
arium | -0.189 |
Token | my |
Token ID | 1820 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
worry | +0.068 |
permission | +0.064 |
herself | +0.060 |
Her | +0.060 |
She | +0.059 |
Neg logit contributions | |
Zig | -0.094 |
ousel | -0.094 |
steep | -0.086 |
girls | -0.083 |
zag | -0.081 |
Token | telling |
Token ID | 5149 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
worry | +0.166 |
permission | +0.156 |
herself | +0.146 |
Her | +0.143 |
She | +0.142 |
Neg logit contributions | |
Zig | -0.227 |
ousel | -0.225 |
steep | -0.208 |
girls | -0.198 |
zag | -0.195 |
Token | her |
Token ID | 607 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
worry | +0.002 |
permission | +0.002 |
Daddy | +0.002 |
She | +0.002 |
Her | +0.002 |
Neg logit contributions | |
Zig | -0.009 |
ousel | -0.008 |
steep | -0.008 |
Zoom | -0.008 |
girls | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
worry | +0.128 |
permission | +0.122 |
herself | +0.118 |
Her | +0.114 |
She | +0.112 |
Neg logit contributions | |
ousel | -0.162 |
Zig | -0.160 |
steep | -0.147 |
girls | -0.144 |
rob | -0.143 |
Token | shadows |
Token ID | 16187 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
worry | +0.018 |
permission | +0.016 |
herself | +0.015 |
Her | +0.014 |
She | +0.014 |
Neg logit contributions | |
ousel | -0.041 |
Zig | -0.040 |
steep | -0.038 |
girls | -0.037 |
zag | -0.037 |
Token | can |
Token ID | 460 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
Zig | +0.149 |
ousel | +0.147 |
rob | +0.139 |
girls | +0.137 |
steep | +0.133 |
Neg logit contributions | |
worry | -0.115 |
herself | -0.103 |
permission | -0.101 |
her | -0.097 |
She | -0.097 |
Token | ." |
Token ID | 526 |
Feature activation | +7.85e-02 |
Pos logit contributions | |
worry | +0.054 |
herself | +0.053 |
permission | +0.049 |
She | +0.048 |
her | +0.047 |
Neg logit contributions | |
Zig | -0.101 |
ousel | -0.097 |
rob | -0.092 |
girls | -0.090 |
steep | -0.089 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ousel | +0.156 |
Zig | +0.147 |
steep | +0.146 |
arium | +0.137 |
rob | +0.137 |
Neg logit contributions | |
worry | -0.129 |
herself | -0.124 |
Her | -0.122 |
She | -0.120 |
permission | -0.117 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
Zig | +0.079 |
ousel | +0.078 |
steep | +0.072 |
girls | +0.069 |
arium | +0.068 |
Neg logit contributions | |
worry | -0.061 |
permission | -0.057 |
herself | -0.054 |
Her | -0.054 |
She | -0.053 |
Token | of |
Token ID | 286 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
herself | +0.160 |
permission | +0.159 |
worry | +0.158 |
her | +0.149 |
Her | +0.140 |
Neg logit contributions | |
ousel | -0.200 |
Zig | -0.194 |
girls | -0.190 |
rob | -0.184 |
encl | -0.183 |
Token | a |
Token ID | 257 |
Feature activation | +9.95e-04 |
Pos logit contributions | |
worry | +0.029 |
permission | +0.028 |
Her | +0.027 |
She | +0.026 |
Daddy | +0.026 |
Neg logit contributions | |
Zig | -0.043 |
ousel | -0.043 |
steep | -0.039 |
girls | -0.038 |
Zoom | -0.037 |
Token | plan |
Token ID | 1410 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
steep | +0.002 |
Zig | +0.002 |
ousel | +0.002 |
zag | +0.002 |
ramp | +0.002 |
Neg logit contributions | |
herself | -0.002 |
permission | -0.002 |
Her | -0.002 |
She | -0.001 |
Daddy | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
worry | +0.145 |
permission | +0.138 |
herself | +0.134 |
Her | +0.125 |
She | +0.123 |
Neg logit contributions | |
Zig | -0.264 |
ousel | -0.262 |
steep | -0.246 |
girls | -0.240 |
arium | -0.236 |
Token | He |
Token ID | 679 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ousel | +0.010 |
Zig | +0.009 |
steep | +0.009 |
rob | +0.009 |
arium | +0.009 |
Neg logit contributions | |
worry | -0.007 |
She | -0.007 |
herself | -0.007 |
Her | -0.007 |
permission | -0.006 |
Token | decided |
Token ID | 3066 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
Zig | +0.058 |
lights | +0.056 |
ousel | +0.054 |
rob | +0.054 |
steep | +0.054 |
Neg logit contributions | |
worry | -0.021 |
spit | -0.020 |
pick | -0.020 |
M | -0.018 |
permission | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.33e-03 |
Pos logit contributions | |
worry | +0.046 |
permission | +0.045 |
herself | +0.044 |
her | +0.041 |
pick | +0.040 |
Neg logit contributions | |
ousel | -0.085 |
Zig | -0.085 |
rob | -0.083 |
girls | -0.082 |
lights | -0.081 |
Token | bury |
Token ID | 30033 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
ousel | +0.003 |
Zig | +0.003 |
steep | +0.003 |
girls | +0.003 |
zag | +0.003 |
Neg logit contributions | |
worry | -0.002 |
permission | -0.001 |
herself | -0.001 |
Her | -0.001 |
She | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
worry | +0.004 |
permission | +0.004 |
herself | +0.004 |
Her | +0.004 |
She | +0.004 |
Neg logit contributions | |
Zig | -0.007 |
ousel | -0.007 |
steep | -0.006 |
girls | -0.006 |
zag | -0.006 |
Token | pictures |
Token ID | 5986 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
ousel | +0.069 |
Zig | +0.067 |
steep | +0.063 |
girls | +0.060 |
Zoom | +0.058 |
Neg logit contributions | |
worry | -0.067 |
permission | -0.065 |
Her | -0.063 |
herself | -0.061 |
She | -0.060 |
Token | of |
Token ID | 286 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
worry | +0.009 |
herself | +0.009 |
permission | +0.008 |
She | +0.008 |
Her | +0.008 |
Neg logit contributions | |
Zig | -0.018 |
ousel | -0.018 |
girls | -0.016 |
steep | -0.016 |
rob | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
worry | +0.027 |
permission | +0.025 |
herself | +0.024 |
Her | +0.023 |
She | +0.023 |
Neg logit contributions | |
ousel | -0.042 |
Zig | -0.042 |
steep | -0.039 |
zag | -0.037 |
girls | -0.037 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Zig | +0.074 |
ousel | +0.074 |
steep | +0.067 |
girls | +0.064 |
zag | +0.063 |
Neg logit contributions | |
worry | -0.065 |
permission | -0.061 |
herself | -0.058 |
Her | -0.058 |
She | -0.057 |
Token | things |
Token ID | 1243 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
worry | +0.022 |
permission | +0.020 |
herself | +0.020 |
She | +0.019 |
Her | +0.019 |
Neg logit contributions | |
Zig | -0.031 |
ousel | -0.030 |
steep | -0.028 |
girls | -0.027 |
zag | -0.027 |
Token | inside |
Token ID | 2641 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
worry | +0.118 |
herself | +0.110 |
permission | +0.102 |
She | +0.100 |
Her | +0.095 |
Neg logit contributions | |
Zig | -0.327 |
ousel | -0.323 |
girls | -0.302 |
steep | -0.299 |
zag | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
ousel | +0.111 |
Zig | +0.111 |
steep | +0.102 |
girls | +0.098 |
zag | +0.096 |
Neg logit contributions | |
worry | -0.078 |
permission | -0.073 |
Her | -0.069 |
herself | -0.068 |
She | -0.067 |
Token | |
Token ID | 220 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
worry | +0.009 |
permission | +0.008 |
herself | +0.008 |
Her | +0.008 |
She | +0.008 |
Neg logit contributions | |
ousel | -0.013 |
Zig | -0.013 |
steep | -0.012 |
girls | -0.012 |
zag | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
herself | +0.039 |
She | +0.038 |
worry | +0.038 |
Her | +0.038 |
permission | +0.036 |
Neg logit contributions | |
ousel | -0.064 |
Zig | -0.062 |
steep | -0.059 |
girls | -0.057 |
rob | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +2.72e-03 |
Pos logit contributions | |
Zig | +0.009 |
ousel | +0.009 |
steep | +0.008 |
girls | +0.007 |
Zoom | +0.007 |
Neg logit contributions | |
worry | -0.009 |
permission | -0.008 |
herself | -0.007 |
Her | -0.007 |
She | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
worry | +0.121 |
her | +0.109 |
permission | +0.104 |
pick | +0.099 |
herself | +0.097 |
Neg logit contributions | |
ousel | -0.211 |
Zig | -0.201 |
zag | -0.193 |
girls | -0.189 |
rob | -0.187 |
Token | does |
Token ID | 857 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
pick | +0.074 |
worry | +0.074 |
She | +0.073 |
herself | +0.071 |
her | +0.068 |
Neg logit contributions | |
Zig | -0.099 |
ousel | -0.096 |
lights | -0.092 |
steep | -0.086 |
girls | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
Zig | +0.221 |
ousel | +0.220 |
steep | +0.201 |
girls | +0.196 |
zag | +0.190 |
Neg logit contributions | |
worry | -0.156 |
permission | -0.147 |
herself | -0.139 |
Her | -0.138 |
She | -0.136 |
Token |
|
Token ID | 198 |
Feature activation | -2.75e-03 |
Pos logit contributions | |
She | +0.024 |
Her | +0.024 |
worry | +0.023 |
Daddy | +0.022 |
herself | +0.022 |
Neg logit contributions | |
ousel | -0.057 |
rob | -0.052 |
Zig | -0.051 |
zag | -0.051 |
steep | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
She | +0.003 |
Her | +0.003 |
herself | +0.003 |
worry | +0.003 |
Daddy | +0.003 |
Neg logit contributions | |
ousel | -0.007 |
Zig | -0.006 |
steep | -0.006 |
girls | -0.006 |
rob | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
worry | +0.004 |
permission | +0.004 |
herself | +0.004 |
Her | +0.003 |
She | +0.003 |
Neg logit contributions | |
ousel | -0.009 |
Zig | -0.009 |
steep | -0.008 |
girls | -0.008 |
zag | -0.007 |
Token | Should |
Token ID | 19926 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
worry | +0.151 |
permission | +0.143 |
herself | +0.129 |
Her | +0.124 |
She | +0.120 |
Neg logit contributions | |
Zig | -0.306 |
ousel | -0.304 |
steep | -0.283 |
girls | -0.274 |
zag | -0.269 |
Token | we |
Token ID | 356 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
worry | +0.027 |
permission | +0.022 |
pick | +0.022 |
finger | +0.020 |
her | +0.019 |
Neg logit contributions | |
rob | -0.048 |
ousel | -0.046 |
steep | -0.042 |
encl | -0.041 |
habitats | -0.041 |
Token | press |
Token ID | 1803 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ousel | +0.015 |
Zig | +0.015 |
steep | +0.013 |
girls | +0.013 |
zag | +0.013 |
Neg logit contributions | |
worry | -0.007 |
permission | -0.007 |
herself | -0.006 |
Her | -0.006 |
She | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
ousel | +0.147 |
Zig | +0.147 |
zag | +0.142 |
girls | +0.142 |
rob | +0.136 |
Neg logit contributions | |
worry | -0.062 |
permission | -0.060 |
herself | -0.059 |
her | -0.056 |
Her | -0.047 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
worry | +0.073 |
herself | +0.070 |
She | +0.068 |
Her | +0.068 |
her | +0.066 |
Neg logit contributions | |
Zig | -0.107 |
girls | -0.103 |
ousel | -0.101 |
steep | -0.098 |
encl | -0.097 |