Token | placed |
Token ID | 4624 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
virtue | +0.136 |
vous | +0.134 |
rig | +0.132 |
importance | +0.128 |
Yes | +0.126 |
Neg logit contributions | |
down | -0.113 |
ged | -0.111 |
iked | -0.107 |
onward | -0.100 |
am | -0.097 |
Token | it |
Token ID | 340 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
ged | +0.115 |
down | +0.114 |
iked | +0.109 |
onward | +0.102 |
ls | +0.097 |
Neg logit contributions | |
vous | -0.180 |
virtue | -0.180 |
rig | -0.177 |
importance | -0.173 |
Yes | -0.172 |
Token | onto |
Token ID | 4291 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
iked | +0.089 |
ged | +0.087 |
inspection | +0.082 |
onward | +0.081 |
leys | +0.080 |
Neg logit contributions | |
importance | -0.074 |
vous | -0.073 |
bit | -0.073 |
Yes | -0.072 |
rig | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
down | +0.034 |
ged | +0.031 |
onward | +0.028 |
, | +0.028 |
iked | +0.028 |
Neg logit contributions | |
vous | -0.057 |
rig | -0.056 |
virtue | -0.055 |
leaf | -0.053 |
importance | -0.053 |
Token | wheel |
Token ID | 7825 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
down | +0.012 |
ged | +0.011 |
, | +0.010 |
onward | +0.010 |
iked | +0.010 |
Neg logit contributions | |
vous | -0.017 |
rig | -0.016 |
virtue | -0.016 |
leaf | -0.016 |
Yes | -0.015 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
ged | +0.010 |
iked | +0.010 |
down | +0.010 |
onward | +0.009 |
ls | +0.009 |
Neg logit contributions | |
vous | -0.016 |
virtue | -0.016 |
rig | -0.016 |
Yes | -0.016 |
importance | -0.015 |
Token | row |
Token ID | 808 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
ged | +0.375 |
iked | +0.363 |
down | +0.360 |
onward | +0.348 |
ls | +0.338 |
Neg logit contributions | |
vous | -0.521 |
virtue | -0.520 |
rig | -0.511 |
importance | -0.491 |
Yes | -0.485 |
Token | . |
Token ID | 13 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ged | +0.128 |
iked | +0.126 |
down | +0.118 |
ls | +0.117 |
onward | +0.116 |
Neg logit contributions | |
virtue | -0.163 |
vous | -0.159 |
rig | -0.157 |
importance | -0.156 |
Yes | -0.153 |
Token |
|
Token ID | 198 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
ged | +0.009 |
down | +0.009 |
iked | +0.009 |
onward | +0.008 |
ls | +0.008 |
Neg logit contributions | |
virtue | -0.016 |
vous | -0.016 |
rig | -0.016 |
Yes | -0.016 |
importance | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
virtue | +0.037 |
vous | +0.037 |
matter | +0.037 |
importance | +0.036 |
least | +0.035 |
Neg logit contributions | |
ged | -0.019 |
iked | -0.019 |
down | -0.019 |
onward | -0.019 |
leys | -0.017 |
Token | John |
Token ID | 7554 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
vous | +0.029 |
virtue | +0.029 |
rig | +0.029 |
importance | +0.028 |
matter | +0.028 |
Neg logit contributions | |
iked | -0.027 |
ged | -0.026 |
onward | -0.025 |
down | -0.025 |
leys | -0.024 |
Token | harder |
Token ID | 7069 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
virtue | +0.158 |
vous | +0.155 |
rig | +0.153 |
importance | +0.147 |
leaf | +0.142 |
Neg logit contributions | |
down | -0.123 |
ged | -0.114 |
iked | -0.104 |
onward | -0.102 |
, | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
iked | +0.070 |
ged | +0.069 |
down | +0.065 |
onward | +0.064 |
leys | +0.063 |
Neg logit contributions | |
virtue | -0.104 |
rig | -0.101 |
importance | -0.101 |
vous | -0.100 |
Yes | -0.099 |
Token | push |
Token ID | 4574 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
vous | +0.078 |
virtue | +0.077 |
rig | +0.076 |
importance | +0.074 |
leaf | +0.072 |
Neg logit contributions | |
down | -0.071 |
ged | -0.064 |
, | -0.059 |
onward | -0.058 |
his | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
down | +0.066 |
ged | +0.065 |
iked | +0.059 |
onward | +0.058 |
ls | +0.054 |
Neg logit contributions | |
vous | -0.109 |
virtue | -0.108 |
rig | -0.107 |
importance | -0.105 |
Yes | -0.103 |
Token | wheel |
Token ID | 7825 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
down | +0.005 |
ged | +0.004 |
, | +0.004 |
ls | +0.004 |
onward | +0.004 |
Neg logit contributions | |
vous | -0.007 |
rig | -0.007 |
virtue | -0.006 |
Yes | -0.006 |
leaf | -0.006 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
ged | +0.001 |
iked | +0.001 |
down | +0.001 |
onward | +0.001 |
leys | +0.001 |
Neg logit contributions | |
virtue | -0.002 |
vous | -0.002 |
rig | -0.002 |
Yes | -0.002 |
importance | -0.001 |
Token | row |
Token ID | 808 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
ged | +0.285 |
iked | +0.276 |
down | +0.274 |
onward | +0.251 |
ls | +0.237 |
Neg logit contributions | |
virtue | -0.621 |
vous | -0.620 |
rig | -0.612 |
Yes | -0.598 |
importance | -0.597 |
Token | . |
Token ID | 13 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
iked | +0.117 |
ged | +0.117 |
down | +0.104 |
onward | +0.102 |
leys | +0.102 |
Neg logit contributions | |
virtue | -0.177 |
vous | -0.171 |
rig | -0.170 |
Yes | -0.167 |
importance | -0.166 |
Token | But |
Token ID | 887 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
down | +0.008 |
ged | +0.008 |
iked | +0.008 |
onward | +0.007 |
am | +0.006 |
Neg logit contributions | |
vous | -0.016 |
virtue | -0.016 |
rig | -0.015 |
importance | -0.015 |
leaf | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
vous | +0.123 |
rig | +0.121 |
virtue | +0.118 |
leaf | +0.116 |
importance | +0.114 |
Neg logit contributions | |
down | -0.088 |
ged | -0.084 |
iked | -0.077 |
onward | -0.076 |
, | -0.076 |
Token | backyard |
Token ID | 24296 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
down | +0.113 |
, | +0.110 |
am | +0.109 |
ged | +0.101 |
iked | +0.097 |
Neg logit contributions | |
vous | -0.190 |
leaf | -0.186 |
rig | -0.180 |
Yes | -0.173 |
virtue | -0.173 |
Token | He |
Token ID | 679 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
down | +0.011 |
ged | +0.011 |
iked | +0.011 |
onward | +0.010 |
am | +0.010 |
Neg logit contributions | |
vous | -0.022 |
virtue | -0.022 |
rig | -0.022 |
importance | -0.021 |
Yes | -0.021 |
Token | jumped |
Token ID | 11687 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
ged | +0.123 |
down | +0.118 |
am | +0.114 |
, | +0.112 |
his | +0.107 |
Neg logit contributions | |
virtue | -0.245 |
vous | -0.233 |
leaf | -0.224 |
rig | -0.224 |
importance | -0.217 |
Token | onto |
Token ID | 4291 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
iked | +0.201 |
leys | +0.192 |
ged | +0.189 |
am | +0.181 |
onward | +0.164 |
Neg logit contributions | |
Yes | -0.252 |
rig | -0.248 |
virtue | -0.241 |
importance | -0.230 |
bit | -0.230 |
Token | the |
Token ID | 262 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
down | +0.029 |
ged | +0.027 |
his | +0.025 |
, | +0.024 |
onward | +0.024 |
Neg logit contributions | |
vous | -0.054 |
rig | -0.054 |
virtue | -0.053 |
importance | -0.050 |
leaf | -0.049 |
Token | wheel |
Token ID | 7825 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
down | +0.014 |
ged | +0.014 |
iked | +0.013 |
onward | +0.013 |
ls | +0.012 |
Neg logit contributions | |
vous | -0.017 |
virtue | -0.017 |
rig | -0.017 |
Yes | -0.016 |
importance | -0.016 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
ged | +0.005 |
down | +0.005 |
iked | +0.005 |
onward | +0.005 |
leys | +0.005 |
Neg logit contributions | |
virtue | -0.007 |
vous | -0.007 |
rig | -0.006 |
Yes | -0.006 |
importance | -0.006 |
Token | row |
Token ID | 808 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
ged | +0.359 |
iked | +0.351 |
down | +0.346 |
onward | +0.329 |
ls | +0.321 |
Neg logit contributions | |
vous | -0.533 |
virtue | -0.526 |
rig | -0.521 |
Yes | -0.503 |
importance | -0.498 |
Token | and |
Token ID | 290 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
ged | +0.125 |
iked | +0.123 |
down | +0.120 |
onward | +0.113 |
leys | +0.112 |
Neg logit contributions | |
virtue | -0.163 |
vous | -0.162 |
rig | -0.159 |
Yes | -0.157 |
importance | -0.156 |
Token | started |
Token ID | 2067 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
virtue | +0.137 |
vous | +0.136 |
rig | +0.134 |
importance | +0.131 |
Yes | +0.130 |
Neg logit contributions | |
ged | -0.100 |
down | -0.100 |
iked | -0.096 |
onward | -0.090 |
ls | -0.086 |
Token | rolling |
Token ID | 10708 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
ged | +0.168 |
iked | +0.168 |
leys | +0.166 |
onward | +0.163 |
ls | +0.163 |
Neg logit contributions | |
Yes | -0.143 |
vous | -0.140 |
rig | -0.140 |
importance | -0.139 |
virtue | -0.138 |
Token | around |
Token ID | 1088 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
iked | +0.174 |
leys | +0.160 |
ged | +0.151 |
am | +0.146 |
onward | +0.142 |
Neg logit contributions | |
Yes | -0.224 |
virtue | -0.203 |
rig | -0.201 |
vous | -0.200 |
importance | -0.198 |
Token | back |
Token ID | 736 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
ged | +0.167 |
iked | +0.164 |
ls | +0.156 |
leys | +0.151 |
onward | +0.149 |
Neg logit contributions | |
vous | -0.252 |
Yes | -0.248 |
rig | -0.246 |
virtue | -0.243 |
importance | -0.239 |
Token | with |
Token ID | 351 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
down | +0.160 |
ged | +0.155 |
iked | +0.151 |
onward | +0.142 |
am | +0.133 |
Neg logit contributions | |
virtue | -0.212 |
vous | -0.211 |
rig | -0.206 |
importance | -0.203 |
Yes | -0.200 |
Token | a |
Token ID | 257 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
rig | +0.050 |
virtue | +0.049 |
vous | +0.048 |
leaf | +0.046 |
Yes | +0.046 |
Neg logit contributions | |
down | -0.040 |
ged | -0.039 |
onward | -0.036 |
iked | -0.036 |
, | -0.034 |
Token | big |
Token ID | 1263 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
vous | +0.128 |
virtue | +0.125 |
rig | +0.125 |
Yes | +0.122 |
leaf | +0.121 |
Neg logit contributions | |
down | -0.104 |
ged | -0.101 |
onward | -0.094 |
iked | -0.094 |
, | -0.092 |
Token | wheel |
Token ID | 7825 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
vous | +0.050 |
virtue | +0.050 |
rig | +0.050 |
Yes | +0.048 |
importance | +0.048 |
Neg logit contributions | |
down | -0.031 |
ged | -0.031 |
iked | -0.029 |
onward | -0.027 |
ls | -0.026 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
ged | +0.006 |
down | +0.006 |
iked | +0.006 |
onward | +0.006 |
leys | +0.006 |
Neg logit contributions | |
vous | -0.008 |
virtue | -0.008 |
rig | -0.008 |
Yes | -0.008 |
importance | -0.008 |
Token | row |
Token ID | 808 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ged | +0.336 |
down | +0.332 |
iked | +0.329 |
onward | +0.310 |
ls | +0.294 |
Neg logit contributions | |
vous | -0.553 |
virtue | -0.547 |
rig | -0.537 |
importance | -0.527 |
Yes | -0.524 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ged | +0.122 |
iked | +0.120 |
down | +0.119 |
onward | +0.112 |
leys | +0.109 |
Neg logit contributions | |
virtue | -0.159 |
vous | -0.159 |
rig | -0.155 |
importance | -0.153 |
Yes | -0.152 |
Token | He |
Token ID | 679 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
down | +0.006 |
iked | +0.006 |
ged | +0.005 |
onward | +0.005 |
am | +0.005 |
Neg logit contributions | |
vous | -0.022 |
virtue | -0.021 |
matter | -0.021 |
rig | -0.021 |
importance | -0.021 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
ged | +0.144 |
down | +0.137 |
am | +0.137 |
, | +0.134 |
iked | +0.132 |
Neg logit contributions | |
virtue | -0.223 |
vous | -0.218 |
rig | -0.209 |
matter | -0.207 |
leaf | -0.207 |
Token | the |
Token ID | 262 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
ged | +0.093 |
down | +0.091 |
iked | +0.090 |
onward | +0.083 |
leys | +0.079 |
Neg logit contributions | |
virtue | -0.160 |
vous | -0.160 |
rig | -0.157 |
Yes | -0.155 |
importance | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ged | +0.147 |
iked | +0.146 |
down | +0.139 |
onward | +0.131 |
leys | +0.129 |
Neg logit contributions | |
virtue | -0.207 |
vous | -0.206 |
rig | -0.204 |
Yes | -0.203 |
importance | -0.203 |
Token | She |
Token ID | 1375 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
ged | +0.007 |
down | +0.006 |
iked | +0.006 |
onward | +0.005 |
ls | +0.005 |
Neg logit contributions | |
vous | -0.019 |
virtue | -0.019 |
rig | -0.019 |
Yes | -0.019 |
importance | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
ged | +0.115 |
down | +0.112 |
iked | +0.112 |
am | +0.107 |
, | +0.102 |
Neg logit contributions | |
virtue | -0.147 |
vous | -0.142 |
rig | -0.141 |
leaf | -0.135 |
Yes | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
down | +0.097 |
ged | +0.095 |
iked | +0.091 |
onward | +0.085 |
, | +0.084 |
Neg logit contributions | |
virtue | -0.121 |
rig | -0.118 |
vous | -0.118 |
Yes | -0.110 |
importance | -0.110 |
Token | wheel |
Token ID | 7825 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
vous | +0.134 |
rig | +0.128 |
virtue | +0.124 |
leaf | +0.123 |
Yes | +0.120 |
Neg logit contributions | |
down | -0.109 |
ged | -0.101 |
, | -0.099 |
onward | -0.095 |
ashore | -0.092 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ged | +0.006 |
iked | +0.006 |
down | +0.006 |
onward | +0.006 |
leys | +0.005 |
Neg logit contributions | |
vous | -0.007 |
virtue | -0.007 |
rig | -0.007 |
Yes | -0.007 |
importance | -0.006 |
Token | row |
Token ID | 808 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ged | +0.359 |
iked | +0.355 |
down | +0.351 |
onward | +0.340 |
ls | +0.324 |
Neg logit contributions | |
vous | -0.526 |
virtue | -0.513 |
rig | -0.504 |
importance | -0.494 |
Yes | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
ged | +0.133 |
iked | +0.131 |
down | +0.125 |
leys | +0.122 |
onward | +0.121 |
Neg logit contributions | |
vous | -0.148 |
virtue | -0.145 |
rig | -0.143 |
importance | -0.142 |
Yes | -0.140 |
Token | a |
Token ID | 257 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
down | +0.246 |
ged | +0.228 |
his | +0.226 |
, | +0.222 |
he | +0.208 |
Neg logit contributions | |
virtue | -0.384 |
vous | -0.353 |
rig | -0.342 |
Yes | -0.316 |
importance | -0.316 |
Token | large |
Token ID | 1588 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
vous | +0.136 |
rig | +0.132 |
virtue | +0.131 |
Yes | +0.126 |
leaf | +0.125 |
Neg logit contributions | |
down | -0.108 |
ged | -0.105 |
onward | -0.096 |
iked | -0.096 |
, | -0.093 |
Token | sp |
Token ID | 599 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
vous | +0.066 |
virtue | +0.066 |
rig | +0.065 |
Yes | +0.064 |
importance | +0.063 |
Neg logit contributions | |
ged | -0.049 |
down | -0.049 |
iked | -0.047 |
onward | -0.045 |
ls | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
down | +0.207 |
ged | +0.198 |
iked | +0.195 |
onward | +0.181 |
am | +0.178 |
Neg logit contributions | |
virtue | -0.275 |
rig | -0.268 |
vous | -0.265 |
importance | -0.255 |
Yes | -0.251 |
Token | big |
Token ID | 1263 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
vous | +0.122 |
virtue | +0.121 |
rig | +0.119 |
Yes | +0.116 |
importance | +0.116 |
Neg logit contributions | |
down | -0.112 |
ged | -0.110 |
iked | -0.106 |
onward | -0.101 |
ls | -0.098 |
Token | , |
Token ID | 11 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
virtue | +0.044 |
vous | +0.043 |
Yes | +0.042 |
importance | +0.042 |
rig | +0.042 |
Neg logit contributions | |
iked | -0.037 |
ged | -0.037 |
down | -0.035 |
onward | -0.035 |
leys | -0.035 |
Token | spinning |
Token ID | 19493 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
down | +0.251 |
ged | +0.225 |
onward | +0.208 |
iked | +0.203 |
, | +0.200 |
Neg logit contributions | |
virtue | -0.350 |
vous | -0.339 |
rig | -0.336 |
Yes | -0.323 |
importance | -0.321 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
down | +0.132 |
ged | +0.127 |
iked | +0.114 |
, | +0.112 |
onward | +0.109 |
Neg logit contributions | |
vous | -0.172 |
virtue | -0.170 |
rig | -0.168 |
importance | -0.162 |
leaf | -0.159 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.50e+01 |
Pos logit contributions | |
ged | +0.004 |
iked | +0.004 |
down | +0.004 |
onward | +0.004 |
leys | +0.004 |
Neg logit contributions | |
vous | -0.005 |
virtue | -0.005 |
rig | -0.005 |
Yes | -0.005 |
importance | -0.005 |
Token | row |
Token ID | 808 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
ged | +0.351 |
iked | +0.347 |
down | +0.341 |
onward | +0.332 |
ls | +0.315 |
Neg logit contributions | |
vous | -0.526 |
virtue | -0.516 |
rig | -0.505 |
importance | -0.497 |
Yes | -0.490 |
Token | and |
Token ID | 290 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
ged | +0.137 |
iked | +0.136 |
leys | +0.129 |
onward | +0.128 |
down | +0.128 |
Neg logit contributions | |
virtue | -0.138 |
vous | -0.137 |
rig | -0.134 |
importance | -0.133 |
Yes | -0.132 |
Token | put |
Token ID | 1234 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
virtue | +0.122 |
vous | +0.122 |
rig | +0.120 |
Yes | +0.117 |
importance | +0.116 |
Neg logit contributions | |
ged | -0.119 |
down | -0.117 |
iked | -0.115 |
onward | -0.109 |
leys | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ged | +0.039 |
iked | +0.038 |
down | +0.038 |
onward | +0.035 |
leys | +0.034 |
Neg logit contributions | |
virtue | -0.057 |
vous | -0.057 |
rig | -0.056 |
Yes | -0.056 |
importance | -0.055 |
Token | pumpkin |
Token ID | 30089 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
down | +0.015 |
ged | +0.013 |
, | +0.012 |
iked | +0.012 |
am | +0.012 |
Neg logit contributions | |
rig | -0.029 |
vous | -0.028 |
virtue | -0.028 |
Yes | -0.027 |
leaf | -0.026 |
Token | him |
Token ID | 683 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
down | +0.076 |
ged | +0.074 |
iked | +0.068 |
onward | +0.064 |
am | +0.059 |
Neg logit contributions | |
virtue | -0.168 |
vous | -0.168 |
rig | -0.165 |
importance | -0.162 |
Yes | -0.157 |
Token | a |
Token ID | 257 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
down | +0.142 |
ged | +0.135 |
iked | +0.132 |
onward | +0.122 |
am | +0.120 |
Neg logit contributions | |
virtue | -0.239 |
vous | -0.238 |
rig | -0.233 |
importance | -0.229 |
Yes | -0.228 |
Token | big |
Token ID | 1263 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
vous | +0.135 |
virtue | +0.128 |
rig | +0.126 |
importance | +0.126 |
Yes | +0.124 |
Neg logit contributions | |
down | -0.108 |
ged | -0.098 |
iked | -0.093 |
, | -0.093 |
onward | -0.093 |
Token | red |
Token ID | 2266 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
vous | +0.051 |
rig | +0.050 |
virtue | +0.050 |
importance | +0.048 |
Yes | +0.047 |
Neg logit contributions | |
down | -0.041 |
ged | -0.039 |
, | -0.036 |
iked | -0.036 |
onward | -0.035 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ged | +0.002 |
down | +0.002 |
iked | +0.002 |
onward | +0.002 |
leys | +0.002 |
Neg logit contributions | |
virtue | -0.003 |
vous | -0.003 |
rig | -0.003 |
Yes | -0.003 |
importance | -0.003 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
ged | +0.004 |
down | +0.004 |
iked | +0.004 |
onward | +0.004 |
am | +0.003 |
Neg logit contributions | |
virtue | -0.007 |
vous | -0.007 |
rig | -0.006 |
importance | -0.006 |
Yes | -0.006 |
Token | row |
Token ID | 808 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
ged | +0.344 |
iked | +0.334 |
down | +0.334 |
onward | +0.315 |
ls | +0.300 |
Neg logit contributions | |
vous | -0.537 |
virtue | -0.534 |
rig | -0.526 |
Yes | -0.513 |
importance | -0.513 |
Token | and |
Token ID | 290 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
ged | +0.110 |
down | +0.107 |
iked | +0.107 |
onward | +0.099 |
leys | +0.095 |
Neg logit contributions | |
virtue | -0.164 |
vous | -0.163 |
rig | -0.161 |
Yes | -0.158 |
importance | -0.157 |
Token | filled |
Token ID | 5901 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
virtue | +0.135 |
vous | +0.133 |
rig | +0.132 |
importance | +0.128 |
Yes | +0.125 |
Neg logit contributions | |
down | -0.105 |
ged | -0.105 |
iked | -0.101 |
onward | -0.095 |
am | -0.091 |
Token | it |
Token ID | 340 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
down | +0.109 |
ged | +0.104 |
iked | +0.089 |
his | +0.087 |
ls | +0.082 |
Neg logit contributions | |
vous | -0.235 |
virtue | -0.233 |
rig | -0.224 |
importance | -0.224 |
matter | -0.218 |
Token | with |
Token ID | 351 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ged | +0.097 |
iked | +0.095 |
down | +0.091 |
onward | +0.089 |
leys | +0.088 |
Neg logit contributions | |
virtue | -0.091 |
rig | -0.090 |
vous | -0.089 |
Yes | -0.088 |
importance | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
iked | +0.148 |
ged | +0.146 |
down | +0.136 |
leys | +0.135 |
onward | +0.132 |
Neg logit contributions | |
virtue | -0.231 |
Yes | -0.230 |
vous | -0.229 |
rig | -0.228 |
importance | -0.223 |
Token | cat |
Token ID | 3797 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
down | +0.013 |
ged | +0.013 |
iked | +0.013 |
onward | +0.012 |
ls | +0.011 |
Neg logit contributions | |
vous | -0.017 |
virtue | -0.017 |
rig | -0.017 |
Yes | -0.017 |
importance | -0.016 |
Token | off |
Token ID | 572 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
rig | +0.318 |
vous | +0.315 |
virtue | +0.314 |
Yes | +0.309 |
importance | +0.302 |
Neg logit contributions | |
ged | -0.251 |
iked | -0.250 |
onward | -0.229 |
down | -0.228 |
leys | -0.225 |
Token | the |
Token ID | 262 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
ged | +0.135 |
down | +0.135 |
iked | +0.130 |
onward | +0.123 |
ls | +0.115 |
Neg logit contributions | |
virtue | -0.196 |
vous | -0.196 |
rig | -0.192 |
importance | -0.188 |
Yes | -0.186 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ged | +0.016 |
iked | +0.016 |
down | +0.015 |
onward | +0.015 |
leys | +0.014 |
Neg logit contributions | |
virtue | -0.015 |
vous | -0.015 |
rig | -0.015 |
importance | -0.014 |
Yes | -0.014 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
ged | +0.004 |
down | +0.004 |
iked | +0.004 |
onward | +0.004 |
leys | +0.004 |
Neg logit contributions | |
virtue | -0.005 |
vous | -0.005 |
rig | -0.005 |
importance | -0.004 |
Yes | -0.004 |
Token | row |
Token ID | 808 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ged | +0.353 |
iked | +0.344 |
down | +0.341 |
onward | +0.327 |
ls | +0.316 |
Neg logit contributions | |
vous | -0.526 |
virtue | -0.519 |
rig | -0.514 |
Yes | -0.497 |
importance | -0.494 |
Token | and |
Token ID | 290 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
ged | +0.136 |
iked | +0.134 |
down | +0.129 |
leys | +0.125 |
onward | +0.125 |
Neg logit contributions | |
virtue | -0.136 |
vous | -0.134 |
rig | -0.133 |
Yes | -0.131 |
importance | -0.130 |
Token | put |
Token ID | 1234 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
virtue | +0.135 |
vous | +0.135 |
rig | +0.132 |
importance | +0.128 |
Yes | +0.124 |
Neg logit contributions | |
down | -0.103 |
ged | -0.103 |
iked | -0.096 |
onward | -0.090 |
ls | -0.088 |
Token | him |
Token ID | 683 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
iked | +0.040 |
ged | +0.039 |
down | +0.038 |
leys | +0.036 |
onward | +0.036 |
Neg logit contributions | |
virtue | -0.054 |
vous | -0.053 |
Yes | -0.053 |
rig | -0.052 |
importance | -0.051 |
Token | back |
Token ID | 736 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
iked | +0.130 |
ged | +0.130 |
down | +0.118 |
onward | +0.117 |
ls | +0.113 |
Neg logit contributions | |
vous | -0.229 |
virtue | -0.225 |
rig | -0.222 |
Yes | -0.222 |
importance | -0.219 |
Token | dolls |
Token ID | 36062 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
down | +0.117 |
, | +0.092 |
ls | +0.089 |
ged | +0.089 |
onward | +0.081 |
Neg logit contributions | |
virtue | -0.215 |
vous | -0.211 |
leaf | -0.204 |
rig | -0.201 |
importance | -0.197 |
Token | around |
Token ID | 1088 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
virtue | +0.173 |
vous | +0.173 |
rig | +0.170 |
Yes | +0.166 |
importance | +0.166 |
Neg logit contributions | |
ged | -0.125 |
down | -0.123 |
iked | -0.121 |
onward | -0.113 |
leys | -0.108 |
Token | in |
Token ID | 287 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
down | +0.035 |
, | +0.033 |
ged | +0.031 |
his | +0.026 |
onward | +0.025 |
Neg logit contributions | |
virtue | -0.068 |
vous | -0.068 |
rig | -0.068 |
leaf | -0.065 |
deserve | -0.063 |
Token | a |
Token ID | 257 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
down | +0.027 |
ged | +0.024 |
, | +0.024 |
onward | +0.023 |
his | +0.022 |
Neg logit contributions | |
virtue | -0.045 |
rig | -0.045 |
vous | -0.043 |
leaf | -0.043 |
importance | -0.041 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
virtue | +0.130 |
vous | +0.128 |
rig | +0.127 |
importance | +0.125 |
Yes | +0.124 |
Neg logit contributions | |
down | -0.112 |
ged | -0.110 |
iked | -0.104 |
onward | -0.102 |
ls | -0.098 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
down | +0.003 |
ged | +0.003 |
, | +0.003 |
iked | +0.003 |
onward | +0.003 |
Neg logit contributions | |
virtue | -0.007 |
importance | -0.007 |
rig | -0.007 |
vous | -0.007 |
leaf | -0.007 |
Token | row |
Token ID | 808 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
ged | +0.365 |
down | +0.359 |
iked | +0.357 |
onward | +0.336 |
ls | +0.321 |
Neg logit contributions | |
vous | -0.517 |
virtue | -0.511 |
rig | -0.504 |
Yes | -0.492 |
importance | -0.491 |
Token | she |
Token ID | 673 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
down | +0.108 |
ged | +0.104 |
iked | +0.100 |
onward | +0.093 |
, | +0.090 |
Neg logit contributions | |
virtue | -0.175 |
vous | -0.174 |
rig | -0.173 |
Yes | -0.170 |
leaf | -0.169 |
Token | had |
Token ID | 550 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
ged | +0.126 |
down | +0.123 |
am | +0.114 |
, | +0.103 |
ed | +0.099 |
Neg logit contributions | |
virtue | -0.205 |
rig | -0.198 |
importance | -0.190 |
leaf | -0.189 |
resa | -0.184 |
Token | found |
Token ID | 1043 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
rig | +0.069 |
virtue | +0.068 |
vous | +0.065 |
Yes | +0.065 |
importance | +0.062 |
Neg logit contributions | |
ged | -0.063 |
down | -0.062 |
iked | -0.060 |
, | -0.057 |
onward | -0.056 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
down | +0.100 |
ged | +0.093 |
iked | +0.081 |
onward | +0.079 |
, | +0.077 |
Neg logit contributions | |
rig | -0.244 |
virtue | -0.241 |
vous | -0.239 |
Yes | -0.233 |
importance | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
Yes | +0.125 |
rig | +0.121 |
leaf | +0.120 |
vous | +0.117 |
importance | +0.116 |
Neg logit contributions | |
iked | -0.136 |
leys | -0.133 |
ged | -0.132 |
onward | -0.126 |
am | -0.125 |
Token | He |
Token ID | 679 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
ged | +0.008 |
ls | +0.007 |
leys | +0.007 |
iked | +0.007 |
down | +0.006 |
Neg logit contributions | |
importance | -0.013 |
virtue | -0.013 |
vous | -0.012 |
Yes | -0.012 |
rig | -0.012 |
Token | found |
Token ID | 1043 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
ged | +0.152 |
down | +0.148 |
iked | +0.146 |
am | +0.135 |
onward | +0.134 |
Neg logit contributions | |
virtue | -0.207 |
vous | -0.200 |
rig | -0.198 |
Yes | -0.194 |
importance | -0.191 |
Token | a |
Token ID | 257 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
ged | +0.163 |
down | +0.161 |
iked | +0.160 |
onward | +0.151 |
leys | +0.146 |
Neg logit contributions | |
virtue | -0.155 |
vous | -0.155 |
rig | -0.151 |
Yes | -0.148 |
importance | -0.148 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
vous | +0.148 |
virtue | +0.142 |
rig | +0.140 |
leaf | +0.138 |
Yes | +0.137 |
Neg logit contributions | |
down | -0.096 |
ged | -0.086 |
, | -0.085 |
onward | -0.082 |
iked | -0.082 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.003 |
down | +0.003 |
onward | +0.003 |
leys | +0.002 |
Neg logit contributions | |
vous | -0.003 |
virtue | -0.003 |
rig | -0.003 |
Yes | -0.003 |
importance | -0.003 |
Token | row |
Token ID | 808 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
ged | +0.350 |
iked | +0.347 |
down | +0.346 |
onward | +0.332 |
ls | +0.314 |
Neg logit contributions | |
vous | -0.523 |
virtue | -0.510 |
rig | -0.503 |
importance | -0.492 |
Yes | -0.489 |
Token | , |
Token ID | 11 |
Feature activation | +9.59e+00 |
Pos logit contributions | |
ged | +0.128 |
iked | +0.126 |
down | +0.121 |
onward | +0.118 |
leys | +0.117 |
Neg logit contributions | |
vous | -0.141 |
virtue | -0.140 |
rig | -0.136 |
importance | -0.135 |
Yes | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
down | +0.247 |
ged | +0.244 |
his | +0.222 |
, | +0.221 |
iked | +0.220 |
Neg logit contributions | |
virtue | -0.383 |
vous | -0.351 |
rig | -0.340 |
importance | -0.320 |
Yes | -0.317 |
Token | tr |
Token ID | 491 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
vous | +0.140 |
virtue | +0.138 |
rig | +0.136 |
Yes | +0.131 |
importance | +0.131 |
Neg logit contributions | |
down | -0.103 |
ged | -0.101 |
iked | -0.096 |
onward | -0.093 |
ls | -0.087 |
Token | amp |
Token ID | 696 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
down | +0.140 |
ged | +0.140 |
iked | +0.138 |
onward | +0.132 |
leys | +0.128 |
Neg logit contributions | |
virtue | -0.093 |
vous | -0.092 |
rig | -0.091 |
Yes | -0.087 |
importance | -0.085 |
Token | |
Token ID | 220 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
down | +0.006 |
onward | +0.005 |
ged | +0.005 |
iked | +0.005 |
am | +0.005 |
Neg logit contributions | |
vous | -0.013 |
virtue | -0.013 |
matter | -0.013 |
importance | -0.013 |
rig | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ged | +0.136 |
down | +0.133 |
iked | +0.133 |
onward | +0.124 |
leys | +0.119 |
Neg logit contributions | |
virtue | -0.158 |
vous | -0.157 |
rig | -0.155 |
Yes | -0.152 |
importance | -0.151 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
virtue | +0.038 |
vous | +0.038 |
matter | +0.037 |
importance | +0.037 |
rig | +0.036 |
Neg logit contributions | |
ged | -0.022 |
down | -0.022 |
iked | -0.021 |
onward | -0.021 |
am | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
matter | +0.030 |
virtue | +0.030 |
vous | +0.030 |
rig | +0.030 |
least | +0.029 |
Neg logit contributions | |
ged | -0.029 |
onward | -0.029 |
His | -0.028 |
iked | -0.027 |
down | -0.025 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
virtue | +0.132 |
leaf | +0.132 |
rig | +0.130 |
rather | +0.122 |
deserve | +0.121 |
Neg logit contributions | |
, | -0.089 |
ged | -0.077 |
sand | -0.075 |
iked | -0.072 |
cart | -0.067 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.48e+01 |
Pos logit contributions | |
down | +0.004 |
ged | +0.003 |
iked | +0.003 |
am | +0.003 |
, | +0.003 |
Neg logit contributions | |
virtue | -0.005 |
rig | -0.005 |
vous | -0.004 |
leaf | -0.004 |
Yes | -0.004 |
Token | row |
Token ID | 808 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
ged | +0.302 |
down | +0.292 |
iked | +0.286 |
am | +0.276 |
leys | +0.250 |
Neg logit contributions | |
virtue | -0.603 |
rig | -0.597 |
Yes | -0.587 |
leaf | -0.586 |
importance | -0.577 |
Token | wheel |
Token ID | 7825 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ged | +0.099 |
down | +0.097 |
iked | +0.096 |
onward | +0.089 |
leys | +0.084 |
Neg logit contributions | |
vous | -0.171 |
virtue | -0.171 |
rig | -0.167 |
importance | -0.165 |
Yes | -0.165 |
Token | ed |
Token ID | 276 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
ged | +0.003 |
down | +0.003 |
iked | +0.003 |
onward | +0.003 |
leys | +0.003 |
Neg logit contributions | |
virtue | -0.004 |
vous | -0.004 |
rig | -0.004 |
Yes | -0.004 |
importance | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
iked | +0.108 |
ged | +0.106 |
leys | +0.097 |
onward | +0.093 |
ls | +0.091 |
Neg logit contributions | |
virtue | -0.178 |
vous | -0.173 |
Yes | -0.173 |
importance | -0.173 |
rig | -0.171 |
Token | cup |
Token ID | 6508 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
down | +0.015 |
sand | +0.014 |
, | +0.014 |
iked | +0.013 |
castles | +0.013 |
Neg logit contributions | |
rig | -0.024 |
vous | -0.022 |
leaf | -0.022 |
virtue | -0.022 |
deserve | -0.021 |
Token | uffy |
Token ID | 15352 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
iked | +0.043 |
ged | +0.043 |
down | +0.041 |
am | +0.040 |
ls | +0.039 |
Neg logit contributions | |
vous | -0.081 |
Yes | -0.080 |
virtue | -0.080 |
leaf | -0.080 |
importance | -0.079 |
Token | had |
Token ID | 550 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
virtue | +0.071 |
Yes | +0.070 |
rig | +0.070 |
leaf | +0.070 |
vous | +0.066 |
Neg logit contributions | |
down | -0.056 |
ged | -0.055 |
, | -0.054 |
am | -0.052 |
ls | -0.052 |
Token | made |
Token ID | 925 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
rig | +0.070 |
virtue | +0.063 |
Yes | +0.063 |
vous | +0.062 |
leaf | +0.061 |
Neg logit contributions | |
down | -0.060 |
ged | -0.057 |
his | -0.057 |
, | -0.056 |
iked | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
down | +0.008 |
his | +0.007 |
, | +0.007 |
ged | +0.006 |
out | +0.006 |
Neg logit contributions | |
rig | -0.011 |
vous | -0.011 |
virtue | -0.011 |
Yes | -0.011 |
leaf | -0.011 |
Token | wheel |
Token ID | 7825 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
down | +0.012 |
sand | +0.009 |
, | +0.009 |
castles | +0.009 |
back | +0.009 |
Neg logit contributions | |
leaf | -0.018 |
rig | -0.018 |
vous | -0.017 |
Yes | -0.016 |
virtue | -0.016 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
down | +0.002 |
ged | +0.001 |
iked | +0.001 |
onward | +0.001 |
, | +0.001 |
Neg logit contributions | |
virtue | -0.002 |
vous | -0.002 |
leaf | -0.002 |
importance | -0.002 |
rig | -0.002 |
Token | row |
Token ID | 808 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
down | +0.323 |
ged | +0.321 |
iked | +0.310 |
am | +0.283 |
onward | +0.282 |
Neg logit contributions | |
virtue | -0.559 |
vous | -0.551 |
rig | -0.548 |
Yes | -0.542 |
importance | -0.540 |
Token | much |
Token ID | 881 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
down | +0.125 |
ged | +0.119 |
iked | +0.115 |
onward | +0.111 |
am | +0.106 |
Neg logit contributions | |
virtue | -0.146 |
vous | -0.146 |
rig | -0.143 |
Yes | -0.142 |
leaf | -0.141 |
Token | lighter |
Token ID | 14871 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
virtue | +0.042 |
vous | +0.042 |
rig | +0.042 |
Yes | +0.041 |
importance | +0.041 |
Neg logit contributions | |
ged | -0.045 |
iked | -0.044 |
down | -0.043 |
onward | -0.042 |
leys | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
down | +0.081 |
ged | +0.074 |
iked | +0.069 |
, | +0.069 |
onward | +0.066 |
Neg logit contributions | |
vous | -0.111 |
virtue | -0.107 |
leaf | -0.105 |
Yes | -0.105 |
rig | -0.105 |
Token | The |
Token ID | 383 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
down | +0.006 |
iked | +0.006 |
ged | +0.006 |
onward | +0.006 |
am | +0.005 |
Neg logit contributions | |
vous | -0.017 |
virtue | -0.017 |
rig | -0.016 |
importance | -0.016 |
Yes | -0.016 |
Token | much |
Token ID | 881 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
down | +0.125 |
ged | +0.119 |
iked | +0.115 |
onward | +0.111 |
am | +0.106 |
Neg logit contributions | |
virtue | -0.146 |
vous | -0.146 |
rig | -0.143 |
Yes | -0.142 |
leaf | -0.141 |
Token | lighter |
Token ID | 14871 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
virtue | +0.042 |
vous | +0.042 |
rig | +0.042 |
Yes | +0.041 |
importance | +0.041 |
Neg logit contributions | |
ged | -0.045 |
iked | -0.044 |
down | -0.043 |
onward | -0.042 |
leys | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
down | +0.081 |
ged | +0.074 |
iked | +0.069 |
, | +0.069 |
onward | +0.066 |
Neg logit contributions | |
vous | -0.111 |
virtue | -0.107 |
leaf | -0.105 |
Yes | -0.105 |
rig | -0.105 |
Token | The |
Token ID | 383 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
down | +0.006 |
iked | +0.006 |
ged | +0.006 |
onward | +0.006 |
am | +0.005 |
Neg logit contributions | |
vous | -0.017 |
virtue | -0.017 |
rig | -0.016 |
importance | -0.016 |
Yes | -0.016 |
Token | wheel |
Token ID | 7825 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
rig | +0.118 |
leaf | +0.111 |
vous | +0.107 |
virtue | +0.107 |
illa | +0.101 |
Neg logit contributions | |
down | -0.069 |
ged | -0.066 |
, | -0.063 |
castles | -0.060 |
iked | -0.059 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
down | +0.001 |
ged | +0.001 |
iked | +0.001 |
am | +0.001 |
, | +0.001 |
Neg logit contributions | |
virtue | -0.001 |
rig | -0.001 |
vous | -0.001 |
leaf | -0.001 |
Yes | -0.001 |
Token | row |
Token ID | 808 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ged | +0.311 |
down | +0.306 |
iked | +0.301 |
onward | +0.276 |
leys | +0.262 |
Neg logit contributions | |
virtue | -0.563 |
vous | -0.561 |
rig | -0.554 |
Yes | -0.544 |
importance | -0.543 |
Token | was |
Token ID | 373 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
ged | +0.123 |
down | +0.122 |
iked | +0.120 |
onward | +0.113 |
leys | +0.108 |
Neg logit contributions | |
virtue | -0.141 |
vous | -0.141 |
rig | -0.138 |
Yes | -0.135 |
importance | -0.135 |
Token | now |
Token ID | 783 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
vous | +0.084 |
rig | +0.083 |
virtue | +0.082 |
Yes | +0.081 |
leaf | +0.079 |
Neg logit contributions | |
down | -0.097 |
ged | -0.094 |
iked | -0.090 |
onward | -0.088 |
leys | -0.083 |
Token | much |
Token ID | 881 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
vous | +0.106 |
virtue | +0.104 |
rig | +0.103 |
Yes | +0.101 |
importance | +0.099 |
Neg logit contributions | |
down | -0.109 |
ged | -0.108 |
iked | -0.105 |
onward | -0.100 |
leys | -0.096 |
Token | easier |
Token ID | 4577 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
virtue | +0.048 |
vous | +0.048 |
rig | +0.047 |
Yes | +0.046 |
importance | +0.046 |
Neg logit contributions | |
ged | -0.044 |
down | -0.044 |
iked | -0.043 |
onward | -0.041 |
leys | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
ged | +0.008 |
iked | +0.008 |
leys | +0.007 |
ls | +0.007 |
onward | +0.007 |
Neg logit contributions | |
Yes | -0.006 |
rig | -0.006 |
vous | -0.006 |
virtue | -0.006 |
importance | -0.006 |
Token | soil |
Token ID | 9260 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
virtue | +0.179 |
vous | +0.178 |
rig | +0.175 |
Yes | +0.173 |
importance | +0.173 |
Neg logit contributions | |
ged | -0.141 |
iked | -0.139 |
down | -0.137 |
onward | -0.130 |
leys | -0.124 |
Token | into |
Token ID | 656 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ged | +0.106 |
iked | +0.104 |
leys | +0.100 |
onward | +0.097 |
am | +0.088 |
Neg logit contributions | |
rig | -0.115 |
virtue | -0.112 |
Yes | -0.111 |
importance | -0.108 |
bit | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
down | +0.076 |
ged | +0.075 |
iked | +0.068 |
onward | +0.065 |
, | +0.063 |
Neg logit contributions | |
vous | -0.122 |
virtue | -0.120 |
rig | -0.119 |
leaf | -0.113 |
Yes | -0.112 |
Token | wheel |
Token ID | 7825 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
ged | +0.008 |
iked | +0.008 |
down | +0.008 |
onward | +0.007 |
leys | +0.007 |
Neg logit contributions | |
virtue | -0.011 |
vous | -0.010 |
importance | -0.010 |
rig | -0.010 |
Yes | -0.010 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
ged | +0.001 |
iked | +0.001 |
down | +0.001 |
onward | +0.001 |
ls | +0.001 |
Neg logit contributions | |
vous | -0.002 |
rig | -0.002 |
virtue | -0.002 |
Yes | -0.002 |
importance | -0.002 |
Token | row |
Token ID | 808 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
ged | +0.391 |
onward | +0.376 |
iked | +0.375 |
down | +0.369 |
ls | +0.355 |
Neg logit contributions | |
vous | -0.446 |
rig | -0.444 |
virtue | -0.442 |
importance | -0.420 |
least | -0.412 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ged | +0.115 |
iked | +0.111 |
onward | +0.105 |
down | +0.105 |
leys | +0.105 |
Neg logit contributions | |
virtue | -0.139 |
rig | -0.136 |
vous | -0.133 |
importance | -0.133 |
Yes | -0.132 |
Token | It |
Token ID | 632 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
ged | +0.006 |
down | +0.006 |
iked | +0.006 |
onward | +0.006 |
ls | +0.005 |
Neg logit contributions | |
virtue | -0.010 |
vous | -0.010 |
rig | -0.010 |
Yes | -0.009 |
importance | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
virtue | +0.029 |
vous | +0.028 |
rig | +0.027 |
leaf | +0.027 |
Yes | +0.027 |
Neg logit contributions | |
down | -0.029 |
ged | -0.028 |
iked | -0.027 |
am | -0.026 |
ls | -0.026 |
Token | heavy |
Token ID | 4334 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
vous | +0.081 |
virtue | +0.080 |
rig | +0.078 |
Yes | +0.077 |
importance | +0.075 |
Neg logit contributions | |
down | -0.105 |
ged | -0.104 |
iked | -0.101 |
onward | -0.098 |
am | -0.093 |
Token | filled |
Token ID | 5901 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
down | +0.139 |
ged | +0.137 |
iked | +0.129 |
am | +0.128 |
ls | +0.121 |
Neg logit contributions | |
virtue | -0.204 |
vous | -0.196 |
rig | -0.193 |
importance | -0.188 |
Yes | -0.188 |
Token | up |
Token ID | 510 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
down | +0.106 |
ged | +0.094 |
his | +0.089 |
iked | +0.087 |
am | +0.080 |
Neg logit contributions | |
virtue | -0.222 |
vous | -0.217 |
rig | -0.209 |
importance | -0.205 |
matter | -0.201 |
Token | lots |
Token ID | 6041 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
down | +0.144 |
his | +0.123 |
ged | +0.120 |
iked | +0.114 |
, | +0.111 |
Neg logit contributions | |
virtue | -0.352 |
rig | -0.346 |
vous | -0.342 |
importance | -0.323 |
matter | -0.320 |
Token | of |
Token ID | 286 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
virtue | +0.181 |
vous | +0.179 |
rig | +0.174 |
importance | +0.171 |
Yes | +0.168 |
Neg logit contributions | |
down | -0.253 |
ged | -0.253 |
iked | -0.248 |
onward | -0.237 |
ls | -0.232 |
Token | wheel |
Token ID | 7825 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
virtue | +0.206 |
rig | +0.200 |
vous | +0.187 |
illa | +0.186 |
resa | +0.184 |
Neg logit contributions | |
down | -0.140 |
his | -0.121 |
ged | -0.120 |
, | -0.117 |
castles | -0.117 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
rig | +0.002 |
vous | +0.002 |
virtue | +0.002 |
Yes | +0.002 |
importance | +0.002 |
Neg logit contributions | |
ged | -0.002 |
iked | -0.002 |
down | -0.002 |
onward | -0.002 |
leys | -0.002 |
Token | rows |
Token ID | 8516 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
ged | +0.351 |
iked | +0.346 |
onward | +0.340 |
down | +0.330 |
ls | +0.310 |
Neg logit contributions | |
vous | -0.492 |
virtue | -0.471 |
rig | -0.468 |
importance | -0.456 |
Yes | -0.448 |
Token | with |
Token ID | 351 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
virtue | +0.087 |
vous | +0.087 |
rig | +0.085 |
Yes | +0.084 |
importance | +0.083 |
Neg logit contributions | |
ged | -0.085 |
iked | -0.083 |
down | -0.083 |
onward | -0.078 |
leys | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
virtue | +0.061 |
vous | +0.060 |
rig | +0.060 |
importance | +0.057 |
Yes | +0.057 |
Neg logit contributions | |
down | -0.043 |
ged | -0.043 |
iked | -0.041 |
onward | -0.038 |
am | -0.037 |
Token | waste |
Token ID | 7030 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
down | +0.007 |
, | +0.006 |
ged | +0.006 |
castles | +0.006 |
sand | +0.006 |
Neg logit contributions | |
rig | -0.011 |
virtue | -0.010 |
leaf | -0.010 |
vous | -0.009 |
Yes | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
ged | +0.011 |
down | +0.011 |
iked | +0.010 |
onward | +0.010 |
ls | +0.009 |
Neg logit contributions | |
virtue | -0.014 |
vous | -0.014 |
rig | -0.014 |
Yes | -0.013 |
importance | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
iked | +0.114 |
ged | +0.113 |
down | +0.106 |
leys | +0.102 |
onward | +0.102 |
Neg logit contributions | |
virtue | -0.166 |
vous | -0.165 |
Yes | -0.164 |
rig | -0.160 |
importance | -0.160 |
Token | away |
Token ID | 1497 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
ged | +0.075 |
iked | +0.072 |
onward | +0.065 |
ls | +0.063 |
leys | +0.063 |
Neg logit contributions | |
virtue | -0.103 |
rig | -0.099 |
vous | -0.098 |
Yes | -0.098 |
importance | -0.096 |
Token | in |
Token ID | 287 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
ged | +0.135 |
iked | +0.131 |
down | +0.131 |
onward | +0.120 |
leys | +0.115 |
Neg logit contributions | |
virtue | -0.218 |
vous | -0.217 |
rig | -0.213 |
Yes | -0.210 |
importance | -0.210 |
Token | a |
Token ID | 257 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
down | +0.019 |
ged | +0.017 |
his | +0.016 |
, | +0.016 |
onward | +0.016 |
Neg logit contributions | |
rig | -0.038 |
vous | -0.037 |
leaf | -0.036 |
virtue | -0.036 |
Yes | -0.035 |
Token | wheel |
Token ID | 7825 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
vous | +0.131 |
virtue | +0.131 |
rig | +0.129 |
Yes | +0.126 |
importance | +0.126 |
Neg logit contributions | |
down | -0.117 |
ged | -0.117 |
iked | -0.113 |
onward | -0.109 |
leys | -0.104 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
virtue | +0.004 |
vous | +0.004 |
rig | +0.004 |
importance | +0.004 |
Yes | +0.004 |
Neg logit contributions | |
down | -0.002 |
ged | -0.002 |
iked | -0.002 |
onward | -0.002 |
am | -0.002 |
Token | row |
Token ID | 808 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
ged | +0.349 |
iked | +0.340 |
down | +0.338 |
onward | +0.326 |
ls | +0.311 |
Neg logit contributions | |
vous | -0.508 |
virtue | -0.503 |
rig | -0.491 |
importance | -0.479 |
Yes | -0.472 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
down | +0.089 |
ged | +0.089 |
iked | +0.086 |
onward | +0.079 |
leys | +0.075 |
Neg logit contributions | |
vous | -0.168 |
virtue | -0.167 |
rig | -0.166 |
Yes | -0.163 |
importance | -0.162 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.003 |
down | +0.003 |
ls | +0.003 |
onward | +0.003 |
Neg logit contributions | |
Yes | -0.006 |
vous | -0.005 |
virtue | -0.005 |
importance | -0.005 |
rig | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
virtue | +0.039 |
vous | +0.038 |
rig | +0.037 |
importance | +0.037 |
Yes | +0.037 |
Neg logit contributions | |
ged | -0.028 |
down | -0.027 |
iked | -0.027 |
onward | -0.025 |
leys | -0.024 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
rig | +0.033 |
virtue | +0.033 |
least | +0.032 |
leaf | +0.032 |
vous | +0.032 |
Neg logit contributions | |
iked | -0.031 |
ged | -0.030 |
onward | -0.030 |
down | -0.029 |
leys | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
virtue | +0.103 |
vous | +0.098 |
rig | +0.098 |
Yes | +0.098 |
importance | +0.096 |
Neg logit contributions | |
ged | -0.062 |
down | -0.061 |
iked | -0.058 |
am | -0.058 |
, | -0.055 |
Token | wheel |
Token ID | 7825 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
vous | +0.088 |
virtue | +0.088 |
rig | +0.084 |
importance | +0.082 |
Yes | +0.081 |
Neg logit contributions | |
iked | -0.097 |
ged | -0.096 |
down | -0.091 |
ls | -0.089 |
leys | -0.088 |
Token | ing |
Token ID | 278 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
vous | +0.004 |
virtue | +0.004 |
rig | +0.004 |
Yes | +0.003 |
importance | +0.003 |
Neg logit contributions | |
ged | -0.002 |
iked | -0.002 |
down | -0.002 |
onward | -0.002 |
leys | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
iked | +0.130 |
ged | +0.129 |
down | +0.123 |
onward | +0.117 |
leys | +0.117 |
Neg logit contributions | |
virtue | -0.192 |
vous | -0.191 |
rig | -0.189 |
Yes | -0.186 |
importance | -0.186 |
Token | wheel |
Token ID | 7825 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
down | +0.011 |
ged | +0.009 |
iked | +0.009 |
ashore | +0.009 |
onward | +0.009 |
Neg logit contributions | |
rig | -0.015 |
vous | -0.014 |
leaf | -0.014 |
virtue | -0.013 |
Yes | -0.013 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
virtue | +0.004 |
vous | +0.004 |
rig | +0.004 |
Yes | +0.004 |
importance | +0.004 |
Neg logit contributions | |
ged | -0.003 |
down | -0.003 |
iked | -0.003 |
onward | -0.003 |
leys | -0.002 |
Token | row |
Token ID | 808 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
ged | +0.322 |
iked | +0.317 |
down | +0.314 |
onward | +0.297 |
ls | +0.286 |
Neg logit contributions | |
vous | -0.525 |
virtue | -0.518 |
rig | -0.509 |
importance | -0.498 |
Yes | -0.496 |
Token | around |
Token ID | 1088 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ged | +0.095 |
iked | +0.093 |
down | +0.091 |
onward | +0.085 |
leys | +0.083 |
Neg logit contributions | |
virtue | -0.152 |
vous | -0.151 |
rig | -0.148 |
importance | -0.146 |
Yes | -0.146 |
Token | she |
Token ID | 673 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
down | +0.025 |
ged | +0.024 |
iked | +0.022 |
onward | +0.021 |
, | +0.020 |
Neg logit contributions | |
vous | -0.052 |
rig | -0.052 |
virtue | -0.052 |
leaf | -0.050 |
importance | -0.049 |
Token | made |
Token ID | 925 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ged | +0.121 |
down | +0.115 |
am | +0.113 |
iked | +0.103 |
onward | +0.100 |
Neg logit contributions | |
virtue | -0.197 |
rig | -0.187 |
leaf | -0.184 |
importance | -0.178 |
Yes | -0.177 |
Token | sure |
Token ID | 1654 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
down | +0.004 |
ged | +0.003 |
iked | +0.003 |
onward | +0.003 |
, | +0.003 |
Neg logit contributions | |
virtue | -0.006 |
vous | -0.006 |
rig | -0.006 |
Yes | -0.006 |
importance | -0.006 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
virtue | +0.152 |
vous | +0.150 |
rig | +0.147 |
Yes | +0.138 |
importance | +0.134 |
Neg logit contributions | |
down | -0.184 |
ged | -0.181 |
iked | -0.178 |
onward | -0.171 |
, | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
vous | +0.004 |
virtue | +0.004 |
rig | +0.004 |
importance | +0.004 |
Yes | +0.004 |
Neg logit contributions | |
ged | -0.003 |
iked | -0.003 |
down | -0.003 |
onward | -0.003 |
leys | -0.003 |
Token | Soon |
Token ID | 15894 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
down | +0.004 |
ged | +0.004 |
iked | +0.004 |
onward | +0.004 |
leys | +0.004 |
Neg logit contributions | |
virtue | -0.007 |
vous | -0.007 |
rig | -0.007 |
importance | -0.007 |
Yes | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ged | +0.043 |
down | +0.041 |
iked | +0.041 |
leys | +0.040 |
ashore | +0.037 |
Neg logit contributions | |
Yes | -0.071 |
virtue | -0.070 |
importance | -0.069 |
matter | -0.069 |
vous | -0.068 |
Token | wheel |
Token ID | 7825 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
down | +0.005 |
ged | +0.005 |
iked | +0.005 |
onward | +0.005 |
, | +0.004 |
Neg logit contributions | |
virtue | -0.009 |
rig | -0.009 |
vous | -0.008 |
leaf | -0.008 |
Yes | -0.008 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
virtue | +0.006 |
vous | +0.006 |
rig | +0.006 |
Yes | +0.006 |
importance | +0.006 |
Neg logit contributions | |
down | -0.006 |
ged | -0.006 |
iked | -0.006 |
onward | -0.006 |
am | -0.005 |
Token | row |
Token ID | 808 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
ged | +0.342 |
down | +0.338 |
iked | +0.334 |
onward | +0.313 |
ls | +0.298 |
Neg logit contributions | |
vous | -0.499 |
virtue | -0.496 |
rig | -0.487 |
Yes | -0.479 |
importance | -0.479 |
Token | was |
Token ID | 373 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ged | +0.110 |
iked | +0.108 |
down | +0.107 |
leys | +0.101 |
onward | +0.101 |
Neg logit contributions | |
vous | -0.118 |
virtue | -0.118 |
rig | -0.114 |
importance | -0.114 |
Yes | -0.114 |
Token | empty |
Token ID | 6565 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
virtue | +0.089 |
vous | +0.087 |
importance | +0.086 |
rig | +0.084 |
matter | +0.084 |
Neg logit contributions | |
ged | -0.109 |
iked | -0.108 |
ls | -0.102 |
down | -0.101 |
leys | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ged | +0.069 |
iked | +0.068 |
leys | +0.063 |
down | +0.062 |
onward | +0.062 |
Neg logit contributions | |
virtue | -0.083 |
importance | -0.081 |
vous | -0.080 |
Yes | -0.080 |
rig | -0.079 |
Token | all |
Token ID | 477 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
vous | +0.148 |
virtue | +0.148 |
rig | +0.145 |
importance | +0.141 |
Yes | +0.139 |
Neg logit contributions | |
down | -0.112 |
ged | -0.108 |
iked | -0.105 |
onward | -0.101 |
ls | -0.094 |
Token | light |
Token ID | 1657 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
virtue | +0.074 |
vous | +0.073 |
rig | +0.070 |
importance | +0.069 |
leaf | +0.067 |
Neg logit contributions | |
down | -0.070 |
ged | -0.067 |
iked | -0.063 |
onward | -0.061 |
, | -0.060 |
Token | en |
Token ID | 268 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
virtue | +0.013 |
vous | +0.013 |
rig | +0.013 |
Yes | +0.013 |
importance | +0.013 |
Neg logit contributions | |
ged | -0.008 |
iked | -0.008 |
down | -0.008 |
onward | -0.007 |
leys | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | +7.35e+00 |
Pos logit contributions | |
ged | +0.111 |
iked | +0.111 |
down | +0.107 |
onward | +0.101 |
leys | +0.099 |
Neg logit contributions | |
virtue | -0.167 |
vous | -0.166 |
rig | -0.166 |
Yes | -0.162 |
importance | -0.162 |
Token | the |
Token ID | 262 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
down | +0.171 |
ged | +0.164 |
iked | +0.156 |
onward | +0.151 |
ls | +0.140 |
Neg logit contributions | |
vous | -0.279 |
virtue | -0.276 |
rig | -0.271 |
Yes | -0.265 |
importance | -0.264 |
Token | wheel |
Token ID | 7825 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
down | +0.004 |
ged | +0.004 |
iked | +0.004 |
onward | +0.004 |
am | +0.003 |
Neg logit contributions | |
vous | -0.006 |
rig | -0.005 |
virtue | -0.005 |
Yes | -0.005 |
leaf | -0.005 |
Token | bar |
Token ID | 5657 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
virtue | +0.012 |
vous | +0.012 |
rig | +0.012 |
importance | +0.011 |
Yes | +0.011 |
Neg logit contributions | |
ged | -0.007 |
down | -0.007 |
iked | -0.007 |
onward | -0.006 |
leys | -0.006 |
Token | row |
Token ID | 808 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
ged | +0.363 |
iked | +0.352 |
down | +0.344 |
onward | +0.340 |
ls | +0.336 |
Neg logit contributions | |
vous | -0.459 |
virtue | -0.454 |
rig | -0.449 |
importance | -0.431 |
least | -0.423 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
ged | +0.094 |
iked | +0.092 |
down | +0.091 |
onward | +0.085 |
leys | +0.082 |
Neg logit contributions | |
virtue | -0.138 |
vous | -0.137 |
rig | -0.135 |
Yes | -0.132 |
importance | -0.132 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
vous | +0.001 |
virtue | +0.001 |
rig | +0.001 |
importance | +0.001 |
matter | +0.001 |
Neg logit contributions | |
down | -0.001 |
ged | -0.001 |
iked | -0.001 |
onward | -0.001 |
am | -0.000 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
vous | +0.054 |
Yes | +0.053 |
importance | +0.052 |
rig | +0.052 |
virtue | +0.052 |
Neg logit contributions | |
iked | -0.038 |
ged | -0.038 |
down | -0.035 |
leys | -0.034 |
am | -0.033 |
Token | there |
Token ID | 612 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
ged | +0.097 |
iked | +0.094 |
down | +0.088 |
onward | +0.087 |
ashore | +0.086 |
Neg logit contributions | |
rig | -0.078 |
Yes | -0.074 |
importance | -0.073 |
vous | -0.073 |
virtue | -0.071 |
Token | whistle |
Token ID | 16121 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
vous | +0.078 |
virtue | +0.076 |
rig | +0.076 |
Yes | +0.074 |
importance | +0.073 |
Neg logit contributions | |
ged | -0.131 |
iked | -0.131 |
down | -0.128 |
onward | -0.124 |
leys | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
down | +0.036 |
ged | +0.034 |
iked | +0.032 |
onward | +0.031 |
, | +0.029 |
Neg logit contributions | |
virtue | -0.060 |
vous | -0.058 |
rig | -0.057 |
importance | -0.057 |
Yes | -0.056 |
Token | The |
Token ID | 383 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
down | +0.016 |
ged | +0.016 |
iked | +0.016 |
onward | +0.015 |
am | +0.014 |
Neg logit contributions | |
vous | -0.027 |
virtue | -0.027 |
rig | -0.026 |
importance | -0.026 |
Yes | -0.026 |
Token | train |
Token ID | 4512 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
virtue | +0.099 |
rig | +0.094 |
illa | +0.089 |
vous | +0.085 |
grand | +0.082 |
Neg logit contributions | |
down | -0.071 |
, | -0.067 |
ged | -0.062 |
he | -0.061 |
his | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
ged | +0.020 |
down | +0.020 |
iked | +0.019 |
onward | +0.018 |
am | +0.017 |
Neg logit contributions | |
virtue | -0.030 |
vous | -0.029 |
rig | -0.029 |
Yes | -0.028 |
leaf | -0.027 |
Token | arriving |
Token ID | 14820 |
Feature activation | +1.39e+01 |
Pos logit contributions | |
virtue | +0.089 |
vous | +0.086 |
rig | +0.084 |
Yes | +0.083 |
importance | +0.082 |
Neg logit contributions | |
down | -0.087 |
ged | -0.084 |
iked | -0.078 |
onward | -0.078 |
ashore | -0.075 |
Token | ! |
Token ID | 0 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
ged | +0.379 |
down | +0.372 |
iked | +0.370 |
onward | +0.347 |
leys | +0.333 |
Neg logit contributions | |
virtue | -0.450 |
vous | -0.448 |
rig | -0.441 |
Yes | -0.433 |
importance | -0.431 |
Token | Exc |
Token ID | 25268 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
vous | +0.034 |
virtue | +0.034 |
rig | +0.033 |
matter | +0.033 |
importance | +0.033 |
Neg logit contributions | |
down | -0.023 |
ged | -0.022 |
iked | -0.022 |
onward | -0.021 |
ls | -0.019 |
Token | ited |
Token ID | 863 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
importance | +0.029 |
virtue | +0.028 |
vous | +0.028 |
song | +0.026 |
meaning | +0.026 |
Neg logit contributions | |
ged | -0.041 |
ls | -0.039 |
iked | -0.038 |
down | -0.038 |
onward | -0.037 |
Token | ly |
Token ID | 306 |
Feature activation | +5.76e+00 |
Pos logit contributions | |
ged | +0.010 |
iked | +0.010 |
onward | +0.009 |
leys | +0.009 |
down | +0.009 |
Neg logit contributions | |
matter | -0.020 |
Yes | -0.020 |
vous | -0.020 |
years | -0.020 |
importance | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +9.73e+00 |
Pos logit contributions | |
leys | +0.087 |
iked | +0.086 |
down | +0.080 |
ged | +0.079 |
onward | +0.074 |
Neg logit contributions | |
Yes | -0.238 |
virtue | -0.236 |
vous | -0.234 |
rig | -0.232 |
child | -0.231 |
Token | he |
Token ID | 339 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
Yes | +0.012 |
matter | +0.011 |
least | +0.010 |
bit | +0.010 |
child | +0.010 |
Neg logit contributions | |
leys | -0.010 |
ged | -0.010 |
iked | -0.010 |
ashore | -0.009 |
rolling | -0.008 |
Token | passed |
Token ID | 3804 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
ged | +0.183 |
down | +0.180 |
iked | +0.172 |
am | +0.167 |
ls | +0.166 |
Neg logit contributions | |
virtue | -0.243 |
vous | -0.235 |
rig | -0.221 |
importance | -0.218 |
matter | -0.211 |
Token | it |
Token ID | 340 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
down | +0.111 |
ged | +0.104 |
iked | +0.094 |
onward | +0.092 |
ls | +0.087 |
Neg logit contributions | |
virtue | -0.202 |
rig | -0.201 |
vous | -0.199 |
importance | -0.193 |
Yes | -0.184 |
Token | to |
Token ID | 284 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ged | +0.077 |
down | +0.076 |
iked | +0.075 |
onward | +0.071 |
leys | +0.068 |
Neg logit contributions | |
virtue | -0.093 |
vous | -0.093 |
rig | -0.091 |
Yes | -0.090 |
importance | -0.089 |
Token | another |
Token ID | 1194 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
rig | +0.106 |
virtue | +0.106 |
vous | +0.104 |
importance | +0.098 |
leaf | +0.096 |
Neg logit contributions | |
down | -0.043 |
ged | -0.039 |
his | -0.036 |
, | -0.033 |
them | -0.032 |
Token | child |
Token ID | 1200 |
Feature activation | -1.32e+01 |
Pos logit contributions | |
virtue | +0.092 |
leaf | +0.088 |
vous | +0.087 |
rig | +0.086 |
Tooth | +0.081 |
Neg logit contributions | |
, | -0.068 |
down | -0.065 |
his | -0.051 |
ged | -0.050 |
onward | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +9.14e+00 |
Pos logit contributions | |
virtue | +0.541 |
vous | +0.531 |
rig | +0.522 |
importance | +0.520 |
Yes | +0.508 |
Neg logit contributions | |
down | -0.267 |
ged | -0.259 |
iked | -0.247 |
onward | -0.228 |
, | -0.222 |
Token | who |
Token ID | 508 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
down | +0.298 |
ged | +0.270 |
, | +0.258 |
his | +0.242 |
onward | +0.237 |
Neg logit contributions | |
vous | -0.312 |
virtue | -0.309 |
importance | -0.286 |
rig | -0.283 |
matter | -0.271 |
Token | also |
Token ID | 635 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
virtue | +0.278 |
rig | +0.265 |
vous | +0.254 |
importance | +0.248 |
resa | +0.227 |
Neg logit contributions | |
ged | -0.178 |
down | -0.174 |
, | -0.170 |
ls | -0.168 |
his | -0.164 |
Token | looked |
Token ID | 3114 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
virtue | +0.127 |
rig | +0.122 |
vous | +0.120 |
importance | +0.115 |
Yes | +0.114 |
Neg logit contributions | |
ged | -0.117 |
down | -0.111 |
iked | -0.104 |
, | -0.103 |
am | -0.101 |
Token | at |
Token ID | 379 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
down | +0.120 |
ged | +0.112 |
iked | +0.102 |
onward | +0.096 |
ls | +0.091 |
Neg logit contributions | |
virtue | -0.305 |
vous | -0.304 |
rig | -0.296 |
importance | -0.294 |
Yes | -0.291 |
Token | was |
Token ID | 373 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ged | +0.149 |
down | +0.147 |
iked | +0.146 |
onward | +0.139 |
leys | +0.135 |
Neg logit contributions | |
vous | -0.100 |
virtue | -0.099 |
rig | -0.096 |
Yes | -0.095 |
importance | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
virtue | +0.107 |
rig | +0.102 |
vous | +0.100 |
importance | +0.098 |
Yes | +0.095 |
Neg logit contributions | |
down | -0.100 |
ged | -0.099 |
iked | -0.094 |
onward | -0.090 |
, | -0.087 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.07e+00 |
Pos logit contributions | |
virtue | +0.126 |
vous | +0.124 |
rig | +0.121 |
importance | +0.118 |
leaf | +0.117 |
Neg logit contributions | |
down | -0.146 |
ged | -0.141 |
iked | -0.133 |
, | -0.132 |
ls | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
virtue | +0.260 |
rig | +0.246 |
importance | +0.238 |
vous | +0.236 |
leaf | +0.227 |
Neg logit contributions | |
down | -0.252 |
ged | -0.238 |
, | -0.228 |
iked | -0.225 |
am | -0.213 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
vous | +0.124 |
Yes | +0.123 |
virtue | +0.120 |
importance | +0.117 |
leaf | +0.115 |
Neg logit contributions | |
iked | -0.136 |
ged | -0.135 |
down | -0.132 |
onward | -0.129 |
leys | -0.126 |
Token | child |
Token ID | 1200 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
virtue | +0.144 |
rig | +0.143 |
vous | +0.142 |
importance | +0.132 |
leaf | +0.130 |
Neg logit contributions | |
down | -0.138 |
, | -0.127 |
ged | -0.125 |
iked | -0.112 |
onward | -0.112 |
Token | who |
Token ID | 508 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
virtue | +0.468 |
rig | +0.458 |
importance | +0.448 |
vous | +0.446 |
matter | +0.424 |
Neg logit contributions | |
down | -0.345 |
ged | -0.345 |
iked | -0.325 |
, | -0.310 |
am | -0.293 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
rig | +0.237 |
virtue | +0.235 |
vous | +0.218 |
leaf | +0.214 |
importance | +0.210 |
Neg logit contributions | |
down | -0.194 |
ged | -0.190 |
, | -0.176 |
iked | -0.174 |
his | -0.167 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
virtue | +0.195 |
rig | +0.195 |
vous | +0.192 |
ight | +0.175 |
deserve | +0.174 |
Neg logit contributions | |
down | -0.073 |
iked | -0.059 |
his | -0.058 |
, | -0.054 |
ged | -0.053 |
Token | go |
Token ID | 467 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
virtue | +0.079 |
rig | +0.076 |
vous | +0.074 |
importance | +0.072 |
leaf | +0.070 |
Neg logit contributions | |
down | -0.065 |
iked | -0.061 |
, | -0.060 |
ged | -0.060 |
am | -0.057 |
Token | for |
Token ID | 329 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
ged | +0.162 |
bled | +0.149 |
leys | +0.149 |
iked | +0.147 |
iece | +0.147 |
Neg logit contributions | |
leaf | -0.099 |
elderly | -0.099 |
Yes | -0.098 |
lecture | -0.093 |
rig | -0.092 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
virtue | +0.001 |
vous | +0.001 |
rig | +0.001 |
importance | +0.001 |
Yes | +0.001 |
Neg logit contributions | |
ged | -0.001 |
down | -0.001 |
iked | -0.001 |
onward | -0.001 |
leys | -0.000 |
Token | L |
Token ID | 43 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
Yes | +0.054 |
vous | +0.053 |
importance | +0.052 |
rig | +0.051 |
leaf | +0.050 |
Neg logit contributions | |
ged | -0.039 |
iked | -0.038 |
leys | -0.034 |
down | -0.034 |
onward | -0.032 |
Token | ily |
Token ID | 813 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
vous | +0.124 |
rig | +0.115 |
Yes | +0.113 |
virtue | +0.111 |
leaf | +0.111 |
Neg logit contributions | |
ged | -0.170 |
down | -0.170 |
iked | -0.162 |
onward | -0.161 |
ashore | -0.149 |
Token | was |
Token ID | 373 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
virtue | +0.067 |
vous | +0.067 |
rig | +0.065 |
Yes | +0.064 |
importance | +0.063 |
Neg logit contributions | |
ged | -0.070 |
down | -0.069 |
iked | -0.068 |
onward | -0.064 |
am | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
virtue | +0.126 |
vous | +0.123 |
importance | +0.120 |
rig | +0.120 |
Yes | +0.118 |
Neg logit contributions | |
down | -0.091 |
ged | -0.085 |
iked | -0.081 |
onward | -0.079 |
am | -0.075 |
Token | child |
Token ID | 1200 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
virtue | +0.139 |
rig | +0.134 |
vous | +0.134 |
importance | +0.130 |
leaf | +0.128 |
Neg logit contributions | |
down | -0.148 |
, | -0.135 |
ged | -0.134 |
onward | -0.127 |
iked | -0.127 |
Token | who |
Token ID | 508 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
virtue | +0.603 |
vous | +0.597 |
importance | +0.595 |
rig | +0.591 |
leaf | +0.557 |
Neg logit contributions | |
, | -0.239 |
down | -0.225 |
ged | -0.197 |
iked | -0.170 |
onward | -0.170 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
virtue | +0.203 |
rig | +0.196 |
vous | +0.189 |
importance | +0.184 |
Yes | +0.181 |
Neg logit contributions | |
down | -0.230 |
ged | -0.225 |
iked | -0.217 |
onward | -0.210 |
, | -0.208 |
Token | to |
Token ID | 284 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
virtue | +0.163 |
vous | +0.162 |
rig | +0.160 |
importance | +0.146 |
deserve | +0.144 |
Neg logit contributions | |
down | -0.084 |
iked | -0.075 |
ged | -0.070 |
his | -0.069 |
, | -0.063 |
Token | whistle |
Token ID | 16121 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
virtue | +0.086 |
vous | +0.083 |
rig | +0.082 |
importance | +0.080 |
Yes | +0.076 |
Neg logit contributions | |
down | -0.069 |
ged | -0.066 |
iked | -0.065 |
onward | -0.061 |
, | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
down | +0.021 |
ged | +0.020 |
iked | +0.019 |
onward | +0.018 |
ls | +0.017 |
Neg logit contributions | |
vous | -0.040 |
virtue | -0.040 |
rig | -0.039 |
Yes | -0.038 |
importance | -0.038 |
Token | You |
Token ID | 921 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
down | +0.000 |
onward | +0.000 |
iked | +0.000 |
, | +0.000 |
He | +0.000 |
Neg logit contributions | |
vous | -0.000 |
rig | -0.000 |
virtue | -0.000 |
matter | -0.000 |
importance | -0.000 |
Token | 're |
Token ID | 821 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
rig | +0.239 |
virtue | +0.231 |
vous | +0.224 |
leaf | +0.213 |
resa | +0.213 |
Neg logit contributions | |
, | -0.150 |
down | -0.141 |
out | -0.119 |
onward | -0.114 |
ashore | -0.113 |
Token | a |
Token ID | 257 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
rig | +0.063 |
vous | +0.059 |
virtue | +0.058 |
Yes | +0.057 |
leaf | +0.054 |
Neg logit contributions | |
down | -0.054 |
, | -0.048 |
his | -0.047 |
onward | -0.045 |
out | -0.044 |
Token | very |
Token ID | 845 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
rig | +0.168 |
ampoo | +0.160 |
leaf | +0.160 |
vous | +0.156 |
outage | +0.150 |
Neg logit contributions | |
, | -0.106 |
down | -0.092 |
back | -0.085 |
, | -0.078 |
his | -0.076 |
Token | smart |
Token ID | 4451 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
rig | +0.152 |
virtue | +0.151 |
importance | +0.147 |
vous | +0.146 |
Yes | +0.145 |
Neg logit contributions | |
down | -0.156 |
onward | -0.143 |
iked | -0.143 |
, | -0.142 |
ged | -0.142 |
Token | child |
Token ID | 1200 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
rig | +0.172 |
leaf | +0.161 |
vous | +0.158 |
Yes | +0.156 |
virtue | +0.155 |
Neg logit contributions | |
, | -0.174 |
down | -0.149 |
ged | -0.140 |
his | -0.130 |
out | -0.128 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
rig | +0.519 |
virtue | +0.487 |
importance | +0.480 |
vous | +0.477 |
leaf | +0.465 |
Neg logit contributions | |
, | -0.330 |
down | -0.326 |
onward | -0.257 |
ged | -0.253 |
his | -0.234 |
Token | |
Token ID | 220 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
vous | +0.181 |
virtue | +0.181 |
matter | +0.174 |
importance | +0.173 |
rig | +0.170 |
Neg logit contributions | |
down | -0.093 |
ged | -0.087 |
onward | -0.082 |
iked | -0.081 |
, | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ged | +0.127 |
iked | +0.123 |
down | +0.122 |
onward | +0.115 |
leys | +0.111 |
Neg logit contributions | |
rig | -0.130 |
virtue | -0.130 |
vous | -0.128 |
Yes | -0.125 |
importance | -0.124 |
Token | The |
Token ID | 464 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
matter | +0.058 |
vous | +0.058 |
virtue | +0.058 |
importance | +0.055 |
rig | +0.054 |
Neg logit contributions | |
ged | -0.028 |
down | -0.028 |
onward | -0.026 |
iked | -0.026 |
am | -0.024 |
Token | j |
Token ID | 474 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
virtue | +0.120 |
rig | +0.119 |
deserve | +0.113 |
leaf | +0.111 |
vous | +0.105 |
Neg logit contributions | |
, | -0.145 |
ged | -0.139 |
down | -0.131 |
ls | -0.129 |
sand | -0.121 |
Token | ? |
Token ID | 30 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
rig | +0.176 |
vous | +0.168 |
virtue | +0.167 |
importance | +0.161 |
leaf | +0.153 |
Neg logit contributions | |
, | -0.107 |
down | -0.101 |
his | -0.092 |
he | -0.084 |
ged | -0.083 |
Token | â |
Token ID | 22940 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
virtue | +0.069 |
vous | +0.068 |
rig | +0.067 |
importance | +0.067 |
matter | +0.065 |
Neg logit contributions | |
down | -0.044 |
ged | -0.042 |
iked | -0.041 |
onward | -0.040 |
am | -0.036 |
Token | € |
Token ID | 26391 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
ged | +0.024 |
down | +0.024 |
iked | +0.024 |
onward | +0.023 |
leys | +0.022 |
Neg logit contributions | |
virtue | -0.018 |
vous | -0.018 |
rig | -0.018 |
importance | -0.018 |
Yes | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ged | +0.094 |
down | +0.093 |
iked | +0.092 |
onward | +0.086 |
leys | +0.083 |
Neg logit contributions | |
virtue | -0.104 |
vous | -0.104 |
rig | -0.102 |
Yes | -0.100 |
importance | -0.100 |
Token | The |
Token ID | 464 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
virtue | +0.048 |
vous | +0.047 |
rig | +0.046 |
importance | +0.046 |
Yes | +0.045 |
Neg logit contributions | |
ged | -0.034 |
down | -0.033 |
iked | -0.033 |
onward | -0.031 |
leys | -0.029 |
Token | child |
Token ID | 1200 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
rig | +0.136 |
virtue | +0.134 |
vous | +0.122 |
leaf | +0.121 |
Yes | +0.118 |
Neg logit contributions | |
down | -0.111 |
iked | -0.110 |
ged | -0.107 |
, | -0.106 |
ashore | -0.101 |
Token | said |
Token ID | 531 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
virtue | +0.477 |
rig | +0.460 |
vous | +0.448 |
importance | +0.433 |
leaf | +0.433 |
Neg logit contributions | |
down | -0.354 |
, | -0.344 |
ged | -0.338 |
am | -0.311 |
iked | -0.307 |
Token | , |
Token ID | 11 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
ged | +0.050 |
iked | +0.050 |
leys | +0.048 |
ashore | +0.042 |
rolling | +0.041 |
Neg logit contributions | |
Yes | -0.109 |
virtue | -0.103 |
song | -0.103 |
bit | -0.102 |
child | -0.101 |
Token | � |
Token ID | 6184 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ged | +0.165 |
iked | +0.159 |
down | +0.158 |
onward | +0.143 |
leys | +0.137 |
Neg logit contributions | |
virtue | -0.375 |
vous | -0.374 |
rig | -0.369 |
Yes | -0.367 |
importance | -0.364 |
Token | � |
Token ID | 95 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ged | +0.053 |
down | +0.052 |
iked | +0.051 |
onward | +0.050 |
leys | +0.049 |
Neg logit contributions | |
virtue | -0.053 |
rig | -0.053 |
vous | -0.052 |
Yes | -0.052 |
leaf | -0.050 |
Token | € |
Token ID | 26391 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
down | +0.029 |
ged | +0.029 |
iked | +0.028 |
am | +0.027 |
onward | +0.027 |
Neg logit contributions | |
virtue | -0.030 |
rig | -0.029 |
Yes | -0.029 |
importance | -0.029 |
vous | -0.028 |
Token | offered |
Token ID | 4438 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
virtue | +0.129 |
rig | +0.125 |
vous | +0.120 |
importance | +0.117 |
Yes | +0.117 |
Neg logit contributions | |
ged | -0.128 |
down | -0.125 |
iked | -0.118 |
am | -0.114 |
onward | -0.113 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
down | +0.052 |
his | +0.049 |
, | +0.044 |
ged | +0.042 |
iked | +0.042 |
Neg logit contributions | |
vous | -0.122 |
rig | -0.121 |
virtue | -0.118 |
importance | -0.109 |
matter | -0.108 |
Token | help |
Token ID | 1037 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
vous | +0.088 |
rig | +0.086 |
virtue | +0.082 |
importance | +0.079 |
poet | +0.073 |
Neg logit contributions | |
his | -0.062 |
down | -0.062 |
, | -0.056 |
their | -0.053 |
them | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
vous | +0.083 |
virtue | +0.081 |
rig | +0.081 |
importance | +0.078 |
leaf | +0.077 |
Neg logit contributions | |
down | -0.054 |
, | -0.049 |
ged | -0.049 |
his | -0.046 |
iked | -0.045 |
Token | other |
Token ID | 584 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
down | +0.004 |
iked | +0.004 |
ged | +0.004 |
onward | +0.004 |
am | +0.004 |
Neg logit contributions | |
virtue | -0.003 |
rig | -0.003 |
vous | -0.003 |
Yes | -0.002 |
leaf | -0.002 |
Token | child |
Token ID | 1200 |
Feature activation | -1.31e+01 |
Pos logit contributions | |
vous | +0.096 |
virtue | +0.096 |
rig | +0.093 |
Yes | +0.091 |
importance | +0.091 |
Neg logit contributions | |
ged | -0.174 |
down | -0.172 |
iked | -0.171 |
onward | -0.163 |
leys | -0.159 |
Token | organize |
Token ID | 16481 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
vous | +0.494 |
virtue | +0.492 |
rig | +0.480 |
Yes | +0.474 |
importance | +0.473 |
Neg logit contributions | |
down | -0.301 |
ged | -0.282 |
iked | -0.274 |
onward | -0.256 |
am | -0.251 |
Token | his |
Token ID | 465 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
down | +0.086 |
ged | +0.081 |
, | +0.073 |
iked | +0.072 |
onward | +0.072 |
Neg logit contributions | |
vous | -0.167 |
rig | -0.160 |
virtue | -0.159 |
importance | -0.153 |
leaf | -0.153 |
Token | things |
Token ID | 1243 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
ged | +0.143 |
iked | +0.138 |
down | +0.136 |
onward | +0.129 |
leys | +0.120 |
Neg logit contributions | |
vous | -0.212 |
virtue | -0.211 |
rig | -0.207 |
importance | -0.206 |
Yes | -0.202 |
Token | into |
Token ID | 656 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
virtue | +0.187 |
vous | +0.186 |
rig | +0.183 |
Yes | +0.180 |
importance | +0.180 |
Neg logit contributions | |
ged | -0.116 |
down | -0.113 |
iked | -0.113 |
onward | -0.104 |
leys | -0.099 |
Token | the |
Token ID | 262 |
Feature activation | +7.32e-02 |
Pos logit contributions | |
down | +0.058 |
ged | +0.056 |
his | +0.051 |
, | +0.050 |
onward | +0.050 |
Neg logit contributions | |
rig | -0.108 |
vous | -0.106 |
virtue | -0.102 |
leaf | -0.102 |
Yes | -0.100 |
Token | |
Token ID | 220 |
Feature activation | +4.34e+00 |
Pos logit contributions | |
virtue | +0.167 |
vous | +0.165 |
rig | +0.162 |
importance | +0.159 |
leaf | +0.153 |
Neg logit contributions | |
down | -0.101 |
ged | -0.096 |
iked | -0.095 |
onward | -0.087 |
am | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ged | +0.134 |
iked | +0.130 |
down | +0.126 |
onward | +0.121 |
leys | +0.117 |
Neg logit contributions | |
rig | -0.125 |
Yes | -0.123 |
virtue | -0.122 |
vous | -0.122 |
importance | -0.118 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
virtue | +0.051 |
vous | +0.050 |
rig | +0.049 |
importance | +0.049 |
matter | +0.047 |
Neg logit contributions | |
down | -0.034 |
ged | -0.034 |
iked | -0.033 |
onward | -0.031 |
leys | -0.030 |
Token | So |
Token ID | 2396 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
virtue | +0.045 |
vous | +0.044 |
rig | +0.042 |
importance | +0.042 |
least | +0.041 |
Neg logit contributions | |
down | -0.041 |
ged | -0.039 |
iked | -0.039 |
onward | -0.037 |
leys | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
virtue | +0.148 |
Yes | +0.147 |
vous | +0.146 |
rig | +0.144 |
importance | +0.143 |
Neg logit contributions | |
ged | -0.067 |
iked | -0.064 |
down | -0.061 |
onward | -0.057 |
leys | -0.056 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
, | +0.004 |
down | +0.003 |
iked | +0.003 |
ged | +0.003 |
sand | +0.003 |
Neg logit contributions | |
virtue | -0.006 |
rig | -0.006 |
leaf | -0.006 |
deserve | -0.006 |
vous | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
virtue | +0.461 |
vous | +0.455 |
rig | +0.449 |
Yes | +0.441 |
importance | +0.439 |
Neg logit contributions | |
down | -0.322 |
ged | -0.319 |
iked | -0.312 |
onward | -0.287 |
am | -0.284 |
Token | Mom |
Token ID | 11254 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
virtue | +0.199 |
rig | +0.196 |
vous | +0.196 |
importance | +0.189 |
leaf | +0.187 |
Neg logit contributions | |
down | -0.078 |
ged | -0.073 |
iked | -0.068 |
onward | -0.061 |
am | -0.058 |
Token | my |
Token ID | 1820 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
vous | +0.118 |
Yes | +0.112 |
virtue | +0.110 |
rig | +0.110 |
importance | +0.107 |
Neg logit contributions | |
ged | -0.227 |
iked | -0.222 |
down | -0.216 |
onward | -0.215 |
ls | -0.213 |
Token | sn |
Token ID | 3013 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
vous | +0.076 |
virtue | +0.074 |
rig | +0.074 |
Yes | +0.074 |
importance | +0.073 |
Neg logit contributions | |
ged | -0.060 |
iked | -0.058 |
down | -0.058 |
onward | -0.056 |
leys | -0.053 |
Token | ugg |
Token ID | 6837 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
down | +0.111 |
ged | +0.109 |
ls | +0.108 |
onward | +0.106 |
iked | +0.105 |
Neg logit contributions | |
virtue | -0.074 |
Yes | -0.072 |
vous | -0.069 |
rig | -0.069 |
leaf | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
virtue | +0.008 |
vous | +0.008 |
rig | +0.008 |
Yes | +0.008 |
importance | +0.007 |
Neg logit contributions | |
down | -0.007 |
ls | -0.006 |
ged | -0.006 |
iked | -0.006 |
am | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
vous | +0.094 |
virtue | +0.091 |
rig | +0.090 |
Yes | +0.088 |
leaf | +0.086 |
Neg logit contributions | |
down | -0.086 |
ged | -0.083 |
iked | -0.079 |
onward | -0.077 |
am | -0.074 |
Token | picture |
Token ID | 4286 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
vous | +0.155 |
rig | +0.152 |
leaf | +0.143 |
illa | +0.133 |
Sad | +0.131 |
Neg logit contributions | |
, | -0.116 |
down | -0.115 |
sand | -0.104 |
sail | -0.099 |
ged | -0.098 |
Token | of |
Token ID | 286 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
virtue | +0.184 |
rig | +0.182 |
vous | +0.181 |
importance | +0.175 |
Yes | +0.173 |
Neg logit contributions | |
down | -0.174 |
ged | -0.167 |
iked | -0.163 |
onward | -0.157 |
, | -0.154 |
Token | a |
Token ID | 257 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
rig | +0.224 |
vous | +0.218 |
virtue | +0.214 |
leaf | +0.190 |
Yes | +0.185 |
Neg logit contributions | |
down | -0.133 |
his | -0.123 |
ged | -0.122 |
, | -0.121 |
their | -0.120 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
rig | +0.156 |
vous | +0.150 |
leaf | +0.139 |
virtue | +0.138 |
importance | +0.133 |
Neg logit contributions | |
down | -0.121 |
, | -0.118 |
ged | -0.105 |
sand | -0.105 |
onward | -0.100 |
Token | with |
Token ID | 351 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
virtue | +0.524 |
vous | +0.510 |
rig | +0.510 |
importance | +0.502 |
Yes | +0.485 |
Neg logit contributions | |
down | -0.281 |
ged | -0.279 |
iked | -0.256 |
onward | -0.243 |
, | -0.238 |
Token | a |
Token ID | 257 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
rig | +0.071 |
virtue | +0.069 |
vous | +0.065 |
importance | +0.063 |
Yes | +0.062 |
Neg logit contributions | |
ged | -0.056 |
down | -0.056 |
iked | -0.051 |
onward | -0.050 |
, | -0.049 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
rig | +0.148 |
vous | +0.146 |
virtue | +0.138 |
importance | +0.132 |
leaf | +0.131 |
Neg logit contributions | |
down | -0.130 |
ged | -0.123 |
, | -0.119 |
onward | -0.115 |
ls | -0.111 |
Token | face |
Token ID | 1986 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
virtue | +0.044 |
vous | +0.043 |
rig | +0.042 |
importance | +0.042 |
Yes | +0.042 |
Neg logit contributions | |
ged | -0.052 |
iked | -0.051 |
down | -0.050 |
onward | -0.048 |
leys | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
vous | +0.120 |
virtue | +0.119 |
rig | +0.117 |
Yes | +0.116 |
importance | +0.116 |
Neg logit contributions | |
ged | -0.074 |
iked | -0.073 |
down | -0.072 |
onward | -0.067 |
leys | -0.064 |
Token | One |
Token ID | 3198 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
virtue | +0.043 |
rig | +0.043 |
vous | +0.042 |
least | +0.042 |
importance | +0.040 |
Neg logit contributions | |
iked | -0.032 |
ged | -0.032 |
down | -0.031 |
onward | -0.030 |
leys | -0.030 |
Token | day |
Token ID | 1110 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
, | +0.060 |
down | +0.048 |
his | +0.046 |
their | +0.042 |
he | +0.040 |
Neg logit contributions | |
virtue | -0.099 |
least | -0.094 |
leaf | -0.093 |
rig | -0.092 |
importance | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
bit | +0.038 |
child | +0.036 |
Yes | +0.036 |
matter | +0.036 |
years | +0.035 |
Neg logit contributions | |
leys | -0.029 |
cast | -0.028 |
iece | -0.026 |
iked | -0.026 |
am | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
down | +0.234 |
ged | +0.214 |
, | +0.213 |
his | +0.194 |
iked | +0.192 |
Neg logit contributions | |
rig | -0.375 |
virtue | -0.363 |
vous | -0.354 |
importance | -0.336 |
leaf | -0.326 |
Token | little |
Token ID | 1310 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
rig | +0.140 |
virtue | +0.138 |
vous | +0.134 |
leaf | +0.130 |
least | +0.129 |
Neg logit contributions | |
down | -0.123 |
, | -0.121 |
ged | -0.110 |
onward | -0.107 |
ls | -0.106 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.203 |
rig | +0.201 |
vous | +0.193 |
importance | +0.191 |
leaf | +0.176 |
Neg logit contributions | |
down | -0.252 |
ged | -0.237 |
iked | -0.224 |
, | -0.220 |
ls | -0.216 |
Token | was |
Token ID | 373 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
vous | +0.511 |
virtue | +0.498 |
Yes | +0.492 |
rig | +0.492 |
importance | +0.485 |
Neg logit contributions | |
ged | -0.262 |
down | -0.259 |
iked | -0.258 |
onward | -0.239 |
leys | -0.224 |
Token | playing |
Token ID | 2712 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
virtue | +0.128 |
rig | +0.127 |
vous | +0.125 |
Yes | +0.123 |
importance | +0.122 |
Neg logit contributions | |
down | -0.082 |
ged | -0.078 |
iked | -0.075 |
onward | -0.070 |
am | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
down | +0.139 |
ged | +0.120 |
, | +0.115 |
his | +0.112 |
iked | +0.102 |
Neg logit contributions | |
virtue | -0.262 |
rig | -0.259 |
vous | -0.250 |
importance | -0.244 |
matter | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
down | +0.015 |
his | +0.013 |
ged | +0.013 |
, | +0.012 |
iked | +0.011 |
Neg logit contributions | |
virtue | -0.032 |
rig | -0.032 |
vous | -0.031 |
leaf | -0.030 |
importance | -0.029 |
Token | town |
Token ID | 3240 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.003 |
down | +0.003 |
onward | +0.003 |
ls | +0.002 |
Neg logit contributions | |
vous | -0.002 |
virtue | -0.002 |
rig | -0.002 |
Yes | -0.002 |
importance | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
virtue | +0.080 |
rig | +0.079 |
importance | +0.075 |
vous | +0.073 |
Yes | +0.071 |
Neg logit contributions | |
down | -0.057 |
ged | -0.055 |
, | -0.053 |
iked | -0.049 |
am | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
vous | +0.127 |
Yes | +0.126 |
virtue | +0.123 |
importance | +0.121 |
leaf | +0.118 |
Neg logit contributions | |
iked | -0.131 |
ged | -0.130 |
down | -0.125 |
onward | -0.124 |
leys | -0.121 |
Token | 3 |
Token ID | 513 |
Feature activation | -9.71e+00 |
Pos logit contributions | |
rig | +0.140 |
virtue | +0.138 |
vous | +0.137 |
leaf | +0.127 |
importance | +0.126 |
Neg logit contributions | |
down | -0.137 |
, | -0.125 |
ged | -0.122 |
iked | -0.113 |
onward | -0.110 |
Token | year |
Token ID | 614 |
Feature activation | -8.88e+00 |
Pos logit contributions | |
virtue | +0.263 |
least | +0.255 |
rig | +0.252 |
importance | +0.227 |
leaf | +0.217 |
Neg logit contributions | |
ged | -0.354 |
, | -0.338 |
down | -0.338 |
iked | -0.326 |
ls | -0.314 |
Token | old |
Token ID | 1468 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
vous | +0.177 |
elderly | +0.177 |
rig | +0.175 |
virtue | +0.170 |
years | +0.160 |
Neg logit contributions | |
ged | -0.371 |
iked | -0.346 |
onward | -0.334 |
down | -0.330 |
leys | -0.322 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.023 |
rig | +0.022 |
vous | +0.022 |
importance | +0.021 |
Yes | +0.021 |
Neg logit contributions | |
down | -0.035 |
ged | -0.035 |
iked | -0.034 |
onward | -0.032 |
ls | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
virtue | +0.436 |
rig | +0.432 |
vous | +0.428 |
importance | +0.417 |
Yes | +0.411 |
Neg logit contributions | |
ged | -0.351 |
down | -0.346 |
iked | -0.338 |
onward | -0.314 |
am | -0.304 |
Token | The |
Token ID | 383 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
vous | +0.002 |
Yes | +0.002 |
virtue | +0.002 |
rig | +0.002 |
importance | +0.002 |
Neg logit contributions | |
ged | -0.002 |
iked | -0.001 |
down | -0.001 |
onward | -0.001 |
ls | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
virtue | +0.122 |
rig | +0.120 |
leaf | +0.116 |
deserve | +0.116 |
vous | +0.115 |
Neg logit contributions | |
, | -0.086 |
down | -0.082 |
back | -0.074 |
sand | -0.072 |
iked | -0.072 |
Token | my |
Token ID | 1820 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
virtue | +0.309 |
rig | +0.294 |
leaf | +0.278 |
importance | +0.277 |
vous | +0.273 |
Neg logit contributions | |
down | -0.217 |
, | -0.198 |
ged | -0.178 |
am | -0.177 |
iked | -0.167 |
Token | was |
Token ID | 373 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
virtue | +0.086 |
rig | +0.083 |
matter | +0.080 |
leaf | +0.078 |
vous | +0.077 |
Neg logit contributions | |
, | -0.057 |
down | -0.053 |
am | -0.050 |
ged | -0.049 |
iked | -0.045 |
Token | seen |
Token ID | 1775 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
virtue | +0.172 |
rig | +0.165 |
Yes | +0.160 |
vous | +0.148 |
leaf | +0.147 |
Neg logit contributions | |
ged | -0.208 |
down | -0.205 |
iked | -0.192 |
leys | -0.190 |
, | -0.187 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
rig | +0.026 |
virtue | +0.025 |
vous | +0.025 |
Yes | +0.025 |
leaf | +0.024 |
Neg logit contributions | |
down | -0.015 |
ged | -0.014 |
, | -0.014 |
onward | -0.013 |
iked | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
vous | +0.000 |
virtue | +0.000 |
rig | +0.000 |
matter | +0.000 |
importance | +0.000 |
Neg logit contributions | |
down | -0.000 |
iked | -0.000 |
ged | -0.000 |
onward | -0.000 |
am | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
matter | +0.051 |
vous | +0.051 |
virtue | +0.050 |
importance | +0.048 |
rig | +0.047 |
Neg logit contributions | |
ged | -0.028 |
down | -0.027 |
iked | -0.027 |
onward | -0.026 |
am | -0.025 |
Token | The |
Token ID | 464 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
vous | +0.039 |
matter | +0.038 |
rig | +0.037 |
virtue | +0.037 |
meaning | +0.036 |
Neg logit contributions | |
iked | -0.038 |
ged | -0.038 |
His | -0.037 |
onward | -0.036 |
leys | -0.035 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.154 |
leaf | +0.153 |
rig | +0.150 |
deserve | +0.146 |
losers | +0.137 |
Neg logit contributions | |
, | -0.109 |
sand | -0.082 |
down | -0.078 |
back | -0.074 |
ged | -0.073 |
Token | was |
Token ID | 373 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
virtue | +0.497 |
vous | +0.476 |
rig | +0.470 |
leaf | +0.445 |
importance | +0.444 |
Neg logit contributions | |
, | -0.328 |
down | -0.322 |
am | -0.318 |
ged | -0.317 |
iked | -0.292 |
Token | so |
Token ID | 523 |
Feature activation | -7.86e+00 |
Pos logit contributions | |
virtue | +0.099 |
rig | +0.098 |
vous | +0.097 |
matter | +0.095 |
leaf | +0.094 |
Neg logit contributions | |
down | -0.117 |
onward | -0.105 |
, | -0.104 |
ged | -0.103 |
am | -0.099 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
virtue | +0.252 |
vous | +0.247 |
rig | +0.241 |
importance | +0.238 |
matter | +0.234 |
Neg logit contributions | |
down | -0.223 |
ged | -0.217 |
iked | -0.210 |
onward | -0.206 |
am | -0.194 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
vous | +0.050 |
virtue | +0.050 |
rig | +0.049 |
importance | +0.047 |
Yes | +0.047 |
Neg logit contributions | |
down | -0.038 |
ged | -0.037 |
iked | -0.036 |
onward | -0.033 |
ls | -0.032 |
Token | From |
Token ID | 3574 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
virtue | +0.001 |
Yes | +0.001 |
rig | +0.001 |
importance | +0.001 |
vous | +0.001 |
Neg logit contributions | |
ged | -0.001 |
down | -0.001 |
iked | -0.001 |
ls | -0.001 |
leys | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
virtue | +0.004 |
vous | +0.004 |
rig | +0.004 |
Yes | +0.004 |
importance | +0.004 |
Neg logit contributions | |
ged | -0.001 |
down | -0.001 |
iked | -0.001 |
onward | -0.001 |
leys | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
down | +0.125 |
ged | +0.122 |
am | +0.116 |
iked | +0.113 |
, | +0.113 |
Neg logit contributions | |
virtue | -0.199 |
vous | -0.192 |
rig | -0.190 |
Yes | -0.184 |
leaf | -0.182 |
Token | over |
Token ID | 625 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ged | +0.156 |
iked | +0.151 |
leys | +0.144 |
am | +0.141 |
onward | +0.140 |
Neg logit contributions | |
rig | -0.159 |
Yes | -0.158 |
leaf | -0.156 |
vous | -0.155 |
virtue | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
down | +0.081 |
ged | +0.076 |
iked | +0.073 |
, | +0.070 |
onward | +0.068 |
Neg logit contributions | |
virtue | -0.136 |
vous | -0.131 |
rig | -0.131 |
importance | -0.126 |
matter | -0.123 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
virtue | +0.107 |
rig | +0.102 |
vous | +0.101 |
importance | +0.097 |
years | +0.092 |
Neg logit contributions | |
down | -0.047 |
his | -0.042 |
ged | -0.037 |
, | -0.037 |
them | -0.034 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
down | +0.003 |
castles | +0.003 |
ls | +0.003 |
back | +0.003 |
iked | +0.003 |
Neg logit contributions | |
virtue | -0.004 |
rig | -0.004 |
vous | -0.004 |
matter | -0.004 |
leaf | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
virtue | +0.502 |
vous | +0.482 |
importance | +0.466 |
Yes | +0.461 |
leaf | +0.460 |
Neg logit contributions | |
down | -0.336 |
, | -0.319 |
ged | -0.295 |
iked | -0.291 |
am | -0.274 |
Token | was |
Token ID | 373 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
virtue | +0.283 |
rig | +0.274 |
vous | +0.253 |
importance | +0.251 |
leaf | +0.243 |
Neg logit contributions | |
ged | -0.173 |
down | -0.173 |
, | -0.162 |
his | -0.154 |
he | -0.154 |
Token | yelling |
Token ID | 22187 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
virtue | +0.104 |
rig | +0.103 |
vous | +0.099 |
Yes | +0.098 |
importance | +0.096 |
Neg logit contributions | |
down | -0.100 |
ged | -0.093 |
, | -0.089 |
onward | -0.088 |
iked | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
iked | +0.126 |
ged | +0.117 |
leys | +0.111 |
onward | +0.111 |
ls | +0.110 |
Neg logit contributions | |
virtue | -0.125 |
importance | -0.124 |
vous | -0.123 |
Yes | -0.122 |
rig | -0.120 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
virtue | +0.129 |
vous | +0.128 |
rig | +0.126 |
importance | +0.122 |
Yes | +0.121 |
Neg logit contributions | |
ged | -0.135 |
down | -0.134 |
iked | -0.131 |
onward | -0.123 |
leys | -0.119 |
Token | down |
Token ID | 866 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
iked | +0.167 |
ged | +0.150 |
am | +0.136 |
onward | +0.135 |
rolled | +0.131 |
Neg logit contributions | |
rig | -0.251 |
Yes | -0.238 |
leaf | -0.235 |
virtue | -0.233 |
importance | -0.231 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
iked | +0.280 |
ged | +0.273 |
drivers | +0.262 |
leys | +0.257 |
rolled | +0.248 |
Neg logit contributions | |
Yes | -0.266 |
elderly | -0.255 |
years | -0.248 |
importance | -0.244 |
meaning | -0.238 |
Token | see |
Token ID | 766 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
vous | +0.078 |
virtue | +0.078 |
rig | +0.077 |
Yes | +0.075 |
importance | +0.075 |
Neg logit contributions | |
ged | -0.061 |
down | -0.060 |
iked | -0.059 |
onward | -0.056 |
leys | -0.053 |
Token | a |
Token ID | 257 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
down | +0.058 |
ged | +0.056 |
iked | +0.053 |
onward | +0.051 |
ls | +0.050 |
Neg logit contributions | |
virtue | -0.068 |
vous | -0.068 |
rig | -0.067 |
importance | -0.065 |
Yes | -0.063 |
Token | small |
Token ID | 1402 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
vous | +0.148 |
rig | +0.145 |
virtue | +0.144 |
leaf | +0.142 |
importance | +0.135 |
Neg logit contributions | |
down | -0.126 |
, | -0.117 |
ged | -0.109 |
ls | -0.105 |
onward | -0.104 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
down | +0.037 |
ged | +0.034 |
, | +0.034 |
iked | +0.032 |
onward | +0.032 |
Neg logit contributions | |
virtue | -0.038 |
rig | -0.037 |
vous | -0.037 |
leaf | -0.036 |
importance | -0.035 |
Token | standing |
Token ID | 5055 |
Feature activation | +8.72e+00 |
Pos logit contributions | |
vous | +0.468 |
virtue | +0.464 |
rig | +0.460 |
Yes | +0.454 |
importance | +0.448 |
Neg logit contributions | |
ged | -0.302 |
iked | -0.296 |
down | -0.294 |
onward | -0.273 |
leys | -0.262 |
Token | with |
Token ID | 351 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ged | +0.216 |
iked | +0.214 |
down | +0.205 |
onward | +0.194 |
leys | +0.187 |
Neg logit contributions | |
vous | -0.300 |
virtue | -0.299 |
rig | -0.295 |
Yes | -0.293 |
importance | -0.288 |
Token | its |
Token ID | 663 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
vous | +0.052 |
virtue | +0.052 |
rig | +0.050 |
Yes | +0.050 |
importance | +0.049 |
Neg logit contributions | |
ged | -0.064 |
iked | -0.063 |
down | -0.063 |
onward | -0.059 |
leys | -0.058 |
Token | arms |
Token ID | 5101 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
down | +0.132 |
ged | +0.125 |
iked | +0.120 |
onward | +0.115 |
am | +0.113 |
Neg logit contributions | |
virtue | -0.167 |
rig | -0.164 |
vous | -0.164 |
Yes | -0.158 |
leaf | -0.156 |
Token | folded |
Token ID | 24650 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
rig | +0.094 |
meaning | +0.093 |
vous | +0.093 |
importance | +0.090 |
ight | +0.089 |
Neg logit contributions | |
iked | -0.120 |
ged | -0.109 |
ls | -0.108 |
onward | -0.107 |
am | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Yes | +0.002 |
virtue | +0.002 |
rig | +0.002 |
vous | +0.002 |
importance | +0.002 |
Neg logit contributions | |
ged | -0.002 |
down | -0.002 |
iked | -0.002 |
ls | -0.002 |
leys | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Yes | +0.038 |
virtue | +0.038 |
rig | +0.037 |
vous | +0.037 |
importance | +0.036 |
Neg logit contributions | |
ged | -0.042 |
down | -0.041 |
iked | -0.040 |
onward | -0.037 |
leys | -0.037 |
Token | " |
Token ID | 1 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
virtue | +0.035 |
vous | +0.035 |
Yes | +0.034 |
rig | +0.034 |
importance | +0.033 |
Neg logit contributions | |
ged | -0.046 |
down | -0.045 |
iked | -0.044 |
onward | -0.042 |
ls | -0.041 |
Token | Let |
Token ID | 5756 |
Feature activation | -7.20e+00 |
Pos logit contributions | |
virtue | +0.019 |
rig | +0.019 |
vous | +0.018 |
least | +0.016 |
importance | +0.016 |
Neg logit contributions | |
ged | -0.019 |
down | -0.017 |
iked | -0.016 |
onward | -0.016 |
leys | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
virtue | +0.260 |
rig | +0.256 |
vous | +0.252 |
leaf | +0.246 |
importance | +0.244 |
Neg logit contributions | |
down | -0.186 |
ged | -0.167 |
, | -0.162 |
am | -0.158 |
onward | -0.155 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
down | +0.005 |
, | +0.004 |
out | +0.004 |
off | +0.004 |
back | +0.004 |
Neg logit contributions | |
rig | -0.008 |
virtue | -0.006 |
ampoo | -0.006 |
rou | -0.006 |
leaf | -0.006 |
Token | decide |
Token ID | 5409 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
virtue | +0.469 |
vous | +0.453 |
rig | +0.453 |
importance | +0.452 |
Yes | +0.438 |
Neg logit contributions | |
down | -0.348 |
ged | -0.308 |
iked | -0.294 |
, | -0.292 |
am | -0.285 |
Token | ," |
Token ID | 553 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
vous | +0.011 |
virtue | +0.011 |
rig | +0.011 |
importance | +0.011 |
Yes | +0.010 |
Neg logit contributions | |
down | -0.009 |
ged | -0.009 |
iked | -0.008 |
onward | -0.008 |
, | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
virtue | +0.052 |
vous | +0.051 |
rig | +0.050 |
importance | +0.049 |
matter | +0.046 |
Neg logit contributions | |
down | -0.040 |
ged | -0.040 |
iked | -0.039 |
onward | -0.036 |
am | -0.035 |
Token | Mum |
Token ID | 38367 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ged | +0.091 |
iked | +0.088 |
leys | +0.087 |
down | +0.086 |
onward | +0.083 |
Neg logit contributions | |
Yes | -0.071 |
vous | -0.065 |
leaf | -0.064 |
virtue | -0.063 |
child | -0.063 |
Token | stern |
Token ID | 26370 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
vous | +0.154 |
rig | +0.152 |
Yes | +0.151 |
virtue | +0.151 |
importance | +0.145 |
Neg logit contributions | |
ged | -0.103 |
iked | -0.102 |
down | -0.097 |
onward | -0.095 |
leys | -0.092 |
Token | sand |
Token ID | 6450 |
Feature activation | +6.82e+00 |
Pos logit contributions | |
down | +0.008 |
ged | +0.007 |
iked | +0.007 |
onward | +0.007 |
leys | +0.006 |
Neg logit contributions | |
virtue | -0.010 |
rig | -0.010 |
vous | -0.010 |
Yes | -0.010 |
importance | -0.010 |
Token | box |
Token ID | 3091 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ged | +0.184 |
down | +0.182 |
iked | +0.180 |
onward | +0.168 |
leys | +0.162 |
Neg logit contributions | |
virtue | -0.222 |
vous | -0.221 |
rig | -0.217 |
Yes | -0.213 |
importance | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
virtue | +0.015 |
vous | +0.015 |
rig | +0.015 |
Yes | +0.015 |
importance | +0.015 |
Neg logit contributions | |
ged | -0.012 |
down | -0.012 |
iked | -0.012 |
onward | -0.011 |
leys | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ged | +0.003 |
down | +0.003 |
iked | +0.003 |
onward | +0.003 |
leys | +0.003 |
Neg logit contributions | |
virtue | -0.004 |
vous | -0.004 |
rig | -0.004 |
Yes | -0.004 |
importance | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
rig | +0.105 |
virtue | +0.102 |
Yes | +0.096 |
vous | +0.091 |
leaf | +0.091 |
Neg logit contributions | |
down | -0.099 |
castles | -0.088 |
, | -0.087 |
ged | -0.085 |
sand | -0.085 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.114 |
rig | +0.111 |
Yes | +0.098 |
leaf | +0.098 |
vous | +0.095 |
Neg logit contributions | |
down | -0.164 |
iked | -0.161 |
ged | -0.160 |
, | -0.156 |
am | -0.156 |
Token | shouted |
Token ID | 17293 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
virtue | +0.502 |
rig | +0.480 |
importance | +0.466 |
vous | +0.458 |
Yes | +0.458 |
Neg logit contributions | |
ged | -0.332 |
down | -0.325 |
, | -0.313 |
am | -0.295 |
iked | -0.281 |
Token | : |
Token ID | 25 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
iked | +0.076 |
ged | +0.074 |
leys | +0.072 |
onward | +0.069 |
valleys | +0.068 |
Neg logit contributions | |
virtue | -0.101 |
importance | -0.098 |
rig | -0.097 |
Yes | -0.096 |
song | -0.094 |
Token | " |
Token ID | 366 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ged | +0.081 |
iked | +0.081 |
ls | +0.077 |
leys | +0.075 |
am | +0.074 |
Neg logit contributions | |
Yes | -0.104 |
importance | -0.100 |
virtue | -0.098 |
rig | -0.096 |
vous | -0.093 |
Token | Help |
Token ID | 22087 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
virtue | +0.034 |
rig | +0.034 |
importance | +0.029 |
years | +0.029 |
meaning | +0.029 |
Neg logit contributions | |
ged | -0.029 |
down | -0.026 |
His | -0.024 |
ging | -0.024 |
iked | -0.023 |
Token | ! |
Token ID | 0 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
virtue | +0.112 |
rig | +0.110 |
vous | +0.108 |
importance | +0.107 |
Yes | +0.104 |
Neg logit contributions | |
down | -0.096 |
ged | -0.095 |
iked | -0.089 |
onward | -0.084 |
, | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
virtue | +0.174 |
Yes | +0.170 |
importance | +0.169 |
vous | +0.169 |
rig | +0.167 |
Neg logit contributions | |
ged | -0.153 |
iked | -0.152 |
onward | -0.139 |
leys | -0.139 |
ls | -0.137 |
Token | everyone |
Token ID | 2506 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
virtue | +0.108 |
rig | +0.107 |
vous | +0.106 |
importance | +0.102 |
Yes | +0.101 |
Neg logit contributions | |
down | -0.040 |
ged | -0.036 |
iked | -0.033 |
onward | -0.032 |
his | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
virtue | +0.163 |
vous | +0.163 |
rig | +0.160 |
importance | +0.157 |
Yes | +0.157 |
Neg logit contributions | |
down | -0.091 |
ged | -0.091 |
iked | -0.088 |
onward | -0.081 |
ls | -0.077 |
Token | So |
Token ID | 1406 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
down | +0.001 |
ged | +0.001 |
iked | +0.001 |
onward | +0.001 |
am | +0.001 |
Neg logit contributions | |
vous | -0.002 |
virtue | -0.002 |
rig | -0.002 |
importance | -0.002 |
Yes | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Yes | +0.081 |
virtue | +0.081 |
importance | +0.079 |
matter | +0.077 |
vous | +0.077 |
Neg logit contributions | |
ged | -0.026 |
iked | -0.024 |
leys | -0.023 |
down | -0.020 |
ls | -0.018 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
rig | +0.005 |
virtue | +0.004 |
vous | +0.004 |
ampoo | +0.004 |
leaf | +0.004 |
Neg logit contributions | |
down | -0.005 |
, | -0.005 |
back | -0.004 |
ged | -0.004 |
ls | -0.004 |
Token | started |
Token ID | 2067 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
virtue | +0.494 |
rig | +0.485 |
vous | +0.480 |
Yes | +0.456 |
leaf | +0.454 |
Neg logit contributions | |
am | -0.310 |
down | -0.307 |
ged | -0.306 |
, | -0.306 |
iked | -0.287 |
Token | to |
Token ID | 284 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ged | +0.129 |
iked | +0.127 |
down | +0.123 |
leys | +0.120 |
onward | +0.119 |
Neg logit contributions | |
virtue | -0.138 |
vous | -0.138 |
rig | -0.138 |
importance | -0.136 |
Yes | -0.135 |
Token | sing |
Token ID | 1702 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
virtue | +0.079 |
vous | +0.079 |
rig | +0.074 |
leaf | +0.072 |
importance | +0.071 |
Neg logit contributions | |
down | -0.072 |
ged | -0.064 |
, | -0.064 |
iked | -0.061 |
his | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
virtue | +0.002 |
vous | +0.002 |
rig | +0.002 |
Yes | +0.002 |
importance | +0.002 |
Neg logit contributions | |
ged | -0.001 |
iked | -0.001 |
down | -0.001 |
onward | -0.001 |
leys | -0.001 |
Token | special |
Token ID | 2041 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
vous | +0.135 |
illa | +0.121 |
leaf | +0.120 |
virtue | +0.115 |
resa | +0.114 |
Neg logit contributions | |
, | -0.147 |
down | -0.143 |
sail | -0.127 |
back | -0.124 |
onward | -0.122 |
Token | compassionate |
Token ID | 32533 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
vous | +0.121 |
rig | +0.118 |
virtue | +0.113 |
importance | +0.107 |
leaf | +0.102 |
Neg logit contributions | |
down | -0.145 |
ged | -0.135 |
iked | -0.134 |
onward | -0.129 |
, | -0.127 |
Token | , |
Token ID | 11 |
Feature activation | +9.08e+00 |
Pos logit contributions | |
vous | +0.109 |
rig | +0.108 |
virtue | +0.105 |
leaf | +0.103 |
Yes | +0.102 |
Neg logit contributions | |
down | -0.049 |
ged | -0.045 |
iked | -0.045 |
onward | -0.041 |
, | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
, | +0.235 |
down | +0.234 |
his | +0.207 |
he | +0.202 |
onward | +0.199 |
Neg logit contributions | |
vous | -0.336 |
rig | -0.326 |
virtue | -0.315 |
resa | -0.314 |
leaf | -0.310 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
rig | +0.164 |
vous | +0.162 |
virtue | +0.152 |
resa | +0.144 |
leaf | +0.144 |
Neg logit contributions | |
down | -0.111 |
, | -0.100 |
his | -0.096 |
ged | -0.093 |
onward | -0.093 |
Token | small |
Token ID | 1402 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
down | +0.001 |
, | +0.000 |
ged | +0.000 |
his | +0.000 |
onward | +0.000 |
Neg logit contributions | |
rig | -0.001 |
virtue | -0.001 |
vous | -0.001 |
leaf | -0.001 |
icated | -0.001 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
down | +0.042 |
ged | +0.042 |
iked | +0.040 |
onward | +0.038 |
ls | +0.038 |
Neg logit contributions | |
rig | -0.025 |
virtue | -0.025 |
vous | -0.025 |
Yes | -0.023 |
leaf | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
rig | +0.431 |
vous | +0.411 |
leaf | +0.398 |
virtue | +0.397 |
resa | +0.379 |
Neg logit contributions | |
, | -0.385 |
down | -0.384 |
ged | -0.362 |
am | -0.351 |
onward | -0.347 |
Token | always |
Token ID | 1464 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
rig | +0.096 |
vous | +0.092 |
virtue | +0.089 |
leaf | +0.087 |
Yes | +0.085 |
Neg logit contributions | |
down | -0.118 |
ged | -0.108 |
, | -0.108 |
onward | -0.108 |
his | -0.105 |
Token | dressed |
Token ID | 12049 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
rig | +0.069 |
vous | +0.069 |
virtue | +0.069 |
Yes | +0.065 |
importance | +0.065 |
Neg logit contributions | |
down | -0.074 |
ged | -0.072 |
iked | -0.068 |
onward | -0.067 |
am | -0.063 |
Token | nicely |
Token ID | 16576 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
down | +0.097 |
ged | +0.095 |
iked | +0.092 |
onward | +0.087 |
am | +0.082 |
Neg logit contributions | |
vous | -0.134 |
virtue | -0.133 |
rig | -0.131 |
Yes | -0.128 |
importance | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
down | +0.059 |
ged | +0.056 |
iked | +0.053 |
onward | +0.052 |
, | +0.048 |
Neg logit contributions | |
vous | -0.117 |
rig | -0.114 |
virtue | -0.114 |
Yes | -0.112 |
leaf | -0.110 |
Token | sky |
Token ID | 6766 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
down | +0.001 |
sand | +0.000 |
castles | +0.000 |
ashore | +0.000 |
, | +0.000 |
Neg logit contributions | |
vous | -0.001 |
virtue | -0.001 |
rig | -0.001 |
teaches | -0.001 |
ampoo | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
Yes | +0.100 |
rig | +0.098 |
vous | +0.098 |
importance | +0.098 |
matter | +0.096 |
Neg logit contributions | |
ged | -0.090 |
iked | -0.085 |
onward | -0.079 |
leys | -0.078 |
ls | -0.078 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Yes | +0.001 |
importance | +0.001 |
vous | +0.001 |
rig | +0.001 |
child | +0.001 |
Neg logit contributions | |
ged | -0.001 |
ls | -0.001 |
ging | -0.001 |
ooming | -0.001 |
iked | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +9.16e+00 |
Pos logit contributions | |
agged | +0.101 |
arl | +0.098 |
agons | +0.097 |
iked | +0.097 |
leys | +0.096 |
Neg logit contributions | |
child | -0.076 |
bit | -0.070 |
cater | -0.068 |
never | -0.067 |
matter | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
iked | +0.277 |
ged | +0.275 |
am | +0.261 |
leys | +0.258 |
onward | +0.255 |
Neg logit contributions | |
Yes | -0.259 |
vous | -0.245 |
importance | -0.241 |
matter | -0.237 |
child | -0.235 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.000 |
rig | +0.000 |
vous | +0.000 |
deserve | +0.000 |
teaches | +0.000 |
Neg logit contributions | |
down | -0.000 |
sand | -0.000 |
, | -0.000 |
back | -0.000 |
iked | -0.000 |
Token | heard |
Token ID | 2982 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
vous | +0.409 |
virtue | +0.404 |
rig | +0.397 |
Yes | +0.393 |
importance | +0.392 |
Neg logit contributions | |
ged | -0.358 |
iked | -0.353 |
down | -0.353 |
onward | -0.331 |
leys | -0.316 |
Token | a |
Token ID | 257 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
ged | +0.009 |
down | +0.009 |
iked | +0.009 |
onward | +0.009 |
leys | +0.008 |
Neg logit contributions | |
virtue | -0.008 |
vous | -0.008 |
rig | -0.007 |
Yes | -0.007 |
importance | -0.007 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
virtue | +0.133 |
vous | +0.130 |
rig | +0.123 |
importance | +0.123 |
leaf | +0.120 |
Neg logit contributions | |
down | -0.143 |
ged | -0.137 |
iked | -0.131 |
onward | -0.127 |
ls | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
vous | +0.082 |
rig | +0.081 |
Yes | +0.080 |
importance | +0.077 |
matter | +0.077 |
Neg logit contributions | |
iked | -0.064 |
ged | -0.063 |
onward | -0.060 |
down | -0.059 |
leys | -0.058 |
Token | He |
Token ID | 679 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
Yes | +0.002 |
child | +0.001 |
vous | +0.001 |
rig | +0.001 |
importance | +0.001 |
Neg logit contributions | |
ged | -0.002 |
ls | -0.002 |
iked | -0.002 |
ooming | -0.002 |
ging | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ged | +0.184 |
down | +0.182 |
iked | +0.179 |
onward | +0.168 |
leys | +0.160 |
Neg logit contributions | |
virtue | -0.252 |
vous | -0.251 |
rig | -0.247 |
Yes | -0.242 |
importance | -0.241 |
Token | honey |
Token ID | 12498 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
down | +0.004 |
, | +0.004 |
ls | +0.003 |
out | +0.003 |
back | +0.003 |
Neg logit contributions | |
rig | -0.008 |
leaf | -0.008 |
virtue | -0.008 |
Yes | -0.008 |
vous | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
virtue | +0.010 |
vous | +0.010 |
rig | +0.010 |
Yes | +0.010 |
importance | +0.010 |
Neg logit contributions | |
ged | -0.010 |
iked | -0.010 |
down | -0.009 |
onward | -0.009 |
leys | -0.009 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
virtue | +0.153 |
rig | +0.149 |
vous | +0.148 |
importance | +0.141 |
Yes | +0.137 |
Neg logit contributions | |
down | -0.120 |
ged | -0.115 |
iked | -0.110 |
ls | -0.103 |
onward | -0.101 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
his | +0.003 |
down | +0.003 |
, | +0.003 |
them | +0.002 |
ged | +0.002 |
Neg logit contributions | |
virtue | -0.008 |
rig | -0.008 |
vous | -0.008 |
importance | -0.007 |
leaf | -0.007 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
, | +0.004 |
down | +0.003 |
hut | +0.003 |
ls | +0.003 |
deeper | +0.003 |
Neg logit contributions | |
leaf | -0.006 |
virtue | -0.006 |
rig | -0.006 |
deserve | -0.005 |
ampoo | -0.005 |
Token | again |
Token ID | 757 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
vous | +0.494 |
virtue | +0.492 |
rig | +0.480 |
Yes | +0.474 |
importance | +0.474 |
Neg logit contributions | |
down | -0.284 |
ged | -0.280 |
iked | -0.274 |
onward | -0.253 |
am | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
down | +0.050 |
ged | +0.047 |
iked | +0.046 |
, | +0.045 |
onward | +0.043 |
Neg logit contributions | |
vous | -0.110 |
virtue | -0.109 |
rig | -0.107 |
leaf | -0.105 |
importance | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ged | +0.002 |
down | +0.002 |
iked | +0.002 |
onward | +0.002 |
leys | +0.002 |
Neg logit contributions | |
virtue | -0.003 |
vous | -0.003 |
rig | -0.003 |
Yes | -0.003 |
importance | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
virtue | +0.045 |
vous | +0.045 |
importance | +0.044 |
rig | +0.043 |
matter | +0.043 |
Neg logit contributions | |
ged | -0.031 |
down | -0.030 |
iked | -0.029 |
onward | -0.028 |
am | -0.026 |
Token | From |
Token ID | 4863 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
virtue | +0.036 |
matter | +0.035 |
vous | +0.035 |
rig | +0.034 |
importance | +0.034 |
Neg logit contributions | |
ged | -0.039 |
onward | -0.038 |
iked | -0.038 |
down | -0.036 |
His | -0.036 |
Token | closed |
Token ID | 4838 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
importance | +0.136 |
vous | +0.135 |
Yes | +0.134 |
meaning | +0.133 |
rig | +0.131 |
Neg logit contributions | |
iked | -0.152 |
ged | -0.148 |
am | -0.141 |
leys | -0.141 |
ls | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
iked | +0.195 |
ged | +0.189 |
leys | +0.174 |
onward | +0.169 |
am | +0.168 |
Neg logit contributions | |
virtue | -0.237 |
rig | -0.234 |
importance | -0.232 |
years | -0.232 |
Yes | -0.230 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
virtue | +0.000 |
vous | +0.000 |
rig | +0.000 |
importance | +0.000 |
matter | +0.000 |
Neg logit contributions | |
down | -0.000 |
ged | -0.000 |
iked | -0.000 |
onward | -0.000 |
am | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
virtue | +0.049 |
vous | +0.048 |
rig | +0.047 |
importance | +0.047 |
matter | +0.046 |
Neg logit contributions | |
ged | -0.032 |
down | -0.031 |
iked | -0.030 |
onward | -0.029 |
ls | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
virtue | +0.042 |
least | +0.040 |
rig | +0.040 |
importance | +0.039 |
vous | +0.038 |
Neg logit contributions | |
down | -0.038 |
ged | -0.038 |
iked | -0.037 |
onward | -0.037 |
leys | -0.035 |
Token | child |
Token ID | 1200 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
virtue | +0.147 |
leaf | +0.133 |
rig | +0.131 |
deserve | +0.131 |
Yes | +0.126 |
Neg logit contributions | |
, | -0.115 |
down | -0.106 |
ls | -0.097 |
hut | -0.094 |
back | -0.091 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
virtue | +0.495 |
rig | +0.474 |
leaf | +0.457 |
vous | +0.457 |
Yes | +0.454 |
Neg logit contributions | |
down | -0.328 |
ged | -0.319 |
iked | -0.298 |
, | -0.297 |
am | -0.295 |
Token | and |
Token ID | 290 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
ged | +0.103 |
iked | +0.103 |
onward | +0.094 |
leys | +0.094 |
drivers | +0.092 |
Neg logit contributions | |
Yes | -0.063 |
importance | -0.062 |
rig | -0.061 |
elderly | -0.059 |
rather | -0.058 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
virtue | +0.123 |
vous | +0.123 |
rig | +0.120 |
Yes | +0.118 |
importance | +0.117 |
Neg logit contributions | |
ged | -0.141 |
down | -0.139 |
iked | -0.139 |
onward | -0.131 |
leys | -0.127 |
Token | the |
Token ID | 262 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
ged | +0.100 |
iked | +0.099 |
leys | +0.093 |
am | +0.092 |
ooming | +0.091 |
Neg logit contributions | |
Yes | -0.102 |
importance | -0.101 |
virtue | -0.096 |
child | -0.095 |
vous | -0.095 |
Token | witch |
Token ID | 16365 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
virtue | +0.003 |
rig | +0.003 |
leaf | +0.002 |
Yes | +0.002 |
deserve | +0.002 |
Neg logit contributions | |
down | -0.003 |
, | -0.002 |
ls | -0.002 |
back | -0.002 |
his | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
down | +0.005 |
iked | +0.004 |
ged | +0.004 |
onward | +0.004 |
, | +0.004 |
Neg logit contributions | |
vous | -0.010 |
virtue | -0.010 |
rig | -0.010 |
leaf | -0.010 |
matter | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
vous | +0.044 |
virtue | +0.044 |
rig | +0.043 |
Yes | +0.043 |
importance | +0.042 |
Neg logit contributions | |
ged | -0.039 |
iked | -0.039 |
down | -0.038 |
onward | -0.036 |
leys | -0.035 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ged | +0.112 |
iked | +0.111 |
onward | +0.103 |
down | +0.102 |
ashore | +0.101 |
Neg logit contributions | |
rig | -0.093 |
Yes | -0.091 |
vous | -0.090 |
importance | -0.089 |
virtue | -0.087 |
Token | a |
Token ID | 257 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
virtue | +0.040 |
rig | +0.037 |
vous | +0.035 |
importance | +0.035 |
resa | +0.035 |
Neg logit contributions | |
down | -0.026 |
his | -0.024 |
ged | -0.024 |
, | -0.023 |
iked | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
leaf | +0.128 |
virtue | +0.125 |
vous | +0.120 |
Yes | +0.120 |
importance | +0.117 |
Neg logit contributions | |
, | -0.111 |
ged | -0.110 |
down | -0.108 |
iked | -0.103 |
leys | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
Yes | +0.020 |
ever | +0.020 |
vous | +0.020 |
rig | +0.019 |
years | +0.019 |
Neg logit contributions | |
ged | -0.012 |
iked | -0.012 |
leys | -0.012 |
ashore | -0.011 |
down | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
iked | +0.301 |
am | +0.260 |
ged | +0.259 |
leys | +0.257 |
onward | +0.252 |
Neg logit contributions | |
Yes | -0.292 |
vous | -0.287 |
matter | -0.266 |
importance | -0.264 |
child | -0.262 |
Token | little |
Token ID | 1310 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
virtue | +0.111 |
vous | +0.106 |
rig | +0.103 |
importance | +0.102 |
leaf | +0.100 |
Neg logit contributions | |
down | -0.133 |
ged | -0.132 |
iked | -0.124 |
, | -0.122 |
ls | -0.121 |
Token | girl |
Token ID | 2576 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
virtue | +0.165 |
vous | +0.162 |
rig | +0.160 |
importance | +0.156 |
Yes | +0.151 |
Neg logit contributions | |
down | -0.243 |
ged | -0.243 |
iked | -0.236 |
onward | -0.225 |
ls | -0.221 |
Token | named |
Token ID | 3706 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
vous | +0.154 |
virtue | +0.149 |
Yes | +0.145 |
rig | +0.144 |
importance | +0.140 |
Neg logit contributions | |
ged | -0.260 |
iked | -0.258 |
down | -0.257 |
onward | -0.247 |
leys | -0.240 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
vous | +0.127 |
virtue | +0.126 |
Yes | +0.123 |
rig | +0.123 |
importance | +0.121 |
Neg logit contributions | |
ged | -0.116 |
iked | -0.113 |
down | -0.111 |
onward | -0.106 |
leys | -0.102 |
Token | demanded |
Token ID | 12284 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
down | +0.136 |
ged | +0.135 |
iked | +0.124 |
, | +0.122 |
am | +0.121 |
Neg logit contributions | |
virtue | -0.173 |
vous | -0.158 |
rig | -0.157 |
importance | -0.156 |
leaf | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
ged | +0.056 |
down | +0.055 |
iked | +0.054 |
onward | +0.050 |
ls | +0.047 |
Neg logit contributions | |
vous | -0.094 |
virtue | -0.094 |
rig | -0.092 |
importance | -0.090 |
Yes | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
vous | +0.000 |
virtue | +0.000 |
rig | +0.000 |
importance | +0.000 |
Yes | +0.000 |
Neg logit contributions | |
ged | -0.000 |
down | -0.000 |
iked | -0.000 |
onward | -0.000 |
ls | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Yes | +0.037 |
rig | +0.037 |
vous | +0.036 |
virtue | +0.036 |
importance | +0.035 |
Neg logit contributions | |
ged | -0.038 |
down | -0.038 |
iked | -0.038 |
onward | -0.035 |
leys | -0.034 |
Token | Finally |
Token ID | 11158 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
virtue | +0.035 |
vous | +0.035 |
rig | +0.035 |
importance | +0.034 |
Yes | +0.034 |
Neg logit contributions | |
ged | -0.040 |
down | -0.040 |
iked | -0.040 |
onward | -0.038 |
leys | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +9.26e+00 |
Pos logit contributions | |
Yes | +0.074 |
virtue | +0.071 |
years | +0.071 |
matter | +0.071 |
importance | +0.071 |
Neg logit contributions | |
leys | -0.028 |
ged | -0.028 |
iked | -0.027 |
down | -0.025 |
am | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
down | +0.251 |
ged | +0.228 |
onward | +0.220 |
, | +0.218 |
iked | +0.209 |
Neg logit contributions | |
vous | -0.356 |
rig | -0.346 |
virtue | -0.344 |
importance | -0.327 |
leaf | -0.321 |
Token | door |
Token ID | 3420 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
down | +0.004 |
iked | +0.004 |
, | +0.004 |
castles | +0.004 |
am | +0.004 |
Neg logit contributions | |
virtue | -0.008 |
rig | -0.007 |
leaf | -0.007 |
vous | -0.007 |
Yes | -0.007 |
Token | opened |
Token ID | 4721 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
ged | +0.004 |
iked | +0.004 |
down | +0.004 |
onward | +0.004 |
leys | +0.004 |
Neg logit contributions | |
vous | -0.005 |
virtue | -0.005 |
Yes | -0.005 |
rig | -0.005 |
importance | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
iked | +0.234 |
ged | +0.232 |
leys | +0.217 |
am | +0.206 |
onward | +0.203 |
Neg logit contributions | |
Yes | -0.186 |
importance | -0.181 |
virtue | -0.179 |
rig | -0.176 |
matter | -0.175 |
Token | an |
Token ID | 281 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
virtue | +0.150 |
rig | +0.150 |
vous | +0.150 |
importance | +0.141 |
leaf | +0.136 |
Neg logit contributions | |
down | -0.121 |
ged | -0.111 |
iked | -0.105 |
onward | -0.103 |
ls | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
ged | +0.076 |
iked | +0.075 |
down | +0.072 |
onward | +0.068 |
leys | +0.066 |
Neg logit contributions | |
virtue | -0.115 |
vous | -0.114 |
rig | -0.113 |
Yes | -0.113 |
importance | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ged | +0.002 |
iked | +0.001 |
down | +0.001 |
ls | +0.001 |
leys | +0.001 |
Neg logit contributions | |
Yes | -0.002 |
virtue | -0.002 |
rig | -0.002 |
importance | -0.002 |
vous | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
rig | +0.034 |
Yes | +0.034 |
virtue | +0.034 |
vous | +0.034 |
importance | +0.033 |
Neg logit contributions | |
ged | -0.038 |
iked | -0.038 |
down | -0.038 |
onward | -0.035 |
leys | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Yes | +0.036 |
virtue | +0.034 |
rig | +0.033 |
vous | +0.033 |
importance | +0.032 |
Neg logit contributions | |
down | -0.038 |
iked | -0.037 |
ged | -0.036 |
onward | -0.035 |
am | -0.034 |
Token | Ring |
Token ID | 39687 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
rig | +0.020 |
virtue | +0.019 |
years | +0.017 |
illa | +0.017 |
vous | +0.017 |
Neg logit contributions | |
ged | -0.012 |
down | -0.010 |
His | -0.010 |
onward | -0.010 |
valleys | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
virtue | +0.222 |
rig | +0.222 |
vous | +0.221 |
importance | +0.217 |
Yes | +0.214 |
Neg logit contributions | |
ged | -0.074 |
down | -0.073 |
iked | -0.062 |
onward | -0.057 |
, | -0.057 |
Token | ring |
Token ID | 5858 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
down | +0.252 |
ged | +0.241 |
iked | +0.217 |
onward | +0.217 |
, | +0.217 |
Neg logit contributions | |
virtue | -0.323 |
rig | -0.313 |
vous | -0.313 |
importance | -0.296 |
Yes | -0.286 |
Token | , |
Token ID | 11 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
down | +0.070 |
ged | +0.066 |
iked | +0.063 |
onward | +0.061 |
, | +0.060 |
Neg logit contributions | |
virtue | -0.090 |
vous | -0.090 |
rig | -0.088 |
importance | -0.087 |
Yes | -0.085 |
Token | ring |
Token ID | 5858 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
down | +0.246 |
ged | +0.234 |
, | +0.215 |
onward | +0.212 |
iked | +0.210 |
Neg logit contributions | |
virtue | -0.334 |
vous | -0.320 |
rig | -0.319 |
importance | -0.302 |
leaf | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +9.21e+00 |
Pos logit contributions | |
down | +0.073 |
ged | +0.070 |
iked | +0.066 |
onward | +0.064 |
ls | +0.063 |
Neg logit contributions | |
vous | -0.087 |
virtue | -0.087 |
rig | -0.085 |
importance | -0.084 |
Yes | -0.081 |
Token | we |
Token ID | 356 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
down | +0.248 |
ged | +0.232 |
, | +0.218 |
onward | +0.212 |
iked | +0.212 |
Neg logit contributions | |
virtue | -0.335 |
vous | -0.325 |
rig | -0.320 |
importance | -0.303 |
resa | -0.291 |
Token | and |
Token ID | 290 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
virtue | +0.062 |
leaf | +0.062 |
rig | +0.060 |
Yes | +0.060 |
vous | +0.059 |
Neg logit contributions | |
down | -0.040 |
ged | -0.040 |
, | -0.039 |
am | -0.038 |
ls | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
virtue | +0.167 |
rig | +0.166 |
vous | +0.164 |
importance | +0.158 |
leaf | +0.157 |
Neg logit contributions | |
down | -0.085 |
ged | -0.083 |
iked | -0.078 |
onward | -0.071 |
am | -0.068 |
Token | dad |
Token ID | 9955 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
down | +0.150 |
, | +0.139 |
ged | +0.135 |
ls | +0.126 |
his | +0.125 |
Neg logit contributions | |
vous | -0.263 |
rig | -0.260 |
virtue | -0.254 |
deserve | -0.246 |
leaf | -0.245 |
Token | lost |
Token ID | 2626 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
virtue | +0.157 |
rig | +0.155 |
vous | +0.154 |
importance | +0.149 |
Yes | +0.147 |
Neg logit contributions | |
ged | -0.116 |
down | -0.115 |
iked | -0.107 |
onward | -0.102 |
am | -0.098 |
Token | everything |
Token ID | 2279 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
down | +0.043 |
ged | +0.040 |
iked | +0.037 |
onward | +0.035 |
ls | +0.032 |
Neg logit contributions | |
vous | -0.098 |
virtue | -0.097 |
rig | -0.097 |
Yes | -0.094 |
importance | -0.093 |
Token | , |
Token ID | 11 |
Feature activation | +9.72e+00 |
Pos logit contributions | |
virtue | +0.021 |
vous | +0.021 |
rig | +0.021 |
Yes | +0.021 |
importance | +0.021 |
Neg logit contributions | |
ged | -0.014 |
iked | -0.014 |
down | -0.014 |
onward | -0.013 |
leys | -0.012 |
Token | including |
Token ID | 1390 |
Feature activation | -8.67e-01 |
Pos logit contributions | |
down | +0.288 |
his | +0.253 |
ged | +0.241 |
, | +0.237 |
he | +0.234 |
Neg logit contributions | |
virtue | -0.372 |
vous | -0.361 |
rig | -0.355 |
leaf | -0.347 |
resa | -0.344 |
Token | their |
Token ID | 511 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
vous | +0.032 |
virtue | +0.032 |
rig | +0.032 |
Yes | +0.031 |
importance | +0.031 |
Neg logit contributions | |
down | -0.020 |
ged | -0.019 |
iked | -0.019 |
onward | -0.017 |
am | -0.017 |
Token | golf |
Token ID | 13126 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
down | +0.181 |
, | +0.167 |
ged | +0.155 |
castles | +0.149 |
sand | +0.147 |
Neg logit contributions | |
vous | -0.228 |
rig | -0.223 |
resa | -0.216 |
virtue | -0.215 |
Yes | -0.214 |
Token | clubs |
Token ID | 9784 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
down | +0.147 |
ged | +0.147 |
iked | +0.142 |
onward | +0.132 |
am | +0.130 |
Neg logit contributions | |
virtue | -0.190 |
vous | -0.190 |
rig | -0.189 |
Yes | -0.183 |
importance | -0.181 |
Token | . |
Token ID | 13 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
virtue | +0.010 |
vous | +0.010 |
rig | +0.010 |
Yes | +0.010 |
importance | +0.010 |
Neg logit contributions | |
down | -0.009 |
ged | -0.009 |
iked | -0.008 |
onward | -0.008 |
ls | -0.007 |
Token | played |
Token ID | 2826 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
his | +0.132 |
, | +0.125 |
he | +0.124 |
ged | +0.107 |
am | +0.107 |
Neg logit contributions | |
virtue | -0.255 |
rig | -0.253 |
vous | -0.245 |
leaf | -0.240 |
resa | -0.236 |
Token | with |
Token ID | 351 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
down | +0.122 |
ged | +0.120 |
iked | +0.114 |
onward | +0.110 |
ls | +0.103 |
Neg logit contributions | |
vous | -0.146 |
virtue | -0.145 |
rig | -0.143 |
importance | -0.137 |
Yes | -0.137 |
Token | his |
Token ID | 465 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
rig | +0.083 |
virtue | +0.083 |
vous | +0.081 |
importance | +0.080 |
Yes | +0.078 |
Neg logit contributions | |
down | -0.008 |
his | -0.006 |
ged | -0.006 |
, | -0.002 |
ls | -0.002 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
down | +0.130 |
, | +0.121 |
his | +0.111 |
ged | +0.108 |
ls | +0.106 |
Neg logit contributions | |
vous | -0.320 |
virtue | -0.306 |
rig | -0.303 |
leaf | -0.300 |
deserve | -0.288 |
Token | again |
Token ID | 757 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
virtue | +0.080 |
vous | +0.080 |
rig | +0.079 |
importance | +0.078 |
leaf | +0.077 |
Neg logit contributions | |
down | -0.055 |
ged | -0.050 |
, | -0.049 |
onward | -0.045 |
iked | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +9.84e+00 |
Pos logit contributions | |
down | +0.073 |
ged | +0.067 |
, | +0.065 |
onward | +0.062 |
iked | +0.061 |
Neg logit contributions | |
vous | -0.127 |
rig | -0.126 |
virtue | -0.125 |
leaf | -0.124 |
importance | -0.120 |
Token | but |
Token ID | 475 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
down | +0.286 |
ged | +0.250 |
his | +0.244 |
, | +0.231 |
he | +0.224 |
Neg logit contributions | |
vous | -0.378 |
virtue | -0.378 |
rig | -0.366 |
leaf | -0.352 |
importance | -0.326 |
Token | he |
Token ID | 339 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
rig | +0.239 |
vous | +0.239 |
virtue | +0.235 |
leaf | +0.228 |
Yes | +0.227 |
Neg logit contributions | |
down | -0.082 |
ged | -0.081 |
iked | -0.073 |
onward | -0.070 |
ls | -0.061 |
Token | kept |
Token ID | 4030 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
he | +0.171 |
, | +0.169 |
his | +0.168 |
ged | +0.164 |
am | +0.146 |
Neg logit contributions | |
leaf | -0.332 |
rig | -0.327 |
virtue | -0.294 |
meaning | -0.287 |
Yes | -0.285 |
Token | them |
Token ID | 606 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
down | +0.069 |
ged | +0.068 |
iked | +0.064 |
onward | +0.061 |
am | +0.057 |
Neg logit contributions | |
vous | -0.100 |
virtue | -0.099 |
rig | -0.099 |
Yes | -0.095 |
importance | -0.095 |
Token | clean |
Token ID | 3424 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
ged | +0.138 |
iked | +0.136 |
down | +0.128 |
onward | +0.127 |
leys | +0.123 |
Neg logit contributions | |
virtue | -0.133 |
rig | -0.131 |
vous | -0.129 |
Yes | -0.127 |
importance | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ged | +0.123 |
down | +0.120 |
iked | +0.120 |
onward | +0.112 |
leys | +0.107 |
Neg logit contributions | |
virtue | -0.139 |
vous | -0.139 |
rig | -0.137 |
Yes | -0.135 |
importance | -0.133 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
virtue | +0.050 |
vous | +0.049 |
importance | +0.048 |
rig | +0.047 |
leaf | +0.046 |
Neg logit contributions | |
down | -0.030 |
ged | -0.030 |
iked | -0.029 |
onward | -0.028 |
ls | -0.026 |
Token | Then |
Token ID | 6423 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
virtue | +0.037 |
vous | +0.037 |
leaf | +0.037 |
rig | +0.036 |
importance | +0.035 |
Neg logit contributions | |
down | -0.043 |
ged | -0.043 |
iked | -0.041 |
onward | -0.040 |
leys | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +9.11e+00 |
Pos logit contributions | |
iked | +0.012 |
ashore | +0.012 |
leys | +0.012 |
ged | +0.011 |
am | +0.011 |
Neg logit contributions | |
Yes | -0.025 |
matter | -0.025 |
bit | -0.024 |
years | -0.023 |
child | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
down | +0.214 |
ged | +0.208 |
iked | +0.191 |
onward | +0.182 |
, | +0.177 |
Neg logit contributions | |
rig | -0.354 |
vous | -0.352 |
virtue | -0.352 |
importance | -0.334 |
leaf | -0.331 |
Token | got |
Token ID | 1392 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
vous | +0.043 |
rig | +0.041 |
importance | +0.040 |
Yes | +0.039 |
virtue | +0.039 |
Neg logit contributions | |
ged | -0.050 |
iked | -0.049 |
down | -0.048 |
onward | -0.047 |
ls | -0.044 |
Token | lost |
Token ID | 2626 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
down | +0.118 |
ged | +0.113 |
iked | +0.110 |
onward | +0.106 |
am | +0.102 |
Neg logit contributions | |
virtue | -0.108 |
rig | -0.106 |
vous | -0.106 |
importance | -0.102 |
Yes | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
down | +0.038 |
ged | +0.036 |
iked | +0.034 |
onward | +0.032 |
, | +0.031 |
Neg logit contributions | |
vous | -0.052 |
virtue | -0.051 |
rig | -0.051 |
Yes | -0.049 |
leaf | -0.049 |
Token | started |
Token ID | 2067 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
virtue | +0.152 |
rig | +0.149 |
vous | +0.148 |
importance | +0.143 |
leaf | +0.142 |
Neg logit contributions | |
down | -0.125 |
ged | -0.121 |
iked | -0.116 |
onward | -0.110 |
am | -0.107 |
Token | to |
Token ID | 284 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ged | +0.131 |
iked | +0.128 |
down | +0.125 |
onward | +0.122 |
leys | +0.120 |
Neg logit contributions | |
vous | -0.133 |
virtue | -0.132 |
importance | -0.130 |
rig | -0.130 |
Yes | -0.129 |
Token | cry |
Token ID | 3960 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
virtue | +0.053 |
vous | +0.053 |
rig | +0.051 |
Yes | +0.050 |
importance | +0.050 |
Neg logit contributions | |
ged | -0.094 |
down | -0.093 |
iked | -0.093 |
onward | -0.088 |
leys | -0.086 |
Token | J |
Token ID | 41 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
vous | +0.029 |
virtue | +0.028 |
rig | +0.028 |
importance | +0.027 |
matter | +0.026 |
Neg logit contributions | |
ged | -0.022 |
down | -0.021 |
iked | -0.021 |
onward | -0.021 |
leys | -0.020 |
Token | enny |
Token ID | 11870 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
virtue | +0.036 |
vous | +0.035 |
Yes | +0.035 |
importance | +0.034 |
matter | +0.034 |
Neg logit contributions | |
ged | -0.026 |
iked | -0.025 |
down | -0.025 |
leys | -0.024 |
am | -0.023 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
vous | +0.111 |
virtue | +0.111 |
rig | +0.105 |
Yes | +0.104 |
matter | +0.103 |
Neg logit contributions | |
, | -0.076 |
down | -0.073 |
ged | -0.072 |
am | -0.072 |
iked | -0.066 |
Token | for |
Token ID | 329 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
vous | +0.047 |
virtue | +0.046 |
Yes | +0.045 |
rig | +0.045 |
importance | +0.043 |
Neg logit contributions | |
down | -0.030 |
ged | -0.030 |
iked | -0.028 |
onward | -0.027 |
, | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
rig | +0.162 |
virtue | +0.153 |
vous | +0.148 |
acco | +0.145 |
arant | +0.142 |
Neg logit contributions | |
, | -0.071 |
his | -0.069 |
down | -0.060 |
he | -0.052 |
out | -0.050 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
vous | +0.141 |
rig | +0.135 |
virtue | +0.135 |
leaf | +0.133 |
least | +0.131 |
Neg logit contributions | |
down | -0.093 |
ged | -0.093 |
, | -0.088 |
onward | -0.083 |
inspection | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
down | +0.030 |
ged | +0.029 |
, | +0.029 |
iked | +0.027 |
onward | +0.027 |
Neg logit contributions | |
vous | -0.055 |
virtue | -0.055 |
rig | -0.055 |
leaf | -0.052 |
importance | -0.051 |
Token | said |
Token ID | 531 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
virtue | +0.110 |
vous | +0.110 |
rig | +0.108 |
importance | +0.103 |
Yes | +0.100 |
Neg logit contributions | |
ged | -0.130 |
down | -0.129 |
iked | -0.125 |
onward | -0.118 |
am | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | +9.66e+00 |
Pos logit contributions | |
leys | +0.065 |
ged | +0.064 |
iked | +0.062 |
ashore | +0.058 |
ls | +0.058 |
Neg logit contributions | |
virtue | -0.142 |
Yes | -0.141 |
importance | -0.136 |
meaning | -0.134 |
song | -0.134 |
Token | " |
Token ID | 366 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ged | +0.199 |
iked | +0.196 |
down | +0.188 |
ls | +0.182 |
leys | +0.178 |
Neg logit contributions | |
Yes | -0.366 |
virtue | -0.362 |
importance | -0.358 |
vous | -0.353 |
rig | -0.352 |
Token | I |
Token ID | 40 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
rig | +0.017 |
mistake | +0.016 |
virtue | +0.016 |
vous | +0.015 |
least | +0.015 |
Neg logit contributions | |
ged | -0.018 |
down | -0.018 |
onward | -0.018 |
His | -0.017 |
iked | -0.016 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
down | +0.240 |
ged | +0.218 |
, | +0.208 |
iked | +0.206 |
onward | +0.204 |
Neg logit contributions | |
rig | -0.346 |
vous | -0.342 |
virtue | -0.341 |
importance | -0.323 |
leaf | -0.322 |
Token | , |
Token ID | 11 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
vous | +0.047 |
virtue | +0.045 |
importance | +0.045 |
Yes | +0.044 |
child | +0.043 |
Neg logit contributions | |
iked | -0.020 |
ged | -0.019 |
onward | -0.017 |
leys | -0.016 |
down | -0.015 |
Token | I |
Token ID | 314 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
down | +0.289 |
, | +0.259 |
ged | +0.258 |
his | +0.243 |
iked | +0.241 |
Neg logit contributions | |
rig | -0.317 |
vous | -0.307 |
virtue | -0.307 |
importance | -0.284 |
leaf | -0.272 |
Token | found |
Token ID | 1043 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
rig | +0.180 |
virtue | +0.176 |
leaf | +0.172 |
resa | +0.172 |
song | +0.163 |
Neg logit contributions | |
ged | -0.128 |
down | -0.124 |
, | -0.123 |
am | -0.115 |
ed | -0.104 |
Token | your |
Token ID | 534 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
ged | +0.163 |
down | +0.162 |
iked | +0.160 |
onward | +0.151 |
leys | +0.146 |
Neg logit contributions | |
virtue | -0.156 |
vous | -0.156 |
rig | -0.153 |
Yes | -0.150 |
importance | -0.149 |
Token | car |
Token ID | 1097 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
down | +0.107 |
ged | +0.096 |
, | +0.089 |
iked | +0.087 |
ls | +0.085 |
Neg logit contributions | |
vous | -0.175 |
rig | -0.172 |
virtue | -0.169 |
Yes | -0.166 |
leaf | -0.166 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
down | +0.066 |
ged | +0.064 |
iked | +0.061 |
onward | +0.059 |
am | +0.058 |
Neg logit contributions | |
virtue | -0.054 |
vous | -0.054 |
rig | -0.054 |
importance | -0.052 |
Yes | -0.052 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Yes | +0.109 |
vous | +0.104 |
rig | +0.103 |
virtue | +0.100 |
importance | +0.099 |
Neg logit contributions | |
iked | -0.129 |
ged | -0.126 |
down | -0.120 |
onward | -0.120 |
leys | -0.118 |
Token | says |
Token ID | 1139 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
down | +0.051 |
ged | +0.050 |
iked | +0.049 |
onward | +0.046 |
am | +0.045 |
Neg logit contributions | |
virtue | -0.051 |
vous | -0.050 |
rig | -0.049 |
importance | -0.048 |
Yes | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
leys | +0.128 |
iked | +0.126 |
valleys | +0.118 |
onward | +0.117 |
ged | +0.117 |
Neg logit contributions | |
Yes | -0.077 |
song | -0.072 |
bit | -0.071 |
rig | -0.069 |
ever | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | +5.60e+00 |
Pos logit contributions | |
iked | +0.012 |
ged | +0.011 |
leys | +0.011 |
onward | +0.010 |
am | +0.010 |
Neg logit contributions | |
Yes | -0.017 |
vous | -0.016 |
importance | -0.016 |
virtue | -0.016 |
rig | -0.016 |
Token | ?" |
Token ID | 1701 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
virtue | +0.056 |
vous | +0.055 |
rig | +0.054 |
importance | +0.053 |
Yes | +0.053 |
Neg logit contributions | |
down | -0.055 |
ged | -0.053 |
iked | -0.051 |
onward | -0.049 |
am | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
virtue | +0.134 |
vous | +0.134 |
rig | +0.132 |
Yes | +0.129 |
importance | +0.129 |
Neg logit contributions | |
ged | -0.106 |
down | -0.105 |
iked | -0.104 |
onward | -0.097 |
leys | -0.093 |
Token |
|
Token ID | 198 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
Yes | +0.025 |
rig | +0.025 |
virtue | +0.025 |
vous | +0.025 |
importance | +0.024 |
Neg logit contributions | |
ged | -0.027 |
down | -0.027 |
iked | -0.026 |
onward | -0.024 |
leys | -0.024 |
Token | N |
Token ID | 45 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
vous | +0.020 |
Yes | +0.020 |
virtue | +0.020 |
rig | +0.020 |
importance | +0.019 |
Neg logit contributions | |
ged | -0.032 |
down | -0.032 |
iked | -0.031 |
ls | -0.029 |
onward | -0.029 |
Token | ana |
Token ID | 2271 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ged | +0.042 |
down | +0.041 |
iked | +0.041 |
onward | +0.039 |
ls | +0.038 |
Neg logit contributions | |
virtue | -0.027 |
vous | -0.027 |
rig | -0.027 |
importance | -0.026 |
Yes | -0.025 |
Token | smiled |
Token ID | 13541 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
virtue | +0.064 |
vous | +0.063 |
rig | +0.061 |
importance | +0.059 |
Yes | +0.059 |
Neg logit contributions | |
down | -0.050 |
ged | -0.050 |
iked | -0.048 |
am | -0.045 |
, | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
iked | +0.162 |
ged | +0.158 |
drivers | +0.157 |
igs | +0.155 |
leys | +0.155 |
Neg logit contributions | |
Yes | -0.041 |
elderly | -0.039 |
child | -0.039 |
rig | -0.036 |
rather | -0.034 |
Token | pointed |
Token ID | 6235 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
Yes | +0.085 |
rig | +0.081 |
vous | +0.081 |
virtue | +0.080 |
importance | +0.078 |
Neg logit contributions | |
iked | -0.143 |
ged | -0.142 |
down | -0.138 |
onward | -0.137 |
leys | -0.133 |
Token | to |
Token ID | 284 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
iked | +0.268 |
ged | +0.263 |
leys | +0.253 |
ooming | +0.239 |
onward | +0.237 |
Neg logit contributions | |
Yes | -0.255 |
leaf | -0.240 |
child | -0.232 |
meaning | -0.229 |
rig | -0.229 |
Token | an |
Token ID | 281 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
virtue | +0.070 |
vous | +0.069 |
rig | +0.068 |
importance | +0.065 |
Yes | +0.064 |
Neg logit contributions | |
down | -0.041 |
ged | -0.040 |
iked | -0.039 |
onward | -0.036 |
, | -0.033 |
Token | old |
Token ID | 1468 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
virtue | +0.120 |
Yes | +0.116 |
rig | +0.115 |
vous | +0.114 |
importance | +0.112 |
Neg logit contributions | |
down | -0.112 |
ged | -0.104 |
iked | -0.099 |
, | -0.097 |
onward | -0.096 |
Token | We |
Token ID | 775 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
down | +0.008 |
iked | +0.007 |
onward | +0.007 |
ged | +0.007 |
, | +0.007 |
Neg logit contributions | |
virtue | -0.010 |
vous | -0.010 |
rig | -0.010 |
importance | -0.010 |
matter | -0.010 |
Token | have |
Token ID | 423 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
rig | +0.195 |
vous | +0.187 |
virtue | +0.186 |
resa | +0.185 |
Yes | +0.176 |
Neg logit contributions | |
down | -0.171 |
, | -0.161 |
ged | -0.160 |
am | -0.148 |
onward | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
rig | +0.143 |
vous | +0.133 |
virtue | +0.132 |
Yes | +0.125 |
resa | +0.125 |
Neg logit contributions | |
down | -0.069 |
, | -0.064 |
am | -0.062 |
his | -0.061 |
iked | -0.059 |
Token | pray |
Token ID | 12472 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
vous | +0.076 |
rig | +0.074 |
virtue | +0.073 |
leaf | +0.072 |
importance | +0.070 |
Neg logit contributions | |
down | -0.053 |
, | -0.053 |
his | -0.047 |
am | -0.046 |
ashore | -0.045 |
Token | for |
Token ID | 329 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
down | +0.052 |
, | +0.047 |
ged | +0.043 |
onward | +0.042 |
iked | +0.041 |
Neg logit contributions | |
vous | -0.087 |
virtue | -0.080 |
rig | -0.080 |
importance | -0.079 |
leaf | -0.078 |
Token | them |
Token ID | 606 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
rig | +0.145 |
vous | +0.141 |
virtue | +0.136 |
importance | +0.129 |
Yes | +0.127 |
Neg logit contributions | |
down | -0.094 |
, | -0.088 |
ged | -0.086 |
his | -0.085 |
them | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
down | +0.093 |
ged | +0.082 |
iked | +0.081 |
, | +0.080 |
onward | +0.079 |
Neg logit contributions | |
vous | -0.165 |
virtue | -0.160 |
rig | -0.159 |
Yes | -0.156 |
leaf | -0.154 |
Token | the |
Token ID | 262 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
vous | +0.142 |
rig | +0.135 |
virtue | +0.131 |
importance | +0.122 |
leaf | +0.120 |
Neg logit contributions | |
down | -0.130 |
, | -0.116 |
his | -0.113 |
iked | -0.106 |
ged | -0.106 |
Token | people |
Token ID | 661 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
down | +0.011 |
iked | +0.009 |
, | +0.009 |
onward | +0.009 |
ged | +0.009 |
Neg logit contributions | |
rig | -0.016 |
vous | -0.015 |
virtue | -0.015 |
Yes | -0.015 |
leaf | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
virtue | +0.205 |
vous | +0.203 |
rig | +0.201 |
importance | +0.196 |
Yes | +0.193 |
Neg logit contributions | |
down | -0.174 |
ged | -0.164 |
iked | -0.154 |
onward | -0.153 |
, | -0.149 |
Token | the |
Token ID | 262 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
, | +0.020 |
down | +0.019 |
his | +0.019 |
their | +0.018 |
onward | +0.017 |
Neg logit contributions | |
rig | -0.033 |
vous | -0.031 |
leaf | -0.031 |
virtue | -0.031 |
resa | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
down | +0.011 |
ged | +0.011 |
iked | +0.010 |
onward | +0.009 |
ls | +0.009 |
Neg logit contributions | |
vous | -0.016 |
rig | -0.016 |
virtue | -0.016 |
importance | -0.016 |
Yes | -0.016 |
Token | off |
Token ID | 572 |
Feature activation | +5.27e+00 |
Pos logit contributions | |
down | +0.033 |
ged | +0.032 |
iked | +0.031 |
onward | +0.029 |
ls | +0.028 |
Neg logit contributions | |
vous | -0.045 |
virtue | -0.045 |
rig | -0.045 |
Yes | -0.044 |
importance | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
down | +0.127 |
ged | +0.115 |
iked | +0.108 |
onward | +0.107 |
, | +0.105 |
Neg logit contributions | |
vous | -0.202 |
rig | -0.197 |
virtue | -0.197 |
Yes | -0.192 |
importance | -0.190 |
Token | but |
Token ID | 475 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
down | +0.251 |
ged | +0.224 |
onward | +0.209 |
, | +0.208 |
iked | +0.203 |
Neg logit contributions | |
vous | -0.323 |
virtue | -0.316 |
rig | -0.306 |
leaf | -0.299 |
importance | -0.295 |
Token | it |
Token ID | 340 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
vous | +0.225 |
rig | +0.224 |
virtue | +0.218 |
leaf | +0.213 |
importance | +0.212 |
Neg logit contributions | |
down | -0.125 |
ged | -0.116 |
onward | -0.109 |
iked | -0.107 |
, | -0.103 |
Token | just |
Token ID | 655 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
down | +0.066 |
am | +0.063 |
ls | +0.063 |
, | +0.062 |
ged | +0.059 |
Neg logit contributions | |
leaf | -0.086 |
Yes | -0.082 |
rig | -0.081 |
vous | -0.081 |
virtue | -0.080 |
Token | got |
Token ID | 1392 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
vous | +0.134 |
rig | +0.133 |
virtue | +0.131 |
Yes | +0.127 |
leaf | +0.124 |
Neg logit contributions | |
down | -0.137 |
ged | -0.131 |
iked | -0.121 |
onward | -0.119 |
, | -0.118 |
Token | worse |
Token ID | 4785 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
iked | +0.145 |
ged | +0.143 |
onward | +0.134 |
down | +0.133 |
leys | +0.131 |
Neg logit contributions | |
virtue | -0.095 |
vous | -0.093 |
Yes | -0.091 |
rig | -0.090 |
importance | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.003 |
down | +0.003 |
onward | +0.003 |
leys | +0.003 |
Neg logit contributions | |
virtue | -0.005 |
vous | -0.005 |
rig | -0.005 |
importance | -0.005 |
Yes | -0.005 |
Token | worse |
Token ID | 4785 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
vous | +0.129 |
rig | +0.129 |
virtue | +0.128 |
Yes | +0.123 |
leaf | +0.122 |
Neg logit contributions | |
down | -0.122 |
ged | -0.118 |
iked | -0.113 |
onward | -0.109 |
ls | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
iked | +0.004 |
ged | +0.004 |
down | +0.004 |
onward | +0.004 |
leys | +0.004 |
Neg logit contributions | |
virtue | -0.006 |
vous | -0.006 |
importance | -0.006 |
rig | -0.006 |
Yes | -0.006 |
Token | fire |
Token ID | 2046 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
down | +0.090 |
ged | +0.085 |
iked | +0.083 |
onward | +0.076 |
am | +0.074 |
Neg logit contributions | |
virtue | -0.179 |
vous | -0.178 |
rig | -0.176 |
Yes | -0.171 |
importance | -0.170 |
Token | engine |
Token ID | 3113 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
down | +0.113 |
ged | +0.105 |
iked | +0.101 |
am | +0.095 |
ls | +0.093 |
Neg logit contributions | |
virtue | -0.176 |
vous | -0.175 |
rig | -0.174 |
importance | -0.169 |
leaf | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
rig | +0.016 |
vous | +0.016 |
virtue | +0.016 |
leaf | +0.016 |
importance | +0.016 |
Neg logit contributions | |
down | -0.009 |
ged | -0.008 |
, | -0.008 |
iked | -0.007 |
am | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
down | +0.015 |
ged | +0.015 |
iked | +0.014 |
onward | +0.014 |
am | +0.013 |
Neg logit contributions | |
vous | -0.018 |
virtue | -0.018 |
rig | -0.018 |
importance | -0.018 |
matter | -0.017 |
Token | 's |
Token ID | 338 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
virtue | +0.020 |
rig | +0.020 |
vous | +0.020 |
leaf | +0.019 |
Yes | +0.019 |
Neg logit contributions | |
down | -0.017 |
ls | -0.015 |
am | -0.015 |
ged | -0.015 |
, | -0.014 |
Token | red |
Token ID | 2266 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
down | +0.042 |
his | +0.036 |
, | +0.035 |
ged | +0.033 |
out | +0.033 |
Neg logit contributions | |
vous | -0.042 |
rig | -0.041 |
virtue | -0.040 |
leaf | -0.040 |
Yes | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
ged | +0.013 |
down | +0.013 |
iked | +0.013 |
onward | +0.012 |
leys | +0.011 |
Neg logit contributions | |
virtue | -0.017 |
vous | -0.017 |
rig | -0.017 |
Yes | -0.017 |
importance | -0.017 |
Token | shiny |
Token ID | 22441 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
virtue | +0.141 |
vous | +0.141 |
rig | +0.139 |
Yes | +0.136 |
importance | +0.136 |
Neg logit contributions | |
ged | -0.100 |
down | -0.099 |
iked | -0.097 |
onward | -0.091 |
leys | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
ged | +0.057 |
down | +0.056 |
iked | +0.056 |
onward | +0.052 |
leys | +0.050 |
Neg logit contributions | |
virtue | -0.079 |
vous | -0.079 |
rig | -0.077 |
Yes | -0.076 |
importance | -0.076 |
Token | has |
Token ID | 468 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
virtue | +0.138 |
vous | +0.137 |
rig | +0.136 |
importance | +0.131 |
Yes | +0.128 |
Neg logit contributions | |
down | -0.109 |
ged | -0.102 |
onward | -0.095 |
iked | -0.095 |
ls | -0.093 |
Token | a |
Token ID | 257 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
rig | +0.050 |
vous | +0.047 |
virtue | +0.047 |
Yes | +0.045 |
importance | +0.044 |
Neg logit contributions | |
down | -0.041 |
ged | -0.038 |
iked | -0.037 |
am | -0.035 |
onward | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.002 |
down | +0.002 |
onward | +0.002 |
leys | +0.002 |
Neg logit contributions | |
virtue | -0.004 |
vous | -0.004 |
rig | -0.003 |
Yes | -0.003 |
importance | -0.003 |
Token | make |
Token ID | 787 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
down | +0.042 |
ged | +0.037 |
, | +0.035 |
onward | +0.033 |
ls | +0.033 |
Neg logit contributions | |
virtue | -0.055 |
vous | -0.055 |
rig | -0.053 |
resa | -0.052 |
importance | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
virtue | +0.109 |
vous | +0.108 |
rig | +0.104 |
Yes | +0.102 |
leaf | +0.101 |
Neg logit contributions | |
down | -0.087 |
ged | -0.082 |
iked | -0.077 |
am | -0.075 |
onward | -0.073 |
Token | loud |
Token ID | 7812 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
vous | +0.148 |
leaf | +0.141 |
virtue | +0.140 |
rig | +0.138 |
importance | +0.135 |
Neg logit contributions | |
down | -0.122 |
ged | -0.110 |
ls | -0.107 |
iked | -0.102 |
, | -0.102 |
Token | noise |
Token ID | 7838 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
virtue | +0.089 |
vous | +0.088 |
rig | +0.085 |
Yes | +0.083 |
importance | +0.082 |
Neg logit contributions | |
ged | -0.158 |
down | -0.158 |
iked | -0.154 |
onward | -0.147 |
ls | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
vous | +0.084 |
virtue | +0.083 |
rig | +0.082 |
Yes | +0.081 |
importance | +0.080 |
Neg logit contributions | |
ged | -0.057 |
iked | -0.057 |
down | -0.056 |
onward | -0.052 |
leys | -0.050 |
Token | They |
Token ID | 1119 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ged | +0.001 |
iked | +0.001 |
down | +0.001 |
onward | +0.001 |
leys | +0.001 |
Neg logit contributions | |
virtue | -0.002 |
Yes | -0.002 |
vous | -0.002 |
rig | -0.002 |
importance | -0.002 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
down | +0.039 |
ged | +0.034 |
, | +0.033 |
ls | +0.031 |
onward | +0.030 |
Neg logit contributions | |
virtue | -0.054 |
vous | -0.054 |
rig | -0.052 |
importance | -0.050 |
resa | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
down | +0.042 |
ged | +0.039 |
onward | +0.033 |
, | +0.032 |
his | +0.032 |
Neg logit contributions | |
vous | -0.071 |
virtue | -0.071 |
rig | -0.070 |
importance | -0.067 |
leaf | -0.067 |
Token | floor |
Token ID | 4314 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
down | +0.008 |
, | +0.007 |
castles | +0.007 |
ged | +0.006 |
towers | +0.006 |
Neg logit contributions | |
rig | -0.013 |
virtue | -0.013 |
Yes | -0.013 |
leaf | -0.013 |
vous | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
virtue | +0.063 |
vous | +0.062 |
rig | +0.062 |
Yes | +0.061 |
importance | +0.061 |
Neg logit contributions | |
ged | -0.061 |
iked | -0.061 |
down | -0.059 |
onward | -0.057 |
leys | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +9.54e+00 |
Pos logit contributions | |
Yes | +0.070 |
rig | +0.069 |
least | +0.069 |
years | +0.068 |
vous | +0.067 |
Neg logit contributions | |
ged | -0.083 |
iked | -0.080 |
leys | -0.075 |
onward | -0.072 |
am | -0.070 |
Token | the |
Token ID | 262 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
down | +0.253 |
his | +0.232 |
, | +0.218 |
he | +0.212 |
castles | +0.208 |
Neg logit contributions | |
virtue | -0.418 |
vous | -0.374 |
rig | -0.346 |
importance | -0.337 |
leaf | -0.330 |
Token | birds |
Token ID | 10087 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
down | +0.010 |
castles | +0.009 |
sand | +0.008 |
ls | +0.008 |
ged | +0.008 |
Neg logit contributions | |
virtue | -0.017 |
vous | -0.017 |
rig | -0.016 |
leaf | -0.015 |
illa | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Yes | +0.189 |
song | +0.186 |
rig | +0.183 |
least | +0.182 |
vous | +0.182 |
Neg logit contributions | |
iked | -0.152 |
leys | -0.143 |
ged | -0.140 |
onward | -0.137 |
am | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
virtue | +0.153 |
vous | +0.147 |
rig | +0.147 |
importance | +0.139 |
Yes | +0.134 |
Neg logit contributions | |
down | -0.100 |
ged | -0.092 |
iked | -0.086 |
onward | -0.082 |
ls | -0.080 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
down | +0.010 |
ged | +0.008 |
castles | +0.008 |
ls | +0.008 |
, | +0.007 |
Neg logit contributions | |
virtue | -0.015 |
vous | -0.015 |
rig | -0.015 |
leaf | -0.014 |
matter | -0.013 |
Token | s |
Token ID | 82 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
rig | +0.129 |
Yes | +0.128 |
vous | +0.127 |
years | +0.123 |
song | +0.122 |
Neg logit contributions | |
ged | -0.064 |
iked | -0.064 |
onward | -0.060 |
down | -0.057 |
leys | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ged | +0.093 |
iked | +0.092 |
down | +0.089 |
onward | +0.087 |
leys | +0.084 |
Neg logit contributions | |
importance | -0.127 |
vous | -0.127 |
virtue | -0.126 |
Yes | -0.126 |
rig | -0.125 |
Token | He |
Token ID | 679 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
ged | +0.013 |
iked | +0.012 |
down | +0.011 |
leys | +0.011 |
ls | +0.011 |
Neg logit contributions | |
Yes | -0.012 |
rig | -0.011 |
importance | -0.011 |
virtue | -0.011 |
vous | -0.010 |
Token | ran |
Token ID | 4966 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
down | +0.174 |
ged | +0.171 |
am | +0.168 |
, | +0.164 |
iked | +0.163 |
Neg logit contributions | |
virtue | -0.183 |
vous | -0.176 |
rig | -0.170 |
leaf | -0.161 |
Yes | -0.160 |
Token | ahead |
Token ID | 4058 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
ged | +0.179 |
iked | +0.177 |
leys | +0.171 |
onward | +0.164 |
am | +0.164 |
Neg logit contributions | |
Yes | -0.194 |
rig | -0.188 |
vous | -0.186 |
virtue | -0.185 |
leaf | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
rig | +0.090 |
virtue | +0.087 |
vous | +0.084 |
Yes | +0.082 |
leaf | +0.080 |
Neg logit contributions | |
down | -0.063 |
ged | -0.060 |
iked | -0.059 |
onward | -0.055 |
, | -0.054 |
Token | y |
Token ID | 331 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
vous | +0.143 |
rig | +0.139 |
virtue | +0.139 |
leaf | +0.136 |
Yes | +0.134 |
Neg logit contributions | |
down | -0.119 |
ged | -0.112 |
iked | -0.108 |
, | -0.107 |
onward | -0.105 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
virtue | +0.094 |
vous | +0.093 |
rig | +0.091 |
Yes | +0.087 |
matter | +0.085 |
Neg logit contributions | |
ged | -0.107 |
down | -0.101 |
iked | -0.098 |
onward | -0.097 |
leys | -0.097 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
virtue | +0.058 |
rig | +0.056 |
vous | +0.055 |
importance | +0.054 |
Yes | +0.054 |
Neg logit contributions | |
down | -0.047 |
ged | -0.046 |
iked | -0.044 |
, | -0.042 |
ls | -0.041 |
Token | available |
Token ID | 1695 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
down | +0.059 |
ged | +0.058 |
iked | +0.056 |
onward | +0.052 |
, | +0.050 |
Neg logit contributions | |
rig | -0.094 |
virtue | -0.094 |
vous | -0.093 |
importance | -0.090 |
Yes | -0.090 |
Token | for |
Token ID | 329 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
down | +0.144 |
iked | +0.135 |
ged | +0.135 |
onward | +0.121 |
, | +0.120 |
Neg logit contributions | |
vous | -0.262 |
rig | -0.260 |
virtue | -0.259 |
importance | -0.252 |
Yes | -0.252 |
Token | her |
Token ID | 607 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
rig | +0.162 |
virtue | +0.162 |
vous | +0.161 |
importance | +0.154 |
Yes | +0.154 |
Neg logit contributions | |
ged | -0.070 |
down | -0.069 |
iked | -0.068 |
onward | -0.061 |
ls | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
, | +0.099 |
down | +0.086 |
iked | +0.074 |
am | +0.071 |
back | +0.069 |
Neg logit contributions | |
leaf | -0.194 |
virtue | -0.189 |
rig | -0.188 |
vous | -0.186 |
Sad | -0.177 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
virtue | +0.003 |
vous | +0.003 |
Yes | +0.003 |
rig | +0.003 |
importance | +0.003 |
Neg logit contributions | |
ged | -0.003 |
iked | -0.003 |
down | -0.002 |
onward | -0.002 |
leys | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
virtue | +0.049 |
rig | +0.048 |
leaf | +0.047 |
vous | +0.047 |
Yes | +0.046 |
Neg logit contributions | |
down | -0.037 |
ged | -0.036 |
, | -0.036 |
am | -0.035 |
iked | -0.034 |
Token | very |
Token ID | 845 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
virtue | +0.102 |
rig | +0.102 |
leaf | +0.096 |
importance | +0.094 |
vous | +0.093 |
Neg logit contributions | |
down | -0.107 |
, | -0.092 |
onward | -0.091 |
ged | -0.089 |
his | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
ged | +0.003 |
down | +0.003 |
iked | +0.003 |
onward | +0.003 |
leys | +0.003 |
Neg logit contributions | |
virtue | -0.005 |
vous | -0.005 |
rig | -0.005 |
Yes | -0.005 |
importance | -0.005 |
Token | Even |
Token ID | 3412 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
down | +0.011 |
iked | +0.010 |
onward | +0.010 |
ged | +0.010 |
am | +0.008 |
Neg logit contributions | |
vous | -0.024 |
virtue | -0.023 |
matter | -0.023 |
rig | -0.023 |
importance | -0.023 |
Token | though |
Token ID | 996 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
virtue | +0.066 |
vous | +0.063 |
rig | +0.062 |
leaf | +0.061 |
importance | +0.060 |
Neg logit contributions | |
down | -0.053 |
ged | -0.046 |
, | -0.045 |
onward | -0.043 |
his | -0.042 |
Token | she |
Token ID | 673 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
vous | +0.085 |
rig | +0.084 |
virtue | +0.082 |
leaf | +0.081 |
Yes | +0.078 |
Neg logit contributions | |
down | -0.033 |
, | -0.030 |
ged | -0.030 |
onward | -0.029 |
iked | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
ged | +0.116 |
, | +0.115 |
am | +0.103 |
down | +0.098 |
ed | +0.095 |
Neg logit contributions | |
virtue | -0.219 |
rig | -0.211 |
leaf | -0.210 |
Yes | -0.207 |
Tooth | -0.206 |
Token | only |
Token ID | 691 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
virtue | +0.083 |
rig | +0.082 |
vous | +0.081 |
Yes | +0.079 |
leaf | +0.078 |
Neg logit contributions | |
down | -0.092 |
ged | -0.084 |
onward | -0.083 |
iked | -0.080 |
, | -0.079 |
Token | small |
Token ID | 1402 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
virtue | +0.199 |
rig | +0.195 |
Yes | +0.190 |
vous | +0.190 |
leaf | +0.180 |
Neg logit contributions | |
down | -0.225 |
ged | -0.211 |
iked | -0.199 |
onward | -0.197 |
, | -0.191 |
Token | , |
Token ID | 11 |
Feature activation | +9.71e+00 |
Pos logit contributions | |
down | +0.022 |
ged | +0.020 |
iked | +0.018 |
, | +0.017 |
onward | +0.016 |
Neg logit contributions | |
vous | -0.087 |
virtue | -0.086 |
rig | -0.086 |
Yes | -0.084 |
leaf | -0.084 |
Token | she |
Token ID | 673 |
Feature activation | +5.45e+00 |
Pos logit contributions | |
down | +0.115 |
, | +0.097 |
he | +0.086 |
onward | +0.085 |
his | +0.077 |
Neg logit contributions | |
rig | -0.525 |
vous | -0.518 |
virtue | -0.502 |
leaf | -0.497 |
resa | -0.462 |
Token | had |
Token ID | 550 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
, | +0.127 |
ged | +0.123 |
down | +0.120 |
am | +0.119 |
he | +0.109 |
Neg logit contributions | |
leaf | -0.202 |
rig | -0.202 |
virtue | -0.199 |
vous | -0.197 |
Tooth | -0.196 |
Token | done |
Token ID | 1760 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
rig | +0.066 |
vous | +0.062 |
virtue | +0.061 |
leaf | +0.060 |
Yes | +0.059 |
Neg logit contributions | |
down | -0.059 |
ged | -0.055 |
iked | -0.055 |
onward | -0.054 |
, | -0.054 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
vous | +0.136 |
virtue | +0.134 |
rig | +0.132 |
leaf | +0.132 |
years | +0.131 |
Neg logit contributions | |
down | -0.102 |
ged | -0.101 |
, | -0.093 |
iked | -0.089 |
inspection | -0.089 |
Token | and |
Token ID | 290 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
, | +0.029 |
down | +0.026 |
ged | +0.025 |
onward | +0.022 |
iked | +0.022 |
Neg logit contributions | |
vous | -0.053 |
virtue | -0.053 |
rig | -0.052 |
leaf | -0.052 |
importance | -0.049 |
Token | said |
Token ID | 531 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
virtue | +0.114 |
vous | +0.112 |
rig | +0.110 |
importance | +0.107 |
Yes | +0.104 |
Neg logit contributions | |
ged | -0.136 |
down | -0.135 |
iked | -0.131 |
onward | -0.123 |
ls | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +9.52e+00 |
Pos logit contributions | |
leys | +0.090 |
valleys | +0.085 |
rolling | +0.084 |
ashore | +0.084 |
packs | +0.083 |
Neg logit contributions | |
Yes | -0.108 |
bit | -0.106 |
ever | -0.105 |
never | -0.101 |
virtue | -0.101 |
Token | " |
Token ID | 366 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
ged | +0.215 |
iked | +0.215 |
ls | +0.202 |
onward | +0.200 |
down | +0.199 |
Neg logit contributions | |
Yes | -0.339 |
importance | -0.328 |
virtue | -0.326 |
vous | -0.320 |
rig | -0.319 |
Token | We |
Token ID | 1135 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
rig | +0.022 |
virtue | +0.022 |
promise | +0.022 |
least | +0.021 |
mistake | +0.021 |
Neg logit contributions | |
His | -0.016 |
ged | -0.015 |
he | -0.015 |
He | -0.014 |
down | -0.014 |
Token | need |
Token ID | 761 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
rig | +0.281 |
vous | +0.244 |
resa | +0.242 |
leaf | +0.240 |
Yes | +0.235 |
Neg logit contributions | |
, | -0.207 |
down | -0.205 |
ged | -0.183 |
am | -0.176 |
out | -0.176 |
Token | an |
Token ID | 281 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
rig | +0.254 |
vous | +0.245 |
virtue | +0.232 |
importance | +0.224 |
Yes | +0.224 |
Neg logit contributions | |
down | -0.119 |
, | -0.113 |
ged | -0.110 |
iked | -0.109 |
his | -0.103 |
Token | intelligent |
Token ID | 12661 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Yes | +0.122 |
virtue | +0.118 |
rig | +0.116 |
leaf | +0.114 |
vous | +0.107 |
Neg logit contributions | |
am | -0.104 |
, | -0.102 |
down | -0.100 |
iked | -0.096 |
his | -0.096 |
Token | plan |
Token ID | 1410 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
rig | +0.206 |
leaf | +0.185 |
Sad | +0.179 |
virtue | +0.179 |
least | +0.173 |
Neg logit contributions | |
, | -0.168 |
down | -0.142 |
his | -0.129 |
ged | -0.126 |
sand | -0.125 |
Token | to |
Token ID | 284 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
rig | +0.024 |
vous | +0.023 |
virtue | +0.023 |
importance | +0.022 |
Yes | +0.022 |
Neg logit contributions | |
down | -0.013 |
ged | -0.013 |
iked | -0.012 |
, | -0.012 |
onward | -0.011 |
Token | take |
Token ID | 1011 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
vous | +0.143 |
rig | +0.142 |
virtue | +0.141 |
importance | +0.136 |
leaf | +0.133 |
Neg logit contributions | |
down | -0.124 |
, | -0.116 |
ged | -0.115 |
iked | -0.114 |
onward | -0.109 |
Token | it |
Token ID | 340 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
ged | +0.019 |
down | +0.018 |
iked | +0.018 |
onward | +0.017 |
leys | +0.016 |
Neg logit contributions | |
virtue | -0.024 |
vous | -0.024 |
rig | -0.024 |
Yes | -0.023 |
importance | -0.023 |
Token | home |
Token ID | 1363 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ged | +0.065 |
iked | +0.063 |
down | +0.059 |
onward | +0.056 |
leys | +0.054 |
Neg logit contributions | |
virtue | -0.120 |
vous | -0.119 |
rig | -0.118 |
Yes | -0.116 |
importance | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
down | +0.075 |
ged | +0.066 |
, | +0.064 |
iked | +0.062 |
onward | +0.059 |
Neg logit contributions | |
vous | -0.175 |
virtue | -0.171 |
rig | -0.169 |
importance | -0.167 |
leaf | -0.167 |
Token | Her |
Token ID | 2332 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
ged | +0.003 |
iked | +0.003 |
leys | +0.003 |
ashore | +0.002 |
down | +0.002 |
Neg logit contributions | |
Yes | -0.004 |
virtue | -0.003 |
importance | -0.003 |
rig | -0.003 |
vous | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.88e+00 |
Pos logit contributions | |
down | +0.070 |
, | +0.067 |
iked | +0.058 |
ged | +0.057 |
ls | +0.055 |
Neg logit contributions | |
vous | -0.145 |
rig | -0.138 |
leaf | -0.137 |
virtue | -0.133 |
importance | -0.122 |
Token | said |
Token ID | 531 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
virtue | +0.321 |
vous | +0.307 |
rig | +0.298 |
importance | +0.284 |
leaf | +0.279 |
Neg logit contributions | |
, | -0.203 |
ged | -0.181 |
down | -0.177 |
am | -0.164 |
iked | -0.162 |
Token | yes |
Token ID | 3763 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
down | +0.101 |
iked | +0.099 |
ged | +0.098 |
leys | +0.095 |
ashore | +0.095 |
Neg logit contributions | |
virtue | -0.081 |
Yes | -0.081 |
importance | -0.079 |
vous | -0.076 |
matter | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +9.25e+00 |
Pos logit contributions | |
ged | +0.001 |
down | +0.001 |
iked | +0.000 |
onward | +0.000 |
leys | +0.000 |
Neg logit contributions | |
vous | -0.002 |
virtue | -0.002 |
rig | -0.002 |
Yes | -0.002 |
importance | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
, | +0.189 |
down | +0.156 |
he | +0.154 |
his | +0.145 |
they | +0.123 |
Neg logit contributions | |
virtue | -0.444 |
vous | -0.424 |
rig | -0.417 |
illa | -0.386 |
resa | -0.369 |
Token | they |
Token ID | 484 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
vous | +0.290 |
rig | +0.274 |
leaf | +0.257 |
virtue | +0.255 |
importance | +0.239 |
Neg logit contributions | |
down | -0.110 |
, | -0.107 |
onward | -0.082 |
he | -0.080 |
ls | -0.076 |
Token | time |
Token ID | 640 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
leaf | +0.133 |
virtue | +0.132 |
vous | +0.127 |
Yes | +0.127 |
importance | +0.123 |
Neg logit contributions | |
, | -0.121 |
ged | -0.118 |
down | -0.118 |
iked | -0.113 |
leys | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | +9.46e+00 |
Pos logit contributions | |
Yes | +0.034 |
years | +0.033 |
ever | +0.033 |
vous | +0.033 |
rig | +0.032 |
Neg logit contributions | |
ged | -0.020 |
iked | -0.020 |
ashore | -0.019 |
leys | -0.019 |
down | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
iked | +0.261 |
ged | +0.235 |
onward | +0.221 |
leys | +0.219 |
am | +0.218 |
Neg logit contributions | |
vous | -0.319 |
Yes | -0.318 |
importance | -0.299 |
matter | -0.299 |
rig | -0.297 |
Token | was |
Token ID | 373 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
ged | +0.164 |
iked | +0.164 |
down | +0.161 |
onward | +0.155 |
leys | +0.152 |
Neg logit contributions | |
vous | -0.095 |
virtue | -0.093 |
Yes | -0.091 |
importance | -0.091 |
rig | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
virtue | +0.112 |
rig | +0.106 |
vous | +0.103 |
importance | +0.101 |
Yes | +0.098 |
Neg logit contributions | |
down | -0.085 |
ged | -0.080 |
, | -0.076 |
iked | -0.075 |
his | -0.075 |
Token | little |
Token ID | 1310 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
virtue | +0.132 |
vous | +0.129 |
rig | +0.125 |
leaf | +0.122 |
importance | +0.122 |
Neg logit contributions | |
down | -0.134 |
ged | -0.124 |
, | -0.123 |
ls | -0.118 |
iked | -0.117 |
Token | girl |
Token ID | 2576 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
virtue | +0.199 |
rig | +0.196 |
vous | +0.192 |
importance | +0.189 |
leaf | +0.179 |
Neg logit contributions | |
down | -0.231 |
ged | -0.215 |
, | -0.207 |
ls | -0.204 |
iked | -0.201 |
Token | named |
Token ID | 3706 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
virtue | +0.238 |
rig | +0.232 |
importance | +0.231 |
vous | +0.220 |
leaf | +0.216 |
Neg logit contributions | |
down | -0.215 |
ged | -0.210 |
, | -0.208 |
iked | -0.191 |
am | -0.182 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
virtue | +0.156 |
vous | +0.153 |
rig | +0.153 |
importance | +0.149 |
Yes | +0.146 |
Neg logit contributions | |
down | -0.113 |
ged | -0.110 |
iked | -0.108 |
onward | -0.101 |
leys | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
virtue | +0.058 |
rig | +0.057 |
vous | +0.057 |
importance | +0.056 |
leaf | +0.055 |
Neg logit contributions | |
down | -0.026 |
ged | -0.026 |
iked | -0.023 |
, | -0.021 |
am | -0.020 |
Token | She |
Token ID | 1375 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ged | +0.001 |
iked | +0.001 |
ls | +0.001 |
down | +0.001 |
ashore | +0.001 |
Neg logit contributions | |
Yes | -0.002 |
vous | -0.002 |
importance | -0.002 |
virtue | -0.002 |
rig | -0.002 |
Token | time |
Token ID | 640 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
leaf | +0.125 |
virtue | +0.122 |
Yes | +0.117 |
vous | +0.115 |
importance | +0.114 |
Neg logit contributions | |
, | -0.110 |
down | -0.108 |
ged | -0.108 |
onward | -0.101 |
am | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +9.93e+00 |
Pos logit contributions | |
Yes | +0.009 |
ever | +0.009 |
years | +0.008 |
vous | +0.008 |
rig | +0.008 |
Neg logit contributions | |
ged | -0.006 |
iked | -0.006 |
leys | -0.006 |
ashore | -0.006 |
iece | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
iked | +0.285 |
ged | +0.246 |
am | +0.240 |
onward | +0.238 |
leys | +0.233 |
Neg logit contributions | |
Yes | -0.314 |
vous | -0.313 |
rig | -0.303 |
virtue | -0.297 |
importance | -0.296 |
Token | was |
Token ID | 373 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ged | +0.173 |
down | +0.171 |
iked | +0.171 |
onward | +0.162 |
leys | +0.158 |
Neg logit contributions | |
vous | -0.117 |
virtue | -0.116 |
rig | -0.113 |
Yes | -0.111 |
importance | -0.111 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
virtue | +0.099 |
rig | +0.094 |
importance | +0.090 |
vous | +0.090 |
matter | +0.086 |
Neg logit contributions | |
down | -0.074 |
ged | -0.072 |
iked | -0.066 |
, | -0.066 |
his | -0.065 |
Token | little |
Token ID | 1310 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
virtue | +0.111 |
vous | +0.109 |
rig | +0.106 |
importance | +0.103 |
leaf | +0.103 |
Neg logit contributions | |
down | -0.127 |
ged | -0.121 |
, | -0.116 |
iked | -0.114 |
ls | -0.114 |
Token | bear |
Token ID | 6842 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
virtue | +0.167 |
rig | +0.163 |
vous | +0.163 |
importance | +0.159 |
leaf | +0.150 |
Neg logit contributions | |
down | -0.217 |
ged | -0.211 |
iked | -0.201 |
ls | -0.197 |
onward | -0.193 |
Token | . |
Token ID | 13 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
virtue | +0.133 |
importance | +0.130 |
rig | +0.126 |
leaf | +0.124 |
matter | +0.120 |
Neg logit contributions | |
, | -0.094 |
down | -0.086 |
ged | -0.084 |
his | -0.076 |
am | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ged | +0.009 |
iked | +0.008 |
leys | +0.008 |
down | +0.008 |
ls | +0.008 |
Neg logit contributions | |
vous | -0.014 |
Yes | -0.013 |
importance | -0.013 |
virtue | -0.013 |
rig | -0.012 |
Token | little |
Token ID | 1310 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
virtue | +0.090 |
rig | +0.088 |
vous | +0.088 |
leaf | +0.086 |
Yes | +0.083 |
Neg logit contributions | |
down | -0.070 |
ged | -0.066 |
iked | -0.063 |
onward | -0.062 |
, | -0.060 |
Token | bear |
Token ID | 6842 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
vous | +0.144 |
Yes | +0.141 |
importance | +0.137 |
child | +0.135 |
virtue | +0.131 |
Neg logit contributions | |
iked | -0.246 |
ged | -0.239 |
leys | -0.230 |
onward | -0.229 |
am | -0.217 |