Token | cheese |
Token ID | 9891 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
� | +0.023 |
sed | +0.022 |
gust | +0.022 |
stem | +0.021 |
cheeks | +0.020 |
Neg logit contributions | |
and | -0.019 |
as | -0.019 |
ying | -0.018 |
pt | -0.018 |
ful | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
gust | +0.294 |
sed | +0.283 |
� | +0.276 |
stem | +0.270 |
cheeks | +0.266 |
Neg logit contributions | |
and | -0.237 |
as | -0.230 |
ying | -0.230 |
os | -0.210 |
adows | -0.206 |
Token | ol |
Token ID | 25776 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
� | +0.031 |
gust | +0.027 |
sed | +0.027 |
sidelines | +0.021 |
Luckily | +0.021 |
Neg logit contributions | |
and | -0.029 |
as | -0.029 |
if | -0.028 |
pt | -0.027 |
sorts | -0.027 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
gust | +0.114 |
� | +0.112 |
sed | +0.111 |
stem | +0.111 |
mouth | +0.111 |
Neg logit contributions | |
and | -0.025 |
ying | -0.020 |
as | -0.020 |
adows | -0.020 |
inker | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
and | +0.162 |
as | +0.157 |
ying | +0.156 |
pt | +0.145 |
os | +0.144 |
Neg logit contributions | |
gust | -0.196 |
sed | -0.194 |
� | -0.188 |
stem | -0.186 |
mouth | -0.180 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
� | +0.028 |
gust | +0.026 |
sed | +0.025 |
stem | +0.020 |
sidelines | +0.020 |
Neg logit contributions | |
and | -0.032 |
as | -0.032 |
pt | -0.030 |
sorts | -0.030 |
smart | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
gust | +0.445 |
� | +0.408 |
sed | +0.401 |
stem | +0.390 |
cheeks | +0.380 |
Neg logit contributions | |
as | -0.351 |
and | -0.350 |
ying | -0.333 |
adows | -0.310 |
os | -0.308 |
Token | They |
Token ID | 1119 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
gust | +0.096 |
sed | +0.093 |
stem | +0.090 |
cheeks | +0.086 |
� | +0.084 |
Neg logit contributions | |
and | -0.098 |
as | -0.088 |
ying | -0.083 |
os | -0.082 |
udd | -0.081 |
Token | see |
Token ID | 766 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
gust | +0.092 |
sed | +0.090 |
� | +0.088 |
mouth | +0.085 |
stem | +0.085 |
Neg logit contributions | |
and | -0.084 |
as | -0.082 |
ying | -0.080 |
adows | -0.078 |
pt | -0.077 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
� | +0.025 |
sed | +0.024 |
gust | +0.024 |
stem | +0.023 |
cheeks | +0.022 |
Neg logit contributions | |
and | -0.021 |
as | -0.020 |
ying | -0.019 |
pt | -0.019 |
os | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
gust | +0.086 |
sed | +0.084 |
� | +0.081 |
stem | +0.078 |
cheeks | +0.075 |
Neg logit contributions | |
and | -0.064 |
as | -0.062 |
ying | -0.061 |
os | -0.058 |
adows | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
mouth | +0.137 |
gust | +0.134 |
sed | +0.130 |
stem | +0.128 |
� | +0.128 |
Neg logit contributions | |
and | -0.201 |
as | -0.191 |
adows | -0.189 |
ying | -0.188 |
inker | -0.186 |
Token | He |
Token ID | 679 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
gust | +0.082 |
sed | +0.079 |
stem | +0.077 |
cheeks | +0.073 |
� | +0.072 |
Neg logit contributions | |
and | -0.114 |
as | -0.103 |
ying | -0.102 |
adows | -0.101 |
pt | -0.096 |
Token | likes |
Token ID | 7832 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
gust | +0.077 |
sed | +0.073 |
� | +0.073 |
stem | +0.072 |
mouth | +0.071 |
Neg logit contributions | |
and | -0.072 |
as | -0.070 |
ying | -0.069 |
adows | -0.067 |
udd | -0.066 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
and | +0.009 |
as | +0.008 |
ying | +0.008 |
os | +0.008 |
udd | +0.008 |
Neg logit contributions | |
� | -0.007 |
gust | -0.007 |
sed | -0.007 |
stem | -0.006 |
cheeks | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
gust | +0.250 |
sed | +0.242 |
stem | +0.237 |
mouth | +0.237 |
� | +0.236 |
Neg logit contributions | |
and | -0.279 |
as | -0.263 |
ying | -0.263 |
adows | -0.258 |
os | -0.246 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
� | +0.035 |
gust | +0.034 |
sed | +0.032 |
stem | +0.028 |
sidelines | +0.027 |
Neg logit contributions | |
and | -0.044 |
as | -0.042 |
sorts | -0.041 |
pt | -0.041 |
smart | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
gust | +0.428 |
� | +0.397 |
sed | +0.390 |
stem | +0.383 |
mouth | +0.369 |
Neg logit contributions | |
and | -0.362 |
as | -0.352 |
ying | -0.339 |
adows | -0.324 |
pt | -0.314 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
� | +0.035 |
gust | +0.032 |
sed | +0.029 |
sidelines | +0.025 |
stem | +0.025 |
Neg logit contributions | |
and | -0.044 |
pt | -0.043 |
as | -0.043 |
smart | -0.042 |
ful | -0.041 |
Token | too |
Token ID | 1165 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
mouth | +0.181 |
gust | +0.181 |
sed | +0.179 |
stem | +0.177 |
� | +0.172 |
Neg logit contributions | |
and | -0.232 |
ying | -0.219 |
adows | -0.218 |
as | -0.217 |
inker | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
gust | +0.121 |
sed | +0.117 |
stem | +0.114 |
� | +0.114 |
mouth | +0.114 |
Neg logit contributions | |
and | -0.128 |
as | -0.121 |
ying | -0.120 |
adows | -0.117 |
os | -0.112 |
Token | He |
Token ID | 679 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
gust | +0.084 |
sed | +0.080 |
stem | +0.078 |
� | +0.075 |
cheeks | +0.074 |
Neg logit contributions | |
and | -0.122 |
as | -0.112 |
ying | -0.110 |
adows | -0.109 |
udd | -0.105 |
Token | put |
Token ID | 1234 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
gust | +0.029 |
sed | +0.028 |
� | +0.028 |
stem | +0.027 |
mouth | +0.027 |
Neg logit contributions | |
and | -0.032 |
as | -0.032 |
pt | -0.030 |
ying | -0.030 |
adows | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
and | +0.007 |
pt | +0.007 |
os | +0.007 |
as | +0.007 |
ying | +0.006 |
Neg logit contributions | |
gust | -0.013 |
sed | -0.012 |
� | -0.012 |
stem | -0.012 |
cheeks | -0.011 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
� | +0.059 |
gust | +0.059 |
sidelines | +0.046 |
cheeks | +0.043 |
sed | +0.043 |
Neg logit contributions | |
as | -0.064 |
and | -0.064 |
ont | -0.063 |
aky | -0.062 |
pt | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +9.60e-03 |
Pos logit contributions | |
gust | +0.290 |
sed | +0.282 |
stem | +0.277 |
� | +0.276 |
mouth | +0.276 |
Neg logit contributions | |
and | -0.236 |
as | -0.221 |
ying | -0.220 |
adows | -0.215 |
os | -0.202 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
� | +0.019 |
gust | +0.018 |
sed | +0.017 |
sidelines | +0.016 |
sing | +0.015 |
Neg logit contributions | |
pt | -0.014 |
if | -0.012 |
os | -0.012 |
ful | -0.012 |
as | -0.011 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
� | +0.056 |
gust | +0.050 |
sidelines | +0.038 |
sed | +0.035 |
Luckily | +0.035 |
Neg logit contributions | |
and | -0.064 |
as | -0.064 |
pt | -0.063 |
aky | -0.060 |
if | -0.058 |
Token | on |
Token ID | 319 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
gust | +0.448 |
� | +0.406 |
sidelines | +0.386 |
sed | +0.369 |
Really | +0.359 |
Neg logit contributions | |
as | -0.367 |
and | -0.357 |
ying | -0.326 |
pt | -0.322 |
adows | -0.313 |
Token | the |
Token ID | 262 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
and | +0.004 |
ful | +0.004 |
as | +0.004 |
pt | +0.003 |
sorts | +0.003 |
Neg logit contributions | |
sed | -0.007 |
gust | -0.007 |
� | -0.007 |
cheeks | -0.006 |
sidelines | -0.006 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
� | +0.059 |
gust | +0.055 |
Really | +0.043 |
sed | +0.039 |
avail | +0.037 |
Neg logit contributions | |
and | -0.061 |
ows | -0.055 |
pt | -0.055 |
as | -0.055 |
adows | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
gust | +0.208 |
mouth | +0.207 |
sed | +0.205 |
stem | +0.205 |
� | +0.199 |
Neg logit contributions | |
and | -0.243 |
ying | -0.231 |
as | -0.229 |
adows | -0.226 |
inker | -0.218 |
Token | Mom |
Token ID | 11254 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
gust | +0.063 |
sed | +0.061 |
stem | +0.060 |
� | +0.056 |
cheeks | +0.056 |
Neg logit contributions | |
and | -0.071 |
as | -0.065 |
adows | -0.062 |
udd | -0.061 |
ying | -0.060 |
Token | because |
Token ID | 780 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
mouth | +0.034 |
stem | +0.033 |
gust | +0.032 |
sed | +0.031 |
cheeks | +0.030 |
Neg logit contributions | |
and | -0.052 |
ying | -0.052 |
inker | -0.052 |
iam | -0.051 |
asc | -0.051 |
Token | I |
Token ID | 314 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
gust | +0.001 |
sed | +0.001 |
stem | +0.001 |
� | +0.001 |
mouth | +0.001 |
Neg logit contributions | |
and | -0.002 |
as | -0.002 |
ying | -0.002 |
adows | -0.002 |
os | -0.002 |
Token | like |
Token ID | 588 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
� | +0.045 |
sed | +0.045 |
mouth | +0.044 |
stem | +0.042 |
tongue | +0.041 |
Neg logit contributions | |
and | -0.066 |
ying | -0.064 |
adows | -0.058 |
inker | -0.057 |
as | -0.056 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
gust | +0.019 |
� | +0.019 |
sed | +0.018 |
stem | +0.018 |
cheeks | +0.017 |
Neg logit contributions | |
and | -0.020 |
as | -0.018 |
ying | -0.018 |
pt | -0.017 |
os | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
gust | +0.226 |
mouth | +0.226 |
stem | +0.221 |
sed | +0.219 |
� | +0.215 |
Neg logit contributions | |
and | -0.290 |
adows | -0.274 |
ying | -0.273 |
as | -0.272 |
inker | -0.269 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
� | +0.021 |
gust | +0.021 |
sed | +0.019 |
stem | +0.016 |
timer | +0.015 |
Neg logit contributions | |
and | -0.028 |
as | -0.026 |
pt | -0.026 |
smart | -0.025 |
ful | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
gust | +0.396 |
sed | +0.380 |
� | +0.374 |
stem | +0.374 |
mouth | +0.371 |
Neg logit contributions | |
and | -0.374 |
as | -0.352 |
ying | -0.350 |
adows | -0.341 |
os | -0.324 |
Token | yellow |
Token ID | 7872 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
� | +0.021 |
gust | +0.020 |
sed | +0.018 |
stem | +0.016 |
timer | +0.015 |
Neg logit contributions | |
and | -0.030 |
pt | -0.028 |
as | -0.028 |
smart | -0.027 |
ful | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
gust | +0.095 |
� | +0.091 |
sed | +0.089 |
stem | +0.083 |
mouth | +0.079 |
Neg logit contributions | |
and | -0.101 |
as | -0.095 |
pt | -0.094 |
adows | -0.092 |
ying | -0.090 |
Token | red |
Token ID | 2266 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
� | +0.020 |
gust | +0.019 |
sed | +0.017 |
sidelines | +0.014 |
stem | +0.014 |
Neg logit contributions | |
and | -0.028 |
as | -0.027 |
smart | -0.027 |
pt | -0.026 |
ful | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
gust | +0.097 |
� | +0.094 |
sed | +0.091 |
stem | +0.086 |
mouth | +0.081 |
Neg logit contributions | |
and | -0.089 |
pt | -0.083 |
as | -0.082 |
adows | -0.079 |
ying | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
and | +0.009 |
as | +0.008 |
ying | +0.008 |
pt | +0.008 |
os | +0.008 |
Neg logit contributions | |
gust | -0.011 |
sed | -0.011 |
� | -0.010 |
stem | -0.010 |
cheeks | -0.010 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
� | +0.052 |
gust | +0.050 |
sed | +0.044 |
cheeks | +0.041 |
sidelines | +0.040 |
Neg logit contributions | |
and | -0.056 |
as | -0.056 |
pt | -0.054 |
reat | -0.053 |
ont | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
gust | +0.386 |
� | +0.359 |
sed | +0.354 |
stem | +0.337 |
mouth | +0.331 |
Neg logit contributions | |
and | -0.390 |
as | -0.377 |
ying | -0.363 |
adows | -0.348 |
pt | -0.342 |
Token | I |
Token ID | 314 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
gust | +0.059 |
sed | +0.053 |
� | +0.052 |
stem | +0.051 |
cheeks | +0.047 |
Neg logit contributions | |
and | -0.080 |
as | -0.073 |
adows | -0.072 |
ying | -0.069 |
pt | -0.069 |
Token | like |
Token ID | 588 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
� | +0.052 |
mouth | +0.052 |
gust | +0.051 |
sed | +0.051 |
stem | +0.051 |
Neg logit contributions | |
and | -0.057 |
ying | -0.055 |
inker | -0.051 |
adows | -0.050 |
as | -0.049 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
� | +0.029 |
gust | +0.028 |
sed | +0.027 |
stem | +0.025 |
cheeks | +0.025 |
Neg logit contributions | |
and | -0.027 |
as | -0.024 |
pt | -0.024 |
ying | -0.023 |
os | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
gust | +0.440 |
� | +0.408 |
sed | +0.401 |
stem | +0.391 |
mouth | +0.379 |
Neg logit contributions | |
and | -0.349 |
as | -0.339 |
ying | -0.324 |
adows | -0.312 |
pt | -0.306 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
os | +0.011 |
and | +0.011 |
pt | +0.011 |
if | +0.010 |
old | +0.010 |
Neg logit contributions | |
stem | -0.015 |
sed | -0.015 |
� | -0.015 |
gust | -0.014 |
timer | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
gust | +0.023 |
sed | +0.022 |
� | +0.021 |
stem | +0.021 |
mouth | +0.021 |
Neg logit contributions | |
and | -0.026 |
as | -0.025 |
ying | -0.024 |
adows | -0.024 |
os | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
gust | +0.125 |
sed | +0.121 |
stem | +0.120 |
� | +0.119 |
mouth | +0.114 |
Neg logit contributions | |
and | -0.113 |
ying | -0.104 |
as | -0.102 |
adows | -0.098 |
pt | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
sed | +0.072 |
stem | +0.071 |
gust | +0.071 |
cheeks | +0.069 |
� | +0.066 |
Neg logit contributions | |
and | -0.066 |
as | -0.059 |
smart | -0.056 |
os | -0.053 |
ying | -0.052 |
Token | put |
Token ID | 1234 |
Feature activation | -6.65e-03 |
Pos logit contributions | |
sed | +0.034 |
gust | +0.033 |
� | +0.029 |
cheeks | +0.029 |
Really | +0.029 |
Neg logit contributions | |
and | -0.026 |
pt | -0.026 |
as | -0.025 |
os | -0.025 |
reat | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +3.73e-02 |
Pos logit contributions | |
and | +0.011 |
ying | +0.010 |
as | +0.010 |
pt | +0.010 |
os | +0.009 |
Neg logit contributions | |
gust | -0.013 |
sed | -0.012 |
� | -0.012 |
cheeks | -0.011 |
stem | -0.011 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
� | +0.059 |
gust | +0.057 |
cheeks | +0.049 |
sed | +0.048 |
sidelines | +0.046 |
Neg logit contributions | |
as | -0.069 |
and | -0.066 |
reat | -0.062 |
ont | -0.060 |
aking | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
gust | +0.265 |
mouth | +0.259 |
stem | +0.257 |
sed | +0.254 |
� | +0.253 |
Neg logit contributions | |
and | -0.263 |
adows | -0.249 |
as | -0.246 |
ying | -0.244 |
inker | -0.234 |
Token | the |
Token ID | 262 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
� | +0.032 |
sed | +0.031 |
gust | +0.031 |
cheeks | +0.027 |
stem | +0.026 |
Neg logit contributions | |
and | -0.024 |
ful | -0.023 |
if | -0.023 |
pt | -0.022 |
as | -0.022 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
� | +0.057 |
gust | +0.052 |
cheeks | +0.044 |
sed | +0.043 |
Luckily | +0.041 |
Neg logit contributions | |
as | -0.068 |
and | -0.067 |
reat | -0.061 |
pt | -0.060 |
adows | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
gust | +0.400 |
� | +0.365 |
sed | +0.364 |
cheeks | +0.350 |
stem | +0.344 |
Neg logit contributions | |
and | -0.371 |
as | -0.366 |
ying | -0.360 |
pt | -0.333 |
adows | -0.328 |
Token | the |
Token ID | 262 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
and | +0.002 |
as | +0.002 |
ying | +0.002 |
adows | +0.002 |
os | +0.002 |
Neg logit contributions | |
gust | -0.002 |
sed | -0.002 |
� | -0.002 |
stem | -0.002 |
cheeks | -0.002 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
� | +0.060 |
gust | +0.057 |
Really | +0.048 |
sed | +0.047 |
cheeks | +0.042 |
Neg logit contributions | |
and | -0.067 |
as | -0.060 |
adows | -0.058 |
washer | -0.057 |
udd | -0.056 |
Token | ?" |
Token ID | 1701 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
mouth | +0.254 |
stem | +0.246 |
gust | +0.243 |
sed | +0.241 |
� | +0.236 |
Neg logit contributions | |
and | -0.215 |
adows | -0.199 |
as | -0.199 |
ying | -0.199 |
inker | -0.193 |
Token | Mom |
Token ID | 11254 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
sed | +0.017 |
� | +0.016 |
stem | +0.016 |
cheeks | +0.015 |
timer | +0.014 |
Neg logit contributions | |
if | -0.015 |
and | -0.014 |
pt | -0.013 |
iam | -0.013 |
sorts | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
gust | +0.229 |
sed | +0.220 |
� | +0.217 |
stem | +0.214 |
mouth | +0.209 |
Neg logit contributions | |
and | -0.211 |
ying | -0.200 |
as | -0.199 |
adows | -0.190 |
pt | -0.185 |
Token | It |
Token ID | 632 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
gust | +0.050 |
sed | +0.049 |
stem | +0.048 |
cheeks | +0.046 |
mouth | +0.045 |
Neg logit contributions | |
and | -0.071 |
as | -0.064 |
adows | -0.064 |
ying | -0.064 |
os | -0.062 |
Token | had |
Token ID | 550 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
gust | +0.124 |
� | +0.121 |
sed | +0.116 |
stem | +0.116 |
cheeks | +0.113 |
Neg logit contributions | |
pt | -0.087 |
and | -0.086 |
as | -0.085 |
os | -0.083 |
sorts | -0.081 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
gust | +0.097 |
� | +0.096 |
sed | +0.092 |
stem | +0.090 |
mouth | +0.088 |
Neg logit contributions | |
and | -0.103 |
as | -0.098 |
pt | -0.095 |
adows | -0.093 |
ying | -0.093 |
Token | and |
Token ID | 290 |
Feature activation | +4.19e-03 |
Pos logit contributions | |
gust | +0.259 |
sed | +0.249 |
� | +0.245 |
stem | +0.244 |
mouth | +0.241 |
Neg logit contributions | |
and | -0.248 |
as | -0.235 |
ying | -0.233 |
adows | -0.226 |
pt | -0.216 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
� | +0.007 |
gust | +0.006 |
sidelines | +0.005 |
sed | +0.005 |
timer | +0.005 |
Neg logit contributions | |
pt | -0.007 |
ful | -0.007 |
as | -0.007 |
and | -0.007 |
sorts | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
gust | +0.450 |
� | +0.411 |
sidelines | +0.386 |
sed | +0.385 |
stem | +0.384 |
Neg logit contributions | |
as | -0.331 |
and | -0.322 |
ying | -0.304 |
pt | -0.291 |
adows | -0.287 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
� | +0.008 |
gust | +0.007 |
sidelines | +0.006 |
sed | +0.006 |
timer | +0.005 |
Neg logit contributions | |
pt | -0.010 |
ful | -0.009 |
as | -0.009 |
if | -0.009 |
and | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
gust | +0.185 |
sed | +0.181 |
mouth | +0.179 |
stem | +0.178 |
� | +0.176 |
Neg logit contributions | |
and | -0.209 |
as | -0.196 |
ying | -0.196 |
adows | -0.194 |
inker | -0.184 |
Token | She |
Token ID | 1375 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
gust | +0.053 |
sed | +0.053 |
stem | +0.051 |
mouth | +0.049 |
� | +0.048 |
Neg logit contributions | |
and | -0.082 |
as | -0.075 |
ying | -0.075 |
adows | -0.073 |
udd | -0.071 |
Token | did |
Token ID | 750 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
gust | +0.048 |
� | +0.048 |
stem | +0.045 |
sed | +0.044 |
sidelines | +0.042 |
Neg logit contributions | |
as | -0.034 |
pt | -0.033 |
and | -0.033 |
udd | -0.032 |
os | -0.030 |
Token | I |
Token ID | 314 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
gust | +0.065 |
stem | +0.055 |
sed | +0.054 |
timer | +0.054 |
� | +0.053 |
Neg logit contributions | |
and | -0.072 |
as | -0.067 |
os | -0.067 |
adows | -0.066 |
ying | -0.063 |
Token | want |
Token ID | 765 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
� | +0.051 |
mouth | +0.050 |
sed | +0.049 |
gust | +0.048 |
stem | +0.048 |
Neg logit contributions | |
and | -0.063 |
ying | -0.062 |
inker | -0.056 |
as | -0.054 |
adows | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
and | +0.033 |
pt | +0.028 |
as | +0.027 |
ful | +0.026 |
os | +0.026 |
Neg logit contributions | |
gust | -0.054 |
� | -0.053 |
sed | -0.052 |
stem | -0.050 |
cheeks | -0.048 |
Token | put |
Token ID | 1234 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
gust | +0.031 |
sed | +0.030 |
� | +0.027 |
Really | +0.026 |
mouth | +0.026 |
Neg logit contributions | |
and | -0.030 |
pt | -0.030 |
adows | -0.029 |
as | -0.029 |
reat | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
and | +0.009 |
as | +0.008 |
ying | +0.008 |
pt | +0.008 |
os | +0.008 |
Neg logit contributions | |
gust | -0.011 |
sed | -0.011 |
� | -0.010 |
stem | -0.010 |
cheeks | -0.010 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
� | +0.052 |
gust | +0.050 |
sed | +0.044 |
cheeks | +0.041 |
sidelines | +0.040 |
Neg logit contributions | |
and | -0.056 |
as | -0.056 |
pt | -0.054 |
reat | -0.053 |
ont | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
gust | +0.386 |
� | +0.359 |
sed | +0.354 |
stem | +0.337 |
mouth | +0.331 |
Neg logit contributions | |
and | -0.390 |
as | -0.377 |
ying | -0.363 |
adows | -0.348 |
pt | -0.342 |
Token | I |
Token ID | 314 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
gust | +0.059 |
sed | +0.053 |
� | +0.052 |
stem | +0.051 |
cheeks | +0.047 |
Neg logit contributions | |
and | -0.080 |
as | -0.073 |
adows | -0.072 |
ying | -0.069 |
pt | -0.069 |
Token | like |
Token ID | 588 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
� | +0.052 |
mouth | +0.052 |
gust | +0.051 |
sed | +0.051 |
stem | +0.051 |
Neg logit contributions | |
and | -0.057 |
ying | -0.055 |
inker | -0.051 |
adows | -0.050 |
as | -0.049 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
� | +0.029 |
gust | +0.028 |
sed | +0.027 |
stem | +0.025 |
cheeks | +0.025 |
Neg logit contributions | |
and | -0.027 |
as | -0.024 |
pt | -0.024 |
ying | -0.023 |
os | -0.023 |
Token | ." |
Token ID | 526 |
Feature activation | -8.07e-03 |
Pos logit contributions | |
gust | +0.440 |
� | +0.408 |
sed | +0.401 |
stem | +0.391 |
mouth | +0.379 |
Neg logit contributions | |
and | -0.349 |
as | -0.339 |
ying | -0.324 |
adows | -0.312 |
pt | -0.306 |
Token | cheeks |
Token ID | 25839 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
pt | +0.025 |
as | +0.024 |
outage | +0.023 |
adows | +0.023 |
sorts | +0.023 |
Neg logit contributions | |
� | -0.016 |
gust | -0.012 |
Really | -0.011 |
sed | -0.011 |
timer | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
gust | +0.190 |
mouth | +0.186 |
stem | +0.184 |
� | +0.177 |
sed | +0.175 |
Neg logit contributions | |
and | -0.270 |
adows | -0.253 |
ying | -0.247 |
as | -0.244 |
iam | -0.239 |
Token | That |
Token ID | 1320 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
gust | +0.054 |
sed | +0.049 |
� | +0.049 |
stem | +0.048 |
mouth | +0.045 |
Neg logit contributions | |
and | -0.095 |
as | -0.090 |
ying | -0.088 |
adows | -0.088 |
os | -0.086 |
Token | is |
Token ID | 318 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
gust | +0.045 |
� | +0.045 |
sed | +0.043 |
stem | +0.042 |
cheeks | +0.041 |
Neg logit contributions | |
and | -0.035 |
as | -0.034 |
ying | -0.033 |
os | -0.033 |
sorts | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
and | +0.034 |
as | +0.034 |
ying | +0.032 |
adows | +0.030 |
iam | +0.030 |
Neg logit contributions | |
� | -0.044 |
gust | -0.041 |
cheeks | -0.039 |
stem | -0.039 |
sed | -0.038 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +0.072 |
gust | +0.066 |
cheeks | +0.066 |
sed | +0.060 |
mouths | +0.059 |
Neg logit contributions | |
as | -0.059 |
and | -0.059 |
outage | -0.057 |
pt | -0.056 |
ful | -0.055 |
Token | ster |
Token ID | 1706 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
gust | +0.375 |
� | +0.336 |
cheeks | +0.313 |
sed | +0.312 |
stem | +0.307 |
Neg logit contributions | |
as | -0.395 |
and | -0.381 |
ying | -0.375 |
adows | -0.351 |
ful | -0.346 |
Token | . |
Token ID | 13 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
mouth | +0.095 |
gust | +0.095 |
sed | +0.094 |
stem | +0.094 |
� | +0.090 |
Neg logit contributions | |
and | -0.110 |
ying | -0.103 |
as | -0.102 |
adows | -0.102 |
inker | -0.099 |
Token | A |
Token ID | 317 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
gust | +0.062 |
sed | +0.056 |
� | +0.054 |
stem | +0.054 |
cheeks | +0.051 |
Neg logit contributions | |
and | -0.088 |
as | -0.081 |
os | -0.080 |
adows | -0.079 |
ying | -0.079 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
� | +0.110 |
gust | +0.094 |
cheeks | +0.089 |
sed | +0.087 |
sidelines | +0.085 |
Neg logit contributions | |
as | -0.114 |
and | -0.109 |
outage | -0.106 |
pt | -0.104 |
ont | -0.104 |
Token | has |
Token ID | 468 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
sed | +0.090 |
gust | +0.089 |
mouth | +0.089 |
stem | +0.087 |
� | +0.084 |
Neg logit contributions | |
and | -0.107 |
ying | -0.100 |
adows | -0.099 |
as | -0.099 |
inker | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
gust | +0.072 |
sed | +0.069 |
stem | +0.068 |
mouth | +0.068 |
� | +0.067 |
Neg logit contributions | |
and | -0.080 |
as | -0.076 |
ying | -0.075 |
adows | -0.074 |
os | -0.070 |
Token | It |
Token ID | 632 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
gust | +0.047 |
sed | +0.045 |
stem | +0.044 |
cheeks | +0.042 |
� | +0.041 |
Neg logit contributions | |
and | -0.069 |
as | -0.062 |
ying | -0.061 |
adows | -0.061 |
os | -0.059 |
Token | had |
Token ID | 550 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
gust | +0.127 |
� | +0.122 |
sed | +0.116 |
stem | +0.115 |
sidelines | +0.113 |
Neg logit contributions | |
and | -0.085 |
as | -0.083 |
pt | -0.083 |
os | -0.082 |
sorts | -0.079 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
gust | +0.092 |
� | +0.091 |
sed | +0.086 |
stem | +0.084 |
mouth | +0.081 |
Neg logit contributions | |
and | -0.104 |
as | -0.099 |
adows | -0.095 |
pt | -0.094 |
ying | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | +6.29e-03 |
Pos logit contributions | |
gust | +0.250 |
sed | +0.241 |
stem | +0.237 |
� | +0.236 |
mouth | +0.236 |
Neg logit contributions | |
and | -0.256 |
as | -0.241 |
ying | -0.241 |
adows | -0.235 |
os | -0.224 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
� | +0.010 |
gust | +0.009 |
sed | +0.008 |
sidelines | +0.008 |
timer | +0.007 |
Neg logit contributions | |
and | -0.011 |
ful | -0.011 |
as | -0.011 |
pt | -0.011 |
sorts | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +6.98e-03 |
Pos logit contributions | |
gust | +0.421 |
� | +0.388 |
stem | +0.374 |
sed | +0.373 |
cheeks | +0.358 |
Neg logit contributions | |
and | -0.341 |
as | -0.337 |
ying | -0.319 |
adows | -0.308 |
pt | -0.302 |
Token | bread |
Token ID | 8509 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
� | +0.010 |
gust | +0.009 |
sed | +0.008 |
sidelines | +0.008 |
timer | +0.007 |
Neg logit contributions | |
pt | -0.013 |
and | -0.013 |
ful | -0.013 |
as | -0.013 |
smart | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
gust | +0.225 |
sed | +0.216 |
� | +0.212 |
stem | +0.211 |
mouth | +0.209 |
Neg logit contributions | |
and | -0.227 |
as | -0.215 |
ying | -0.213 |
adows | -0.208 |
pt | -0.199 |
Token | He |
Token ID | 679 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
gust | +0.051 |
sed | +0.049 |
stem | +0.048 |
� | +0.045 |
cheeks | +0.045 |
Neg logit contributions | |
and | -0.083 |
as | -0.077 |
ying | -0.076 |
adows | -0.075 |
os | -0.073 |
Token | also |
Token ID | 635 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
gust | +0.062 |
� | +0.060 |
stem | +0.057 |
sed | +0.057 |
mouth | +0.054 |
Neg logit contributions | |
and | -0.052 |
as | -0.052 |
pt | -0.049 |
udd | -0.048 |
os | -0.048 |
Token | Do |
Token ID | 2141 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
gust | +0.062 |
sed | +0.056 |
� | +0.054 |
stem | +0.054 |
cheeks | +0.051 |
Neg logit contributions | |
and | -0.088 |
as | -0.081 |
adows | -0.080 |
ying | -0.077 |
os | -0.077 |
Token | you |
Token ID | 345 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
gust | +0.087 |
� | +0.086 |
sed | +0.083 |
stem | +0.083 |
timer | +0.079 |
Neg logit contributions | |
and | -0.083 |
as | -0.079 |
adows | -0.074 |
ying | -0.073 |
os | -0.070 |
Token | like |
Token ID | 588 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
gust | +0.067 |
sed | +0.064 |
stem | +0.064 |
mouth | +0.064 |
� | +0.063 |
Neg logit contributions | |
and | -0.042 |
ying | -0.039 |
as | -0.038 |
adows | -0.037 |
os | -0.035 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
� | +0.018 |
gust | +0.017 |
sed | +0.017 |
cheeks | +0.016 |
stem | +0.015 |
Neg logit contributions | |
and | -0.017 |
as | -0.015 |
os | -0.015 |
smart | -0.015 |
ful | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +9.73e-03 |
Pos logit contributions | |
gust | +0.291 |
mouth | +0.283 |
sed | +0.282 |
stem | +0.281 |
� | +0.279 |
Neg logit contributions | |
and | -0.221 |
as | -0.204 |
ying | -0.202 |
adows | -0.201 |
os | -0.187 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
� | +0.016 |
gust | +0.014 |
sed | +0.013 |
sidelines | +0.011 |
cheeks | +0.011 |
Neg logit contributions | |
and | -0.018 |
if | -0.017 |
ful | -0.017 |
as | -0.017 |
smart | -0.017 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
gust | +0.426 |
sed | +0.403 |
� | +0.398 |
stem | +0.395 |
mouth | +0.389 |
Neg logit contributions | |
and | -0.330 |
as | -0.313 |
ying | -0.310 |
adows | -0.297 |
os | -0.283 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
and | +0.031 |
as | +0.029 |
ying | +0.028 |
adows | +0.028 |
os | +0.028 |
Neg logit contributions | |
gust | -0.024 |
sed | -0.024 |
stem | -0.023 |
� | -0.022 |
mouth | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
gust | +0.018 |
sed | +0.017 |
mouth | +0.017 |
stem | +0.017 |
� | +0.017 |
Neg logit contributions | |
and | -0.030 |
ying | -0.029 |
as | -0.028 |
adows | -0.028 |
os | -0.027 |
Token | L |
Token ID | 43 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
gust | +0.018 |
mouth | +0.018 |
stem | +0.017 |
� | +0.017 |
sed | +0.017 |
Neg logit contributions | |
ying | -0.027 |
and | -0.027 |
adows | -0.026 |
as | -0.025 |
outage | -0.025 |
Token | ila |
Token ID | 10102 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
and | +0.039 |
adows | +0.036 |
outage | +0.035 |
pt | +0.035 |
sorts | +0.035 |
Neg logit contributions | |
gust | -0.034 |
sed | -0.033 |
stem | -0.033 |
mouth | -0.032 |
� | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
gust | +0.250 |
sed | +0.241 |
� | +0.236 |
stem | +0.233 |
mouth | +0.232 |
Neg logit contributions | |
and | -0.214 |
as | -0.201 |
ying | -0.200 |
adows | -0.193 |
os | -0.185 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
� | +0.020 |
sed | +0.019 |
gust | +0.019 |
sidelines | +0.017 |
stem | +0.017 |
Neg logit contributions | |
and | -0.016 |
as | -0.016 |
pt | -0.015 |
os | -0.015 |
ful | -0.015 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
� | +0.059 |
gust | +0.053 |
sed | +0.044 |
Luckily | +0.042 |
Really | +0.041 |
Neg logit contributions | |
as | -0.063 |
and | -0.060 |
pt | -0.056 |
reat | -0.056 |
udd | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
gust | +0.284 |
sed | +0.271 |
� | +0.265 |
stem | +0.256 |
mouth | +0.254 |
Neg logit contributions | |
and | -0.241 |
as | -0.228 |
ying | -0.226 |
adows | -0.212 |
os | -0.208 |
Token | the |
Token ID | 262 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
� | +0.024 |
sed | +0.022 |
gust | +0.022 |
sidelines | +0.020 |
stem | +0.020 |
Neg logit contributions | |
and | -0.016 |
os | -0.015 |
as | -0.015 |
pt | -0.015 |
ful | -0.015 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
� | +0.056 |
gust | +0.049 |
sed | +0.042 |
Luckily | +0.040 |
cheeks | +0.038 |
Neg logit contributions | |
as | -0.065 |
and | -0.063 |
pt | -0.059 |
reat | -0.058 |
adows | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
gust | +0.429 |
� | +0.386 |
sidelines | +0.367 |
sed | +0.365 |
Really | +0.356 |
Neg logit contributions | |
as | -0.351 |
and | -0.338 |
ying | -0.318 |
ful | -0.301 |
adows | -0.298 |
Token | They |
Token ID | 1119 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
sed | +0.070 |
gust | +0.070 |
stem | +0.068 |
cheeks | +0.065 |
timer | +0.062 |
Neg logit contributions | |
and | -0.083 |
as | -0.075 |
udd | -0.072 |
ying | -0.072 |
adows | -0.070 |
Token | put |
Token ID | 1234 |
Feature activation | -7.67e-03 |
Pos logit contributions | |
gust | +0.062 |
sed | +0.060 |
stem | +0.058 |
� | +0.058 |
mouth | +0.058 |
Neg logit contributions | |
and | -0.069 |
as | -0.065 |
ying | -0.065 |
adows | -0.064 |
os | -0.061 |
Token | them |
Token ID | 606 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
and | +0.010 |
as | +0.010 |
ying | +0.010 |
os | +0.010 |
pt | +0.010 |
Neg logit contributions | |
sed | -0.016 |
gust | -0.016 |
cheeks | -0.015 |
� | -0.015 |
stem | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -3.69e-03 |
Pos logit contributions | |
and | +0.015 |
ying | +0.014 |
as | +0.014 |
adows | +0.014 |
inker | +0.013 |
Neg logit contributions | |
gust | -0.016 |
sed | -0.015 |
mouth | -0.015 |
stem | -0.015 |
� | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
gust | +0.112 |
mouth | +0.111 |
stem | +0.105 |
sed | +0.105 |
cheeks | +0.103 |
Neg logit contributions | |
and | -0.168 |
adows | -0.155 |
ying | -0.153 |
as | -0.153 |
outage | -0.149 |
Token | I |
Token ID | 314 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
gust | +0.068 |
stem | +0.056 |
timer | +0.056 |
sed | +0.056 |
sidelines | +0.053 |
Neg logit contributions | |
and | -0.076 |
os | -0.071 |
adows | -0.070 |
ibr | -0.068 |
asc | -0.067 |
Token | love |
Token ID | 1842 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
� | +0.050 |
mouth | +0.049 |
sed | +0.049 |
stem | +0.049 |
gust | +0.048 |
Neg logit contributions | |
and | -0.045 |
ying | -0.044 |
inker | -0.040 |
adows | -0.039 |
as | -0.039 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
and | +0.056 |
os | +0.050 |
ful | +0.050 |
as | +0.049 |
sorts | +0.048 |
Neg logit contributions | |
gust | -0.053 |
� | -0.051 |
sed | -0.049 |
cheeks | -0.044 |
stem | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
mouth | +0.214 |
stem | +0.209 |
gust | +0.205 |
sed | +0.204 |
� | +0.199 |
Neg logit contributions | |
and | -0.285 |
ying | -0.274 |
adows | -0.274 |
as | -0.268 |
inker | -0.268 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
gust | +0.013 |
� | +0.013 |
sed | +0.012 |
sidelines | +0.010 |
timer | +0.010 |
Neg logit contributions | |
and | -0.017 |
if | -0.017 |
ful | -0.017 |
sorts | -0.016 |
smart | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
gust | +0.394 |
sed | +0.369 |
� | +0.366 |
stem | +0.361 |
mouth | +0.355 |
Neg logit contributions | |
and | -0.362 |
as | -0.345 |
ying | -0.339 |
adows | -0.329 |
os | -0.315 |
Token | Thank |
Token ID | 6952 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
gust | +0.068 |
sed | +0.059 |
stem | +0.058 |
� | +0.055 |
cheeks | +0.054 |
Neg logit contributions | |
and | -0.085 |
adows | -0.078 |
as | -0.077 |
os | -0.075 |
ibr | -0.075 |
Token | you |
Token ID | 345 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
sed | +0.213 |
gust | +0.212 |
stem | +0.200 |
mouth | +0.190 |
sing | +0.190 |
Neg logit contributions | |
and | -0.171 |
as | -0.151 |
ful | -0.146 |
smart | -0.144 |
os | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
mouth | +0.049 |
gust | +0.047 |
sed | +0.045 |
stem | +0.044 |
� | +0.044 |
Neg logit contributions | |
ying | -0.068 |
and | -0.067 |
adows | -0.065 |
as | -0.065 |
outage | -0.063 |
Token | boy |
Token ID | 2933 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
gust | +0.073 |
sed | +0.072 |
� | +0.072 |
stem | +0.071 |
mouth | +0.067 |
Neg logit contributions | |
and | -0.107 |
as | -0.103 |
ying | -0.101 |
adows | -0.098 |
os | -0.098 |
Token | do |
Token ID | 466 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
sed | +0.044 |
mouth | +0.044 |
gust | +0.043 |
� | +0.043 |
stem | +0.042 |
Neg logit contributions | |
and | -0.049 |
ying | -0.047 |
adows | -0.045 |
as | -0.043 |
inker | -0.043 |
Token | not |
Token ID | 407 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
gust | +0.070 |
sed | +0.066 |
� | +0.064 |
stem | +0.064 |
mouth | +0.063 |
Neg logit contributions | |
and | -0.085 |
as | -0.081 |
ying | -0.080 |
adows | -0.078 |
udd | -0.075 |
Token | like |
Token ID | 588 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
and | +0.003 |
ying | +0.002 |
as | +0.002 |
adows | +0.002 |
os | +0.002 |
Neg logit contributions | |
gust | -0.004 |
sed | -0.004 |
stem | -0.004 |
mouth | -0.004 |
� | -0.004 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
� | +0.013 |
sed | +0.012 |
gust | +0.012 |
stem | +0.011 |
cheeks | +0.011 |
Neg logit contributions | |
and | -0.014 |
ying | -0.013 |
as | -0.013 |
ful | -0.012 |
reat | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
gust | +0.219 |
mouth | +0.218 |
stem | +0.214 |
sed | +0.211 |
� | +0.209 |
Neg logit contributions | |
and | -0.280 |
adows | -0.270 |
ying | -0.263 |
as | -0.263 |
inker | -0.258 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
� | +0.004 |
gust | +0.003 |
sed | +0.003 |
stem | +0.003 |
timer | +0.003 |
Neg logit contributions | |
and | -0.004 |
as | -0.004 |
pt | -0.004 |
ful | -0.004 |
ying | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
gust | +0.378 |
sed | +0.363 |
� | +0.357 |
stem | +0.356 |
mouth | +0.353 |
Neg logit contributions | |
and | -0.366 |
as | -0.345 |
ying | -0.343 |
adows | -0.335 |
os | -0.318 |
Token | They |
Token ID | 1119 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
gust | +0.044 |
� | +0.039 |
sed | +0.038 |
stem | +0.037 |
timer | +0.037 |
Neg logit contributions | |
and | -0.059 |
as | -0.054 |
os | -0.053 |
ibr | -0.051 |
smart | -0.051 |
Token | are |
Token ID | 389 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
gust | +0.063 |
sed | +0.061 |
� | +0.060 |
stem | +0.060 |
mouth | +0.059 |
Neg logit contributions | |
and | -0.042 |
as | -0.039 |
ying | -0.039 |
adows | -0.038 |
pt | -0.036 |
Token | too |
Token ID | 1165 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
and | +0.069 |
as | +0.068 |
ying | +0.065 |
pt | +0.063 |
adows | +0.061 |
Neg logit contributions | |
� | -0.078 |
gust | -0.075 |
sed | -0.070 |
cheeks | -0.068 |
stem | -0.068 |
Token | salty |
Token ID | 36021 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
gust | +0.089 |
sed | +0.086 |
� | +0.085 |
stem | +0.083 |
mouth | +0.082 |
Neg logit contributions | |
and | -0.125 |
as | -0.120 |
ying | -0.118 |
adows | -0.115 |
udd | -0.111 |
Token | " |
Token ID | 1 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
gust | +0.024 |
sed | +0.023 |
stem | +0.023 |
� | +0.023 |
mouth | +0.023 |
Neg logit contributions | |
and | -0.019 |
ying | -0.018 |
as | -0.017 |
adows | -0.017 |
pt | -0.016 |
Token | I |
Token ID | 40 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
and | +0.065 |
as | +0.061 |
ying | +0.057 |
iam | +0.056 |
os | +0.055 |
Neg logit contributions | |
gust | -0.060 |
sed | -0.058 |
mouth | -0.056 |
stem | -0.055 |
cheeks | -0.054 |
Token | want |
Token ID | 765 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
� | +0.061 |
mouth | +0.060 |
sed | +0.060 |
gust | +0.060 |
stem | +0.056 |
Neg logit contributions | |
and | -0.078 |
ying | -0.078 |
adows | -0.068 |
inker | -0.067 |
as | -0.067 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
and | +0.068 |
as | +0.064 |
ying | +0.063 |
adows | +0.061 |
os | +0.060 |
Neg logit contributions | |
gust | -0.049 |
sed | -0.048 |
� | -0.047 |
stem | -0.046 |
mouth | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
gust | +0.228 |
sed | +0.220 |
mouth | +0.216 |
stem | +0.216 |
� | +0.215 |
Neg logit contributions | |
and | -0.282 |
ying | -0.266 |
as | -0.266 |
adows | -0.262 |
pt | -0.249 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
gust | +0.008 |
� | +0.008 |
sed | +0.007 |
stem | +0.006 |
sidelines | +0.006 |
Neg logit contributions | |
and | -0.010 |
sorts | -0.009 |
as | -0.009 |
if | -0.009 |
os | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
gust | +0.418 |
� | +0.384 |
sed | +0.383 |
stem | +0.376 |
mouth | +0.362 |
Neg logit contributions | |
and | -0.339 |
as | -0.330 |
ying | -0.320 |
adows | -0.304 |
os | -0.297 |
Token | pineapple |
Token ID | 45540 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
gust | +0.009 |
� | +0.009 |
sed | +0.008 |
stem | +0.007 |
sidelines | +0.007 |
Neg logit contributions | |
and | -0.012 |
as | -0.012 |
smart | -0.012 |
if | -0.011 |
ful | -0.011 |
Token | ," |
Token ID | 553 |
Feature activation | +6.43e-02 |
Pos logit contributions | |
gust | +0.241 |
sed | +0.233 |
� | +0.229 |
stem | +0.227 |
mouth | +0.224 |
Neg logit contributions | |
and | -0.221 |
as | -0.210 |
ying | -0.207 |
adows | -0.200 |
os | -0.193 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
� | +0.113 |
sed | +0.110 |
stem | +0.107 |
gust | +0.098 |
tongue | +0.092 |
Neg logit contributions | |
iam | -0.105 |
if | -0.101 |
as | -0.100 |
and | -0.099 |
sorts | -0.097 |
Token | said |
Token ID | 531 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
gust | +0.056 |
sed | +0.054 |
mouth | +0.053 |
stem | +0.052 |
� | +0.051 |
Neg logit contributions | |
and | -0.083 |
ying | -0.080 |
as | -0.079 |
adows | -0.079 |
inker | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
mouth | +0.166 |
sed | +0.157 |
stem | +0.155 |
� | +0.153 |
gust | +0.146 |
Neg logit contributions | |
and | -0.251 |
adows | -0.246 |
inker | -0.246 |
ying | -0.244 |
outage | -0.236 |
Token | It |
Token ID | 632 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
gust | +0.062 |
sed | +0.054 |
stem | +0.053 |
� | +0.051 |
timer | +0.051 |
Neg logit contributions | |
and | -0.078 |
adows | -0.069 |
as | -0.069 |
ibr | -0.068 |
os | -0.068 |
Token | is |
Token ID | 318 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
gust | +0.116 |
sed | +0.110 |
� | +0.108 |
stem | +0.108 |
mouth | +0.106 |
Neg logit contributions | |
and | -0.099 |
as | -0.094 |
ying | -0.093 |
adows | -0.090 |
os | -0.088 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
and | +0.041 |
as | +0.040 |
ying | +0.038 |
adows | +0.037 |
pt | +0.037 |
Neg logit contributions | |
� | -0.052 |
gust | -0.051 |
sed | -0.049 |
cheeks | -0.047 |
stem | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
mouth | +0.203 |
stem | +0.197 |
sed | +0.194 |
gust | +0.190 |
� | +0.187 |
Neg logit contributions | |
and | -0.288 |
inker | -0.276 |
ying | -0.275 |
adows | -0.273 |
as | -0.268 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
� | +0.009 |
gust | +0.009 |
sed | +0.008 |
sidelines | +0.007 |
cheeks | +0.007 |
Neg logit contributions | |
and | -0.011 |
ful | -0.011 |
smart | -0.011 |
pt | -0.011 |
as | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
gust | +0.370 |
sed | +0.356 |
stem | +0.349 |
� | +0.349 |
mouth | +0.347 |
Neg logit contributions | |
and | -0.370 |
as | -0.349 |
ying | -0.347 |
adows | -0.339 |
os | -0.322 |
Token | Do |
Token ID | 2141 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
gust | +0.062 |
sed | +0.056 |
� | +0.054 |
stem | +0.054 |
cheeks | +0.051 |
Neg logit contributions | |
and | -0.088 |
as | -0.081 |
adows | -0.080 |
ying | -0.077 |
os | -0.077 |
Token | you |
Token ID | 345 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
gust | +0.087 |
� | +0.086 |
sed | +0.083 |
stem | +0.083 |
timer | +0.079 |
Neg logit contributions | |
and | -0.083 |
as | -0.079 |
adows | -0.074 |
ying | -0.073 |
os | -0.070 |
Token | like |
Token ID | 588 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
gust | +0.067 |
sed | +0.064 |
stem | +0.064 |
mouth | +0.064 |
� | +0.063 |
Neg logit contributions | |
and | -0.042 |
ying | -0.039 |
as | -0.038 |
adows | -0.037 |
os | -0.035 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
� | +0.018 |
gust | +0.017 |
sed | +0.017 |
cheeks | +0.016 |
stem | +0.015 |
Neg logit contributions | |
and | -0.017 |
as | -0.015 |
os | -0.015 |
smart | -0.015 |
ful | -0.015 |
Token | tasty |
Token ID | 25103 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
� | +0.059 |
sed | +0.056 |
gust | +0.054 |
cheeks | +0.054 |
stem | +0.050 |
Neg logit contributions | |
as | -0.076 |
and | -0.073 |
outage | -0.070 |
udd | -0.069 |
ying | -0.066 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
� | +0.042 |
sed | +0.042 |
Really | +0.038 |
mouths | +0.038 |
cheeks | +0.037 |
Neg logit contributions | |
sorts | -0.045 |
reat | -0.043 |
aking | -0.041 |
and | -0.041 |
udd | -0.041 |
Token | with |
Token ID | 351 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
gust | +0.232 |
sed | +0.223 |
� | +0.220 |
stem | +0.219 |
mouth | +0.217 |
Neg logit contributions | |
and | -0.198 |
as | -0.186 |
ying | -0.186 |
adows | -0.178 |
os | -0.170 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
� | +0.139 |
gust | +0.136 |
sed | +0.130 |
stem | +0.124 |
cheeks | +0.121 |
Neg logit contributions | |
and | -0.115 |
pt | -0.110 |
as | -0.109 |
ful | -0.102 |
col | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +8.72e-04 |
Pos logit contributions | |
gust | +0.260 |
sed | +0.249 |
� | +0.246 |
stem | +0.244 |
mouth | +0.242 |
Neg logit contributions | |
and | -0.236 |
as | -0.224 |
ying | -0.222 |
adows | -0.214 |
pt | -0.206 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
� | +0.001 |
gust | +0.001 |
sed | +0.001 |
sidelines | +0.001 |
stem | +0.001 |
Neg logit contributions | |
and | -0.001 |
pt | -0.001 |
as | -0.001 |
if | -0.001 |
sorts | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
gust | +0.432 |
� | +0.397 |
sed | +0.376 |
stem | +0.375 |
cheeks | +0.367 |
Neg logit contributions | |
as | -0.327 |
and | -0.318 |
ying | -0.302 |
pt | -0.286 |
adows | -0.285 |
Token | She |
Token ID | 1375 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
gust | +0.059 |
timer | +0.058 |
sed | +0.058 |
stem | +0.057 |
cheeks | +0.057 |
Neg logit contributions | |
and | -0.068 |
as | -0.060 |
ying | -0.059 |
os | -0.058 |
adows | -0.058 |
Token | feels |
Token ID | 5300 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
gust | +0.046 |
� | +0.045 |
stem | +0.042 |
sed | +0.041 |
cheeks | +0.040 |
Neg logit contributions | |
as | -0.033 |
and | -0.032 |
udd | -0.031 |
pt | -0.031 |
ying | -0.030 |
Token | hungry |
Token ID | 14720 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
and | +0.009 |
pt | +0.008 |
ying | +0.008 |
as | +0.008 |
adows | +0.008 |
Neg logit contributions | |
� | -0.009 |
sed | -0.009 |
gust | -0.009 |
stem | -0.008 |
cheeks | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
gust | +0.052 |
mouth | +0.051 |
stem | +0.049 |
sed | +0.049 |
� | +0.047 |
Neg logit contributions | |
and | -0.061 |
as | -0.059 |
ying | -0.059 |
adows | -0.058 |
inker | -0.056 |
Token | ol |
Token ID | 25776 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
and | +0.031 |
as | +0.029 |
ying | +0.029 |
os | +0.028 |
sorts | +0.027 |
Neg logit contributions | |
� | -0.025 |
gust | -0.025 |
sed | -0.024 |
cheeks | -0.022 |
stem | -0.022 |
Token | ives |
Token ID | 1083 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
� | +0.082 |
gust | +0.079 |
mouth | +0.076 |
grape | +0.076 |
stem | +0.076 |
Neg logit contributions | |
and | -0.023 |
ying | -0.022 |
inker | -0.021 |
adows | -0.021 |
pt | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
and | +0.214 |
ying | +0.200 |
as | +0.199 |
adows | +0.198 |
outage | +0.188 |
Neg logit contributions | |
gust | -0.177 |
mouth | -0.170 |
sed | -0.169 |
� | -0.168 |
stem | -0.167 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
as | +0.012 |
and | +0.011 |
sorts | +0.011 |
ying | +0.011 |
os | +0.011 |
Neg logit contributions | |
gust | -0.010 |
� | -0.009 |
sed | -0.009 |
stem | -0.008 |
mouth | -0.008 |
Token | likes |
Token ID | 7832 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
and | +0.008 |
ying | +0.008 |
as | +0.008 |
adows | +0.007 |
inker | +0.007 |
Neg logit contributions | |
gust | -0.008 |
sed | -0.007 |
mouth | -0.007 |
stem | -0.007 |
� | -0.007 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
and | +0.027 |
as | +0.025 |
ying | +0.024 |
os | +0.024 |
adows | +0.023 |
Neg logit contributions | |
gust | -0.024 |
sed | -0.024 |
� | -0.023 |
stem | -0.022 |
cheeks | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
gust | +0.358 |
sed | +0.346 |
stem | +0.339 |
� | +0.338 |
mouth | +0.338 |
Neg logit contributions | |
and | -0.379 |
as | -0.357 |
ying | -0.356 |
adows | -0.349 |
os | -0.332 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
gust | +0.007 |
sed | +0.006 |
stem | +0.006 |
timer | +0.006 |
cheeks | +0.006 |
Neg logit contributions | |
and | -0.007 |
as | -0.007 |
ying | -0.007 |
udd | -0.007 |
os | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
and | +0.036 |
ying | +0.035 |
as | +0.035 |
adows | +0.035 |
pt | +0.033 |
Neg logit contributions | |
gust | -0.020 |
� | -0.019 |
sed | -0.019 |
mouth | -0.019 |
stem | -0.018 |
Token | Mom |
Token ID | 29252 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
and | +0.033 |
as | +0.031 |
ying | +0.031 |
adows | +0.031 |
os | +0.029 |
Neg logit contributions | |
gust | -0.030 |
sed | -0.029 |
stem | -0.028 |
mouth | -0.028 |
� | -0.028 |
Token | has |
Token ID | 468 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
gust | +0.110 |
sed | +0.107 |
mouth | +0.107 |
stem | +0.105 |
� | +0.105 |
Neg logit contributions | |
and | -0.138 |
adows | -0.127 |
as | -0.126 |
ying | -0.125 |
pt | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
mouth | +0.078 |
gust | +0.078 |
stem | +0.075 |
� | +0.074 |
sed | +0.074 |
Neg logit contributions | |
and | -0.107 |
adows | -0.103 |
as | -0.103 |
ying | -0.102 |
inker | -0.101 |
Token | They |
Token ID | 1119 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
gust | +0.046 |
sed | +0.045 |
stem | +0.044 |
cheeks | +0.041 |
� | +0.041 |
Neg logit contributions | |
and | -0.065 |
ying | -0.060 |
as | -0.060 |
udd | -0.058 |
adows | -0.057 |
Token | were |
Token ID | 547 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
gust | +0.041 |
sed | +0.040 |
mouth | +0.040 |
stem | +0.039 |
� | +0.039 |
Neg logit contributions | |
and | -0.060 |
ying | -0.057 |
adows | -0.055 |
as | -0.054 |
inker | -0.054 |
Token | cheese |
Token ID | 9891 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
� | +0.009 |
gust | +0.009 |
sed | +0.009 |
stem | +0.008 |
cheeks | +0.008 |
Neg logit contributions | |
and | -0.008 |
as | -0.008 |
ying | -0.008 |
adows | -0.007 |
pt | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
gust | +0.225 |
sed | +0.221 |
mouth | +0.219 |
stem | +0.217 |
� | +0.215 |
Neg logit contributions | |
and | -0.274 |
ying | -0.259 |
as | -0.255 |
adows | -0.253 |
inker | -0.243 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
� | +0.004 |
gust | +0.004 |
sed | +0.003 |
sidelines | +0.003 |
Luckily | +0.003 |
Neg logit contributions | |
ful | -0.004 |
and | -0.004 |
sorts | -0.004 |
as | -0.004 |
pt | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e-03 |
Pos logit contributions | |
gust | +0.399 |
� | +0.370 |
sed | +0.368 |
stem | +0.366 |
mouth | +0.357 |
Neg logit contributions | |
and | -0.347 |
as | -0.333 |
ying | -0.322 |
adows | -0.317 |
os | -0.301 |
Token | lettuce |
Token ID | 39406 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
� | +0.005 |
gust | +0.005 |
sed | +0.004 |
stem | +0.004 |
sidelines | +0.004 |
Neg logit contributions | |
and | -0.007 |
pt | -0.006 |
ful | -0.006 |
as | -0.006 |
smart | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
sed | +0.166 |
mouth | +0.166 |
gust | +0.163 |
stem | +0.162 |
� | +0.159 |
Neg logit contributions | |
and | -0.214 |
ying | -0.203 |
as | -0.199 |
adows | -0.199 |
inker | -0.195 |
Token | They |
Token ID | 1119 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
gust | +0.054 |
sed | +0.052 |
stem | +0.051 |
mouth | +0.048 |
cheeks | +0.048 |
Neg logit contributions | |
and | -0.075 |
as | -0.069 |
ying | -0.069 |
adows | -0.066 |
udd | -0.065 |
Token | were |
Token ID | 547 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
gust | +0.050 |
sed | +0.048 |
stem | +0.047 |
� | +0.047 |
mouth | +0.047 |
Neg logit contributions | |
and | -0.062 |
as | -0.059 |
ying | -0.058 |
adows | -0.057 |
os | -0.055 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
and | +0.014 |
as | +0.014 |
ying | +0.013 |
adows | +0.013 |
pt | +0.013 |
Neg logit contributions | |
gust | -0.009 |
� | -0.008 |
sed | -0.008 |
stem | -0.008 |
mouth | -0.008 |
Token | ster |
Token ID | 1706 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
gust | +0.285 |
� | +0.256 |
sed | +0.242 |
stem | +0.233 |
mouth | +0.220 |
Neg logit contributions | |
as | -0.454 |
and | -0.444 |
adows | -0.431 |
ying | -0.428 |
pt | -0.413 |
Token | cage |
Token ID | 17186 |
Feature activation | +7.66e-02 |
Pos logit contributions | |
gust | +0.086 |
sed | +0.082 |
� | +0.081 |
stem | +0.076 |
mouth | +0.073 |
Neg logit contributions | |
and | -0.094 |
as | -0.094 |
adows | -0.091 |
ying | -0.090 |
pt | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
gust | +0.118 |
mouth | +0.118 |
stem | +0.114 |
sed | +0.113 |
cheeks | +0.110 |
Neg logit contributions | |
and | -0.157 |
ying | -0.146 |
adows | -0.140 |
iam | -0.139 |
as | -0.139 |
Token | Their |
Token ID | 5334 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
gust | +0.054 |
sed | +0.053 |
stem | +0.052 |
cheeks | +0.050 |
� | +0.047 |
Neg logit contributions | |
and | -0.069 |
as | -0.061 |
ying | -0.061 |
smart | -0.059 |
os | -0.059 |
Token | ham |
Token ID | 8891 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
� | +0.051 |
gust | +0.051 |
stem | +0.036 |
sidelines | +0.035 |
sed | +0.035 |
Neg logit contributions | |
and | -0.086 |
as | -0.085 |
pt | -0.082 |
adows | -0.080 |
os | -0.080 |
Token | ster |
Token ID | 1706 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
gust | +0.336 |
� | +0.306 |
sed | +0.279 |
stem | +0.279 |
sidelines | +0.271 |
Neg logit contributions | |
as | -0.413 |
and | -0.401 |
ying | -0.386 |
adows | -0.386 |
pt | -0.378 |
Token | , |
Token ID | 11 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
gust | +0.099 |
� | +0.095 |
sed | +0.088 |
stem | +0.086 |
sidelines | +0.084 |
Neg logit contributions | |
as | -0.090 |
and | -0.087 |
pt | -0.084 |
os | -0.083 |
adows | -0.083 |
Token | Fl |
Token ID | 1610 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
gust | +0.069 |
� | +0.068 |
sed | +0.066 |
stem | +0.065 |
mouth | +0.062 |
Neg logit contributions | |
and | -0.073 |
as | -0.069 |
ying | -0.068 |
pt | -0.066 |
adows | -0.065 |
Token | uffy |
Token ID | 15352 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
gust | +0.084 |
sidelines | +0.075 |
timer | +0.072 |
stem | +0.071 |
� | +0.068 |
Neg logit contributions | |
as | -0.063 |
udd | -0.059 |
adows | -0.059 |
adow | -0.056 |
os | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
and | +0.035 |
as | +0.035 |
adows | +0.033 |
ying | +0.033 |
os | +0.033 |
Neg logit contributions | |
gust | -0.034 |
� | -0.032 |
sed | -0.031 |
stem | -0.031 |
mouth | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
mouth | +0.044 |
gust | +0.043 |
sed | +0.042 |
stem | +0.042 |
� | +0.041 |
Neg logit contributions | |
and | -0.052 |
as | -0.050 |
ying | -0.050 |
adows | -0.048 |
udd | -0.047 |
Token | put |
Token ID | 1234 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
and | +0.038 |
as | +0.036 |
ying | +0.036 |
udd | +0.033 |
adows | +0.033 |
Neg logit contributions | |
stem | -0.021 |
gust | -0.020 |
mouth | -0.020 |
� | -0.019 |
sed | -0.019 |
Token | stones |
Token ID | 14966 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
and | +0.068 |
as | +0.063 |
ying | +0.061 |
outage | +0.061 |
adows | +0.061 |
Neg logit contributions | |
gust | -0.051 |
mouth | -0.051 |
� | -0.048 |
stem | -0.048 |
sed | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
inker | +0.055 |
and | +0.055 |
asc | +0.055 |
iam | +0.054 |
ibr | +0.052 |
Neg logit contributions | |
stem | -0.043 |
mouth | -0.042 |
gust | -0.041 |
� | -0.039 |
sed | -0.039 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
and | +0.060 |
ying | +0.057 |
as | +0.057 |
adows | +0.055 |
udd | +0.053 |
Neg logit contributions | |
gust | -0.045 |
sed | -0.044 |
stem | -0.043 |
mouth | -0.043 |
� | -0.042 |
Token | bags |
Token ID | 34005 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
sed | +0.024 |
mouth | +0.024 |
stem | +0.023 |
cheeks | +0.023 |
� | +0.022 |
Neg logit contributions | |
and | -0.028 |
outage | -0.027 |
sorts | -0.026 |
iam | -0.026 |
ying | -0.026 |
Token | around |
Token ID | 1088 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
and | +0.425 |
iam | +0.414 |
asc | +0.414 |
ying | +0.406 |
inker | +0.403 |
Neg logit contributions | |
gust | -0.432 |
� | -0.411 |
sed | -0.409 |
mouth | -0.408 |
cheeks | -0.405 |
Token | the |
Token ID | 262 |
Feature activation | -3.94e-04 |
Pos logit contributions | |
and | +0.112 |
as | +0.107 |
ying | +0.106 |
adows | +0.104 |
udd | +0.102 |
Neg logit contributions | |
gust | -0.083 |
stem | -0.079 |
� | -0.078 |
mouth | -0.078 |
sed | -0.078 |
Token | lake |
Token ID | 13546 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
and | +0.001 |
as | +0.001 |
ying | +0.001 |
adows | +0.001 |
os | +0.001 |
Neg logit contributions | |
gust | -0.001 |
sed | -0.001 |
stem | -0.001 |
mouth | -0.001 |
� | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -7.38e-03 |
Pos logit contributions | |
mouth | +0.005 |
stem | +0.005 |
gust | +0.005 |
sed | +0.005 |
� | +0.005 |
Neg logit contributions | |
and | -0.007 |
ying | -0.007 |
as | -0.007 |
inker | -0.006 |
asc | -0.006 |
Token | But |
Token ID | 887 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
and | +0.016 |
as | +0.015 |
adows | +0.015 |
ying | +0.015 |
os | +0.015 |
Neg logit contributions | |
gust | -0.010 |
sed | -0.010 |
stem | -0.010 |
mouth | -0.009 |
cheeks | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
and | +0.006 |
as | +0.006 |
ying | +0.006 |
udd | +0.006 |
outage | +0.006 |
Neg logit contributions | |
gust | -0.002 |
mouth | -0.002 |
sed | -0.002 |
stem | -0.002 |
� | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
and | +0.050 |
ying | +0.048 |
as | +0.047 |
adows | +0.046 |
outage | +0.044 |
Neg logit contributions | |
gust | -0.034 |
sed | -0.032 |
mouth | -0.032 |
stem | -0.031 |
� | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | +7.55e-03 |
Pos logit contributions | |
and | +0.023 |
as | +0.022 |
ying | +0.022 |
adows | +0.021 |
udd | +0.021 |
Neg logit contributions | |
gust | -0.016 |
mouth | -0.016 |
sed | -0.016 |
stem | -0.015 |
� | -0.015 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
cheeks | +0.012 |
� | +0.012 |
sed | +0.012 |
gust | +0.012 |
mouths | +0.011 |
Neg logit contributions | |
and | -0.013 |
as | -0.012 |
outage | -0.012 |
sorts | -0.012 |
udd | -0.011 |
Token | qu |
Token ID | 627 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
gust | +0.032 |
sed | +0.031 |
stem | +0.030 |
� | +0.030 |
mouth | +0.029 |
Neg logit contributions | |
and | -0.032 |
as | -0.030 |
ying | -0.030 |
adows | -0.029 |
pt | -0.028 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
and | +0.033 |
ying | +0.030 |
as | +0.030 |
adows | +0.029 |
os | +0.027 |
Neg logit contributions | |
gust | -0.050 |
sed | -0.048 |
stem | -0.048 |
� | -0.048 |
mouth | -0.048 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
and | +0.390 |
as | +0.376 |
adows | +0.374 |
os | +0.370 |
udd | +0.365 |
Neg logit contributions | |
gust | -0.456 |
stem | -0.426 |
timer | -0.399 |
cheeks | -0.397 |
mouth | -0.391 |
Token | with |
Token ID | 351 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
and | +0.234 |
as | +0.220 |
adows | +0.217 |
ying | +0.215 |
udd | +0.208 |
Neg logit contributions | |
gust | -0.229 |
sed | -0.222 |
mouth | -0.220 |
stem | -0.215 |
� | -0.204 |
Token | a |
Token ID | 257 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
gust | +0.085 |
sed | +0.085 |
� | +0.083 |
stem | +0.082 |
mouth | +0.079 |
Neg logit contributions | |
and | -0.080 |
as | -0.074 |
pt | -0.072 |
adows | -0.071 |
ying | -0.071 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
sed | +0.011 |
� | +0.010 |
gust | +0.010 |
cheeks | +0.010 |
stem | +0.010 |
Neg logit contributions | |
as | -0.013 |
and | -0.013 |
pt | -0.013 |
outage | -0.013 |
sorts | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
gust | +0.086 |
mouth | +0.085 |
sed | +0.084 |
stem | +0.083 |
� | +0.082 |
Neg logit contributions | |
and | -0.098 |
ying | -0.093 |
as | -0.091 |
adows | -0.091 |
inker | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
and | +0.199 |
as | +0.188 |
adows | +0.184 |
ying | +0.184 |
inker | +0.182 |
Neg logit contributions | |
gust | -0.122 |
mouth | -0.115 |
stem | -0.112 |
sed | -0.105 |
� | -0.101 |
Token | other |
Token ID | 584 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
and | +0.030 |
ying | +0.029 |
as | +0.029 |
adows | +0.028 |
os | +0.027 |
Neg logit contributions | |
gust | -0.017 |
stem | -0.017 |
sed | -0.016 |
mouth | -0.016 |
� | -0.016 |
Token | kn |
Token ID | 638 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
and | +0.035 |
pt | +0.032 |
as | +0.032 |
ying | +0.031 |
outage | +0.031 |
Neg logit contributions | |
gust | -0.023 |
stem | -0.022 |
mouth | -0.021 |
cheeks | -0.020 |
sed | -0.020 |
Token | obs |
Token ID | 8158 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
and | +0.032 |
ying | +0.030 |
as | +0.029 |
adows | +0.029 |
pt | +0.028 |
Neg logit contributions | |
gust | -0.049 |
sed | -0.047 |
stem | -0.047 |
mouth | -0.047 |
� | -0.046 |
Token | qu |
Token ID | 627 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
and | +0.157 |
as | +0.143 |
ying | +0.143 |
adows | +0.143 |
inker | +0.140 |
Neg logit contributions | |
gust | -0.120 |
mouth | -0.120 |
sed | -0.119 |
stem | -0.118 |
� | -0.114 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
and | +0.039 |
ying | +0.036 |
outage | +0.036 |
adows | +0.035 |
iam | +0.034 |
Neg logit contributions | |
gust | -0.054 |
stem | -0.053 |
� | -0.052 |
mouth | -0.051 |
sed | -0.049 |
Token | led |
Token ID | 992 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
and | +0.432 |
adows | +0.406 |
iam | +0.402 |
ibr | +0.402 |
as | +0.389 |
Neg logit contributions | |
gust | -0.415 |
stem | -0.380 |
cheeks | -0.369 |
mouth | -0.357 |
timer | -0.349 |
Token | over |
Token ID | 625 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
outage | +0.010 |
ying | +0.010 |
and | +0.010 |
adows | +0.010 |
as | +0.010 |
Neg logit contributions | |
mouth | -0.007 |
gust | -0.006 |
stem | -0.006 |
sed | -0.006 |
cheeks | -0.006 |
Token | who |
Token ID | 508 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
and | +0.105 |
ying | +0.100 |
adows | +0.100 |
as | +0.099 |
outage | +0.096 |
Neg logit contributions | |
gust | -0.073 |
mouth | -0.070 |
stem | -0.069 |
sed | -0.069 |
� | -0.068 |
Token | should |
Token ID | 815 |
Feature activation | +9.26e-04 |
Pos logit contributions | |
and | +0.016 |
ying | +0.015 |
adows | +0.014 |
as | +0.014 |
inker | +0.014 |
Neg logit contributions | |
gust | -0.013 |
� | -0.012 |
sed | -0.012 |
mouth | -0.012 |
stem | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
gust | +0.001 |
sed | +0.001 |
� | +0.001 |
stem | +0.001 |
mouth | +0.001 |
Neg logit contributions | |
and | -0.002 |
as | -0.002 |
ying | -0.002 |
adows | -0.002 |
pt | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
and | +0.010 |
as | +0.009 |
ying | +0.009 |
adows | +0.009 |
pt | +0.009 |
Neg logit contributions | |
gust | -0.008 |
mouth | -0.007 |
sed | -0.007 |
stem | -0.007 |
� | -0.007 |
Token | today |
Token ID | 1909 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
and | +0.025 |
as | +0.024 |
ying | +0.024 |
adows | +0.023 |
udd | +0.022 |
Neg logit contributions | |
gust | -0.017 |
sed | -0.016 |
mouth | -0.016 |
stem | -0.016 |
� | -0.015 |
Token | they |
Token ID | 484 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
and | +0.080 |
as | +0.076 |
adows | +0.075 |
ying | +0.075 |
aking | +0.071 |
Neg logit contributions | |
gust | -0.039 |
mouth | -0.036 |
� | -0.035 |
sed | -0.034 |
stem | -0.034 |
Token | were |
Token ID | 547 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
and | +0.098 |
ying | +0.087 |
adows | +0.087 |
as | +0.085 |
outage | +0.084 |
Neg logit contributions | |
gust | -0.062 |
mouth | -0.057 |
� | -0.056 |
sed | -0.056 |
stem | -0.055 |
Token | qu |
Token ID | 627 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
and | +0.046 |
ying | +0.043 |
as | +0.043 |
adows | +0.042 |
inker | +0.040 |
Neg logit contributions | |
gust | -0.042 |
sed | -0.040 |
mouth | -0.040 |
stem | -0.039 |
� | -0.039 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
and | +0.022 |
ying | +0.020 |
outage | +0.019 |
adows | +0.018 |
pt | +0.018 |
Neg logit contributions | |
gust | -0.063 |
� | -0.062 |
stem | -0.060 |
mouth | -0.059 |
sed | -0.058 |
Token | ling |
Token ID | 1359 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
and | +0.373 |
outage | +0.351 |
adows | +0.350 |
pt | +0.348 |
iam | +0.347 |
Neg logit contributions | |
gust | -0.453 |
timer | -0.402 |
cheeks | -0.400 |
stem | -0.395 |
gu | -0.380 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
and | +0.070 |
ying | +0.068 |
as | +0.067 |
adows | +0.066 |
outage | +0.065 |
Neg logit contributions | |
gust | -0.054 |
mouth | -0.053 |
sed | -0.050 |
cheeks | -0.049 |
stem | -0.049 |
Token | Jenna |
Token ID | 45377 |
Feature activation | -6.79e-02 |
Pos logit contributions | |
and | +0.050 |
as | +0.047 |
ying | +0.047 |
adows | +0.046 |
os | +0.044 |
Neg logit contributions | |
gust | -0.037 |
sed | -0.035 |
stem | -0.035 |
� | -0.034 |
mouth | -0.034 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
and | +0.145 |
ying | +0.136 |
as | +0.134 |
adows | +0.133 |
inker | +0.128 |
Neg logit contributions | |
gust | -0.098 |
sed | -0.093 |
mouth | -0.092 |
stem | -0.092 |
� | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
and | +0.040 |
ying | +0.038 |
as | +0.038 |
adows | +0.038 |
udd | +0.035 |
Neg logit contributions | |
gust | -0.043 |
mouth | -0.042 |
sed | -0.041 |
stem | -0.041 |
� | -0.040 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
and | +0.082 |
as | +0.081 |
ying | +0.078 |
adows | +0.075 |
os | +0.072 |
Neg logit contributions | |
� | -0.076 |
sed | -0.076 |
gust | -0.074 |
stem | -0.074 |
mouth | -0.071 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
and | +0.136 |
adows | +0.125 |
ying | +0.124 |
as | +0.122 |
outage | +0.121 |
Neg logit contributions | |
gust | -0.099 |
mouth | -0.090 |
sed | -0.090 |
cheeks | -0.089 |
stem | -0.087 |
Token | 't |
Token ID | 470 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
and | +0.057 |
adows | +0.056 |
as | +0.056 |
ying | +0.055 |
udd | +0.053 |
Neg logit contributions | |
� | -0.019 |
gust | -0.017 |
mouth | -0.015 |
sed | -0.015 |
stem | -0.014 |
Token | stop |
Token ID | 2245 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ying | +0.079 |
os | +0.077 |
adows | +0.077 |
udd | +0.076 |
ibr | +0.076 |
Neg logit contributions | |
gust | -0.073 |
stem | -0.064 |
be | -0.064 |
mouth | -0.063 |
cheeks | -0.062 |
Token | qu |
Token ID | 627 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
and | +0.041 |
ying | +0.039 |
as | +0.038 |
pt | +0.037 |
adows | +0.036 |
Neg logit contributions | |
gust | -0.042 |
sed | -0.042 |
stem | -0.042 |
� | -0.041 |
mouth | -0.040 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
and | +0.012 |
ying | +0.011 |
adows | +0.010 |
as | +0.010 |
outage | +0.009 |
Neg logit contributions | |
gust | -0.044 |
� | -0.043 |
mouth | -0.043 |
stem | -0.042 |
sed | -0.042 |
Token | ling |
Token ID | 1359 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
adows | +0.327 |
and | +0.319 |
ibr | +0.305 |
as | +0.304 |
iam | +0.303 |
Neg logit contributions | |
gust | -0.501 |
cheeks | -0.457 |
timer | -0.445 |
mouth | -0.427 |
stem | -0.423 |
Token | and |
Token ID | 290 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
and | +0.065 |
as | +0.064 |
adows | +0.063 |
ying | +0.062 |
asc | +0.061 |
Neg logit contributions | |
gust | -0.046 |
mouth | -0.044 |
cheeks | -0.042 |
sed | -0.041 |
tongue | -0.040 |
Token | were |
Token ID | 547 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
and | +0.080 |
as | +0.076 |
ying | +0.076 |
adows | +0.074 |
os | +0.071 |
Neg logit contributions | |
gust | -0.063 |
sed | -0.060 |
stem | -0.059 |
mouth | -0.059 |
� | -0.059 |
Token | getting |
Token ID | 1972 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
and | +0.042 |
ying | +0.040 |
adows | +0.040 |
as | +0.039 |
inker | +0.038 |
Neg logit contributions | |
gust | -0.035 |
sed | -0.033 |
mouth | -0.033 |
stem | -0.031 |
� | -0.031 |
Token | louder |
Token ID | 27089 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
and | +0.013 |
as | +0.012 |
ying | +0.012 |
adows | +0.012 |
os | +0.011 |
Neg logit contributions | |
gust | -0.011 |
sed | -0.011 |
stem | -0.010 |
� | -0.010 |
mouth | -0.010 |
Token | Please |
Token ID | 5492 |
Feature activation | +9.33e-02 |
Pos logit contributions | |
and | +0.100 |
as | +0.094 |
ying | +0.093 |
adows | +0.092 |
os | +0.088 |
Neg logit contributions | |
gust | -0.074 |
sed | -0.073 |
mouth | -0.071 |
stem | -0.070 |
� | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +3.52e-04 |
Pos logit contributions | |
gust | +0.136 |
mouth | +0.131 |
� | +0.131 |
sed | +0.130 |
stem | +0.128 |
Neg logit contributions | |
and | -0.202 |
ying | -0.188 |
as | -0.185 |
adows | -0.182 |
udd | -0.174 |
Token | no |
Token ID | 645 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
gust | +0.000 |
mouth | +0.000 |
stem | +0.000 |
sed | +0.000 |
� | +0.000 |
Neg logit contributions | |
and | -0.001 |
as | -0.001 |
adows | -0.001 |
ying | -0.001 |
udd | -0.001 |
Token | more |
Token ID | 517 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
sed | +0.059 |
gust | +0.057 |
� | +0.057 |
stem | +0.056 |
mouth | +0.055 |
Neg logit contributions | |
and | -0.042 |
as | -0.039 |
ying | -0.039 |
adows | -0.038 |
inker | -0.036 |
Token | qu |
Token ID | 627 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
gust | +0.060 |
mouth | +0.055 |
stem | +0.054 |
sed | +0.053 |
cheeks | +0.052 |
Neg logit contributions | |
and | -0.073 |
adows | -0.067 |
as | -0.067 |
ying | -0.066 |
udd | -0.064 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
and | +0.023 |
adows | +0.019 |
ying | +0.019 |
as | +0.018 |
outage | +0.018 |
Neg logit contributions | |
gust | -0.056 |
� | -0.055 |
mouth | -0.053 |
stem | -0.053 |
sed | -0.051 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
and | +0.386 |
adows | +0.359 |
ibr | +0.346 |
iam | +0.343 |
udd | +0.343 |
Neg logit contributions | |
gust | -0.462 |
stem | -0.403 |
cheeks | -0.401 |
timer | -0.394 |
mouth | -0.389 |
Token | ! |
Token ID | 0 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
and | +0.053 |
adows | +0.050 |
udd | +0.049 |
iam | +0.048 |
ying | +0.048 |
Neg logit contributions | |
gust | -0.044 |
mouth | -0.044 |
stem | -0.041 |
top | -0.039 |
tongue | -0.039 |
Token | Let |
Token ID | 3914 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
and | +0.022 |
as | +0.021 |
ying | +0.021 |
os | +0.021 |
adows | +0.020 |
Neg logit contributions | |
gust | -0.013 |
stem | -0.012 |
sed | -0.012 |
� | -0.011 |
mouth | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
and | +0.057 |
as | +0.053 |
adows | +0.053 |
ying | +0.052 |
outage | +0.049 |
Neg logit contributions | |
gust | -0.035 |
mouth | -0.033 |
sed | -0.031 |
stem | -0.031 |
� | -0.031 |
Token | find |
Token ID | 1064 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
gust | +0.015 |
sed | +0.015 |
stem | +0.014 |
� | +0.014 |
mouth | +0.014 |
Neg logit contributions | |
and | -0.023 |
as | -0.022 |
ying | -0.022 |
adows | -0.021 |
os | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
gust | +0.035 |
sed | +0.034 |
� | +0.034 |
stem | +0.034 |
mouth | +0.033 |
Neg logit contributions | |
and | -0.028 |
ying | -0.026 |
as | -0.026 |
adows | -0.025 |
pt | -0.024 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
and | +0.072 |
as | +0.069 |
ying | +0.069 |
adows | +0.067 |
os | +0.064 |
Neg logit contributions | |
gust | -0.050 |
sed | -0.047 |
stem | -0.046 |
mouth | -0.046 |
� | -0.046 |
Token | two |
Token ID | 734 |
Feature activation | -4.36e-02 |
Pos logit contributions | |
and | +0.049 |
as | +0.047 |
ying | +0.047 |
adows | +0.045 |
aking | +0.045 |
Neg logit contributions | |
gust | -0.029 |
mouth | -0.028 |
sed | -0.027 |
stem | -0.025 |
cheeks | -0.025 |
Token | birds |
Token ID | 10087 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
as | +0.083 |
and | +0.082 |
adows | +0.079 |
ying | +0.078 |
pt | +0.075 |
Neg logit contributions | |
� | -0.068 |
sed | -0.067 |
stem | -0.065 |
gust | -0.064 |
mouth | -0.061 |
Token | qu |
Token ID | 627 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
gust | +0.041 |
sed | +0.040 |
stem | +0.039 |
� | +0.039 |
mouth | +0.039 |
Neg logit contributions | |
and | -0.055 |
as | -0.052 |
ying | -0.052 |
adows | -0.051 |
os | -0.048 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
and | +0.023 |
ying | +0.021 |
as | +0.020 |
adows | +0.020 |
outage | +0.019 |
Neg logit contributions | |
gust | -0.036 |
stem | -0.034 |
sed | -0.034 |
� | -0.034 |
mouth | -0.034 |
Token | ling |
Token ID | 1359 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
and | +0.360 |
adows | +0.334 |
udd | +0.332 |
iam | +0.331 |
as | +0.328 |
Neg logit contributions | |
gust | -0.460 |
stem | -0.426 |
cheeks | -0.421 |
timer | -0.417 |
mouth | -0.402 |
Token | ! |
Token ID | 0 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
and | +0.058 |
ying | +0.055 |
as | +0.055 |
adows | +0.054 |
udd | +0.052 |
Neg logit contributions | |
gust | -0.053 |
sed | -0.051 |
mouth | -0.051 |
stem | -0.050 |
� | -0.049 |
Token | They |
Token ID | 1119 |
Feature activation | -9.45e-03 |
Pos logit contributions | |
gust | +0.005 |
stem | +0.005 |
sed | +0.005 |
� | +0.005 |
cheeks | +0.004 |
Neg logit contributions | |
and | -0.007 |
os | -0.007 |
as | -0.007 |
adows | -0.007 |
ying | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
and | +0.018 |
ying | +0.017 |
adows | +0.017 |
as | +0.017 |
outage | +0.016 |
Neg logit contributions | |
gust | -0.016 |
sed | -0.015 |
stem | -0.015 |
mouth | -0.015 |
� | -0.014 |
Token | squ |
Token ID | 2809 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
and | +0.028 |
ying | +0.026 |
as | +0.026 |
adows | +0.025 |
os | +0.024 |
Neg logit contributions | |
gust | -0.029 |
sed | -0.028 |
mouth | -0.027 |
stem | -0.027 |
� | -0.027 |
Token | both |
Token ID | 1111 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
gust | +0.010 |
sed | +0.010 |
� | +0.009 |
stem | +0.009 |
mouth | +0.009 |
Neg logit contributions | |
and | -0.013 |
ying | -0.013 |
as | -0.013 |
adows | -0.012 |
os | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e-03 |
Pos logit contributions | |
gust | +0.058 |
mouth | +0.055 |
stem | +0.054 |
sed | +0.053 |
cheeks | +0.051 |
Neg logit contributions | |
and | -0.055 |
ying | -0.050 |
as | -0.050 |
adows | -0.050 |
inker | -0.048 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.92e-02 |
Pos logit contributions | |
as | +0.009 |
and | +0.009 |
ying | +0.008 |
adows | +0.008 |
pt | +0.008 |
Neg logit contributions | |
� | -0.008 |
gust | -0.008 |
sed | -0.008 |
stem | -0.007 |
mouth | -0.007 |
Token | stopped |
Token ID | 5025 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
and | +0.124 |
ying | +0.113 |
adows | +0.112 |
as | +0.112 |
inker | +0.110 |
Neg logit contributions | |
gust | -0.091 |
mouth | -0.085 |
sed | -0.083 |
stem | -0.082 |
� | -0.082 |
Token | qu |
Token ID | 627 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
gust | +0.014 |
sed | +0.013 |
stem | +0.013 |
� | +0.013 |
mouth | +0.013 |
Neg logit contributions | |
and | -0.014 |
ying | -0.013 |
as | -0.013 |
adows | -0.012 |
pt | -0.012 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
and | +0.018 |
as | +0.016 |
ying | +0.016 |
adows | +0.015 |
os | +0.014 |
Neg logit contributions | |
gust | -0.043 |
sed | -0.042 |
stem | -0.041 |
� | -0.041 |
mouth | -0.041 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
and | +0.348 |
as | +0.329 |
adows | +0.327 |
pt | +0.308 |
iam | +0.306 |
Neg logit contributions | |
gust | -0.496 |
stem | -0.455 |
cheeks | -0.453 |
mouth | -0.445 |
timer | -0.444 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
and | +0.054 |
as | +0.052 |
ying | +0.051 |
adows | +0.050 |
inker | +0.049 |
Neg logit contributions | |
gust | -0.047 |
mouth | -0.045 |
sed | -0.044 |
stem | -0.043 |
� | -0.043 |
Token | They |
Token ID | 1119 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
and | +0.024 |
as | +0.022 |
os | +0.022 |
ying | +0.022 |
adows | +0.021 |
Neg logit contributions | |
gust | -0.017 |
stem | -0.016 |
sed | -0.016 |
timer | -0.015 |
mouth | -0.015 |
Token | decided |
Token ID | 3066 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
and | +0.018 |
ying | +0.017 |
adows | +0.017 |
inker | +0.016 |
outage | +0.016 |
Neg logit contributions | |
gust | -0.013 |
mouth | -0.012 |
stem | -0.012 |
sed | -0.012 |
cheeks | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
as | +0.060 |
and | +0.059 |
adows | +0.059 |
ibr | +0.057 |
os | +0.056 |
Neg logit contributions | |
mouth | -0.040 |
gust | -0.040 |
sed | -0.038 |
cheeks | -0.037 |
stem | -0.036 |
Token | little |
Token ID | 1310 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
as | +0.081 |
and | +0.081 |
ying | +0.077 |
adows | +0.076 |
udd | +0.075 |
Neg logit contributions | |
sed | -0.063 |
� | -0.063 |
gust | -0.061 |
stem | -0.061 |
mouth | -0.057 |
Token | birds |
Token ID | 10087 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
� | +0.012 |
gust | +0.012 |
sed | +0.012 |
stem | +0.011 |
mouth | +0.011 |
Neg logit contributions | |
and | -0.017 |
as | -0.017 |
adows | -0.016 |
ying | -0.016 |
pt | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -5.46e-03 |
Pos logit contributions | |
gust | +0.050 |
sed | +0.048 |
stem | +0.047 |
� | +0.047 |
mouth | +0.047 |
Neg logit contributions | |
and | -0.063 |
as | -0.060 |
ying | -0.060 |
adows | -0.059 |
pt | -0.057 |
Token | were |
Token ID | 547 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
and | +0.011 |
ying | +0.010 |
as | +0.010 |
adows | +0.010 |
iam | +0.010 |
Neg logit contributions | |
gust | -0.009 |
sed | -0.008 |
mouth | -0.008 |
stem | -0.008 |
� | -0.008 |
Token | qu |
Token ID | 627 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
and | +0.045 |
ying | +0.043 |
as | +0.042 |
adows | +0.042 |
os | +0.040 |
Neg logit contributions | |
gust | -0.029 |
sed | -0.028 |
stem | -0.027 |
mouth | -0.027 |
� | -0.027 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
and | +0.022 |
ying | +0.020 |
adows | +0.020 |
outage | +0.019 |
as | +0.019 |
Neg logit contributions | |
gust | -0.046 |
� | -0.044 |
stem | -0.044 |
mouth | -0.043 |
sed | -0.042 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
and | +0.382 |
adows | +0.361 |
iam | +0.351 |
as | +0.344 |
ibr | +0.344 |
Neg logit contributions | |
gust | -0.455 |
stem | -0.414 |
cheeks | -0.401 |
timer | -0.388 |
mouth | -0.386 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ying | +0.063 |
and | +0.062 |
iam | +0.062 |
adows | +0.061 |
as | +0.061 |
Neg logit contributions | |
gust | -0.039 |
mouth | -0.037 |
sed | -0.034 |
stem | -0.034 |
cheeks | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
and | +0.043 |
os | +0.040 |
as | +0.039 |
adows | +0.037 |
ying | +0.037 |
Neg logit contributions | |
gust | -0.034 |
sed | -0.033 |
stem | -0.033 |
� | -0.031 |
tongue | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
and | +0.075 |
ying | +0.074 |
as | +0.073 |
adows | +0.073 |
pt | +0.071 |
Neg logit contributions | |
gust | -0.038 |
� | -0.037 |
sed | -0.035 |
stem | -0.035 |
mouth | -0.035 |
Token | The |
Token ID | 464 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
and | +0.065 |
ying | +0.062 |
as | +0.061 |
adows | +0.061 |
pt | +0.058 |
Neg logit contributions | |
gust | -0.053 |
stem | -0.050 |
� | -0.049 |
sed | -0.049 |
mouth | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
and | +0.150 |
ying | +0.139 |
as | +0.139 |
adows | +0.139 |
inker | +0.136 |
Neg logit contributions | |
gust | -0.105 |
mouth | -0.104 |
� | -0.101 |
sed | -0.099 |
stem | -0.099 |
Token | their |
Token ID | 511 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
and | +0.078 |
ying | +0.075 |
as | +0.073 |
adows | +0.072 |
udd | +0.069 |
Neg logit contributions | |
gust | -0.061 |
sed | -0.058 |
mouth | -0.057 |
stem | -0.056 |
� | -0.055 |
Token | children |
Token ID | 1751 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
and | +0.077 |
as | +0.075 |
ying | +0.071 |
adows | +0.071 |
udd | +0.069 |
Neg logit contributions | |
gust | -0.062 |
� | -0.059 |
stem | -0.058 |
sed | -0.057 |
mouth | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
and | +0.118 |
as | +0.110 |
ying | +0.110 |
adows | +0.108 |
inker | +0.107 |
Neg logit contributions | |
gust | -0.080 |
mouth | -0.079 |
sed | -0.076 |
� | -0.076 |
stem | -0.074 |
Token | qu |
Token ID | 627 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
gust | +0.006 |
mouth | +0.006 |
sed | +0.006 |
� | +0.006 |
stem | +0.006 |
Neg logit contributions | |
and | -0.008 |
ying | -0.007 |
as | -0.007 |
adows | -0.007 |
inker | -0.007 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
and | +0.020 |
ying | +0.018 |
adows | +0.018 |
outage | +0.017 |
as | +0.017 |
Neg logit contributions | |
gust | -0.041 |
mouth | -0.040 |
� | -0.039 |
stem | -0.039 |
sed | -0.039 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
and | +0.435 |
adows | +0.418 |
ibr | +0.410 |
pt | +0.406 |
iam | +0.400 |
Neg logit contributions | |
gust | -0.364 |
timer | -0.339 |
cheeks | -0.336 |
stem | -0.329 |
lips | -0.309 |
Token | . |
Token ID | 13 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
and | +0.057 |
ying | +0.054 |
as | +0.054 |
adows | +0.053 |
outage | +0.052 |
Neg logit contributions | |
gust | -0.042 |
mouth | -0.041 |
cheeks | -0.040 |
sed | -0.039 |
stem | -0.039 |
Token | |
Token ID | 220 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
and | +0.055 |
as | +0.050 |
os | +0.050 |
ying | +0.049 |
adows | +0.049 |
Neg logit contributions | |
sed | -0.042 |
gust | -0.042 |
stem | -0.041 |
tongue | -0.037 |
cheeks | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
� | +0.039 |
gust | +0.039 |
mouth | +0.038 |
sed | +0.037 |
stem | +0.035 |
Neg logit contributions | |
and | -0.085 |
ying | -0.083 |
adows | -0.083 |
as | -0.082 |
pt | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
ying | +0.098 |
adows | +0.097 |
and | +0.095 |
pt | +0.094 |
as | +0.094 |
Neg logit contributions | |
� | -0.042 |
gust | -0.041 |
mouth | -0.037 |
stem | -0.037 |
sed | -0.035 |
Token | told |
Token ID | 1297 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
and | +0.060 |
adows | +0.058 |
ying | +0.056 |
as | +0.056 |
inker | +0.054 |
Neg logit contributions | |
gust | -0.037 |
mouth | -0.034 |
sed | -0.034 |
� | -0.033 |
stem | -0.033 |
Token | them |
Token ID | 606 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
and | +0.125 |
as | +0.119 |
ying | +0.117 |
adows | +0.117 |
os | +0.110 |
Neg logit contributions | |
gust | -0.109 |
sed | -0.102 |
mouth | -0.101 |
stem | -0.101 |
� | -0.101 |
Token | to |
Token ID | 284 |
Feature activation | -8.10e-03 |
Pos logit contributions | |
and | +0.060 |
adows | +0.059 |
as | +0.058 |
aking | +0.057 |
asc | +0.057 |
Neg logit contributions | |
mouth | -0.046 |
gust | -0.044 |
cheeks | -0.043 |
sed | -0.041 |
mouths | -0.040 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
and | +0.018 |
as | +0.018 |
ying | +0.018 |
adows | +0.017 |
pt | +0.017 |
Neg logit contributions | |
gust | -0.010 |
sed | -0.010 |
stem | -0.009 |
� | -0.009 |
mouth | -0.009 |
Token | qu |
Token ID | 627 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
and | +0.022 |
ying | +0.021 |
as | +0.021 |
adows | +0.020 |
pt | +0.019 |
Neg logit contributions | |
gust | -0.019 |
sed | -0.019 |
� | -0.018 |
stem | -0.018 |
mouth | -0.018 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
and | +0.006 |
ying | +0.005 |
as | +0.005 |
adows | +0.005 |
outage | +0.004 |
Neg logit contributions | |
gust | -0.021 |
mouth | -0.021 |
� | -0.021 |
sed | -0.020 |
stem | -0.020 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
adows | +0.418 |
and | +0.402 |
pt | +0.395 |
outage | +0.394 |
iam | +0.393 |
Neg logit contributions | |
gust | -0.355 |
timer | -0.344 |
cheeks | -0.338 |
lips | -0.316 |
stem | -0.313 |
Token | and |
Token ID | 290 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
adows | +0.276 |
and | +0.273 |
asc | +0.270 |
inker | +0.269 |
iam | +0.267 |
Neg logit contributions | |
mouth | -0.140 |
gust | -0.129 |
cheeks | -0.129 |
tongue | -0.121 |
sed | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -6.55e-03 |
Pos logit contributions | |
and | +0.052 |
ying | +0.049 |
as | +0.049 |
adows | +0.048 |
pt | +0.046 |
Neg logit contributions | |
gust | -0.041 |
sed | -0.040 |
� | -0.039 |
stem | -0.039 |
mouth | -0.038 |
Token | share |
Token ID | 2648 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
and | +0.014 |
as | +0.013 |
ying | +0.013 |
adows | +0.013 |
os | +0.012 |
Neg logit contributions | |
gust | -0.010 |
sed | -0.009 |
stem | -0.009 |
mouth | -0.009 |
� | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
mouth | +0.037 |
stem | +0.035 |
gust | +0.035 |
� | +0.033 |
cheeks | +0.033 |
Neg logit contributions | |
and | -0.053 |
adows | -0.052 |
ying | -0.051 |
as | -0.051 |
outage | -0.051 |
Token | other |
Token ID | 584 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
gust | +0.001 |
mouth | +0.001 |
stem | +0.001 |
� | +0.001 |
sed | +0.001 |
Neg logit contributions | |
and | -0.002 |
as | -0.002 |
adows | -0.002 |
ying | -0.001 |
udd | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
and | +0.024 |
ying | +0.023 |
asc | +0.023 |
as | +0.023 |
adows | +0.023 |
Neg logit contributions | |
mouth | -0.015 |
gust | -0.015 |
cheeks | -0.014 |
sed | -0.014 |
tongue | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
and | +0.047 |
os | +0.042 |
as | +0.040 |
ying | +0.039 |
sorts | +0.039 |
Neg logit contributions | |
gust | -0.037 |
stem | -0.035 |
sed | -0.033 |
timer | -0.031 |
cheeks | -0.031 |
Token | starting |
Token ID | 3599 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
and | +0.024 |
ying | +0.022 |
adows | +0.022 |
as | +0.021 |
asc | +0.021 |
Neg logit contributions | |
gust | -0.014 |
mouth | -0.013 |
cheeks | -0.013 |
sed | -0.013 |
stem | -0.012 |
Token | qu |
Token ID | 627 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
gust | +0.090 |
mouth | +0.089 |
sed | +0.089 |
� | +0.086 |
stem | +0.086 |
Neg logit contributions | |
and | -0.091 |
as | -0.087 |
ying | -0.087 |
adows | -0.086 |
udd | -0.081 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
and | +0.013 |
ying | +0.012 |
outage | +0.011 |
adows | +0.011 |
as | +0.010 |
Neg logit contributions | |
gust | -0.040 |
mouth | -0.038 |
� | -0.038 |
stem | -0.037 |
sed | -0.037 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
adows | +0.375 |
and | +0.370 |
iam | +0.359 |
ibr | +0.354 |
outage | +0.352 |
Neg logit contributions | |
gust | -0.422 |
cheeks | -0.378 |
timer | -0.356 |
mouth | -0.353 |
stem | -0.352 |
Token | again |
Token ID | 757 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
and | +0.049 |
as | +0.049 |
adows | +0.049 |
ying | +0.049 |
asc | +0.048 |
Neg logit contributions | |
gust | -0.035 |
mouth | -0.035 |
cheeks | -0.033 |
sed | -0.032 |
tongue | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
gust | +0.019 |
mouth | +0.019 |
stem | +0.018 |
� | +0.017 |
sed | +0.017 |
Neg logit contributions | |
ying | -0.028 |
and | -0.028 |
as | -0.028 |
asc | -0.027 |
iam | -0.027 |
Token | their |
Token ID | 511 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
and | +0.063 |
ying | +0.060 |
as | +0.060 |
adows | +0.058 |
os | +0.056 |
Neg logit contributions | |
gust | -0.058 |
sed | -0.056 |
� | -0.055 |
stem | -0.055 |
mouth | -0.054 |
Token | voices |
Token ID | 10839 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
and | +0.062 |
as | +0.061 |
pt | +0.057 |
ying | +0.057 |
adows | +0.057 |
Neg logit contributions | |
gust | -0.051 |
stem | -0.050 |
� | -0.050 |
mouth | -0.048 |
sed | -0.048 |
Token | two |
Token ID | 734 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
gust | +0.052 |
sed | +0.051 |
stem | +0.050 |
mouth | +0.049 |
� | +0.049 |
Neg logit contributions | |
and | -0.081 |
as | -0.077 |
ying | -0.077 |
adows | -0.075 |
pt | -0.072 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
and | +0.093 |
ying | +0.087 |
adows | +0.086 |
as | +0.086 |
outage | +0.082 |
Neg logit contributions | |
gust | -0.069 |
sed | -0.064 |
mouth | -0.063 |
� | -0.063 |
stem | -0.062 |
Token | s |
Token ID | 82 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
sed | +0.077 |
mouth | +0.077 |
gust | +0.076 |
� | +0.073 |
cheeks | +0.069 |
Neg logit contributions | |
and | -0.139 |
ying | -0.127 |
outage | -0.127 |
adows | -0.126 |
inker | -0.125 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
and | +0.006 |
ying | +0.006 |
as | +0.006 |
adows | +0.005 |
outage | +0.005 |
Neg logit contributions | |
gust | -0.005 |
sed | -0.005 |
mouth | -0.005 |
� | -0.005 |
stem | -0.004 |
Token | qu |
Token ID | 627 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
gust | +0.022 |
sed | +0.021 |
mouth | +0.021 |
� | +0.021 |
stem | +0.021 |
Neg logit contributions | |
and | -0.030 |
as | -0.028 |
ying | -0.028 |
adows | -0.028 |
udd | -0.026 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
outage | +0.017 |
and | +0.017 |
ying | +0.016 |
adows | +0.015 |
pt | +0.015 |
Neg logit contributions | |
gust | -0.028 |
� | -0.028 |
mouth | -0.027 |
stem | -0.026 |
lips | -0.025 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
pt | +0.411 |
outage | +0.408 |
ibr | +0.404 |
and | +0.403 |
asc | +0.402 |
Neg logit contributions | |
gust | -0.337 |
cheeks | -0.324 |
timer | -0.308 |
lips | -0.297 |
stem | -0.292 |
Token | until |
Token ID | 1566 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ying | +0.054 |
outage | +0.053 |
and | +0.053 |
adows | +0.052 |
as | +0.052 |
Neg logit contributions | |
mouth | -0.039 |
gust | -0.039 |
cheeks | -0.038 |
stem | -0.036 |
sed | -0.036 |
Token | finally |
Token ID | 3443 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
sed | +0.022 |
gust | +0.021 |
stem | +0.021 |
mouth | +0.020 |
� | +0.020 |
Neg logit contributions | |
and | -0.027 |
ying | -0.026 |
as | -0.026 |
adows | -0.025 |
pt | -0.025 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
gust | +0.046 |
mouth | +0.043 |
cheeks | +0.039 |
sed | +0.038 |
� | +0.037 |
Neg logit contributions | |
and | -0.110 |
as | -0.104 |
adows | -0.103 |
outage | -0.101 |
ying | -0.101 |
Token | said |
Token ID | 531 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
and | +0.085 |
ying | +0.082 |
adows | +0.080 |
as | +0.079 |
outage | +0.077 |
Neg logit contributions | |
gust | -0.051 |
mouth | -0.048 |
� | -0.047 |
sed | -0.047 |
cheeks | -0.044 |
Token | â |
Token ID | 22940 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
and | +0.091 |
adows | +0.089 |
as | +0.088 |
ying | +0.087 |
udd | +0.085 |
Neg logit contributions | |
gust | -0.029 |
� | -0.029 |
stem | -0.022 |
sed | -0.022 |
mouth | -0.022 |
Token | € |
Token ID | 26391 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
and | +0.182 |
ying | +0.171 |
as | +0.171 |
adows | +0.167 |
os | +0.158 |
Neg logit contributions | |
gust | -0.199 |
sed | -0.193 |
stem | -0.189 |
mouth | -0.189 |
� | -0.187 |
Token | ™ |
Token ID | 8151 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
� | +0.019 |
gust | +0.019 |
mouth | +0.018 |
sed | +0.018 |
cheeks | +0.017 |
Neg logit contributions | |
ying | -0.017 |
and | -0.017 |
pt | -0.016 |
as | -0.016 |
sorts | -0.016 |
Token | t |
Token ID | 83 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
and | +0.169 |
adows | +0.163 |
ying | +0.163 |
as | +0.158 |
inker | +0.156 |
Neg logit contributions | |
gust | -0.161 |
� | -0.157 |
mouth | -0.152 |
sed | -0.150 |
stem | -0.145 |
Token | qu |
Token ID | 627 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
and | +0.067 |
adows | +0.065 |
ying | +0.064 |
udd | +0.063 |
inker | +0.063 |
Neg logit contributions | |
gust | -0.051 |
mouth | -0.046 |
stem | -0.044 |
tongue | -0.044 |
cheeks | -0.040 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
and | +0.014 |
ying | +0.012 |
adows | +0.012 |
outage | +0.012 |
as | +0.011 |
Neg logit contributions | |
gust | -0.041 |
� | -0.040 |
mouth | -0.039 |
stem | -0.038 |
sed | -0.037 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
and | +0.405 |
adows | +0.380 |
vern | +0.362 |
ibr | +0.362 |
as | +0.355 |
Neg logit contributions | |
gust | -0.429 |
cheeks | -0.390 |
stem | -0.351 |
mouth | -0.349 |
timer | -0.349 |
Token | , |
Token ID | 11 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
and | +0.050 |
as | +0.048 |
adows | +0.048 |
aking | +0.046 |
ying | +0.046 |
Neg logit contributions | |
gust | -0.029 |
mouth | -0.029 |
cheeks | -0.027 |
sed | -0.025 |
stem | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
gust | +0.014 |
mouth | +0.013 |
� | +0.012 |
sed | +0.012 |
stem | +0.012 |
Neg logit contributions | |
and | -0.026 |
adows | -0.024 |
as | -0.024 |
ying | -0.024 |
inker | -0.023 |
Token | furniture |
Token ID | 13091 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
and | +0.006 |
ying | +0.005 |
as | +0.005 |
adows | +0.005 |
os | +0.005 |
Neg logit contributions | |
gust | -0.004 |
sed | -0.004 |
mouth | -0.004 |
stem | -0.004 |
� | -0.004 |
Token | stayed |
Token ID | 9658 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
and | +0.212 |
ying | +0.195 |
as | +0.195 |
adows | +0.195 |
inker | +0.186 |
Neg logit contributions | |
gust | -0.151 |
sed | -0.143 |
mouth | -0.143 |
� | -0.141 |
stem | -0.139 |
Token | peaceful |
Token ID | 12309 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
and | +0.019 |
ying | +0.018 |
adows | +0.018 |
as | +0.018 |
iam | +0.017 |
Neg logit contributions | |
gust | -0.014 |
mouth | -0.012 |
stem | -0.012 |
sed | -0.012 |
� | -0.012 |
Token | everyone |
Token ID | 2506 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
as | +0.062 |
and | +0.062 |
iam | +0.058 |
adows | +0.058 |
ibr | +0.058 |
Neg logit contributions | |
gust | -0.039 |
sed | -0.037 |
mouth | -0.036 |
� | -0.036 |
stem | -0.036 |
Token | just |
Token ID | 655 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
and | +0.133 |
inker | +0.132 |
adows | +0.127 |
as | +0.126 |
iam | +0.125 |
Neg logit contributions | |
gust | -0.098 |
mouth | -0.094 |
sed | -0.090 |
stem | -0.089 |
cheeks | -0.088 |
Token | stopped |
Token ID | 5025 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
gust | +0.055 |
sed | +0.053 |
mouth | +0.052 |
stem | +0.051 |
� | +0.050 |
Neg logit contributions | |
and | -0.063 |
as | -0.060 |
ying | -0.059 |
adows | -0.057 |
inker | -0.056 |
Token | qu |
Token ID | 627 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
gust | +0.011 |
sed | +0.011 |
� | +0.011 |
stem | +0.011 |
mouth | +0.010 |
Neg logit contributions | |
and | -0.011 |
ying | -0.011 |
as | -0.011 |
adows | -0.010 |
os | -0.010 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
and | +0.018 |
ying | +0.016 |
as | +0.016 |
adows | +0.015 |
outage | +0.014 |
Neg logit contributions | |
gust | -0.043 |
� | -0.041 |
mouth | -0.041 |
stem | -0.041 |
sed | -0.040 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
and | +0.401 |
adows | +0.381 |
iam | +0.375 |
as | +0.374 |
ibr | +0.362 |
Neg logit contributions | |
gust | -0.419 |
cheeks | -0.372 |
timer | -0.369 |
stem | -0.365 |
mouth | -0.348 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
and | +0.056 |
as | +0.055 |
ying | +0.055 |
adows | +0.055 |
udd | +0.054 |
Neg logit contributions | |
gust | -0.036 |
mouth | -0.035 |
stem | -0.033 |
cheeks | -0.032 |
sed | -0.031 |
Token | |
Token ID | 220 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
and | +0.052 |
as | +0.049 |
ying | +0.049 |
adows | +0.048 |
os | +0.046 |
Neg logit contributions | |
gust | -0.029 |
sed | -0.028 |
stem | -0.027 |
� | -0.027 |
mouth | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
gust | +0.050 |
� | +0.049 |
sed | +0.048 |
mouth | +0.047 |
stem | +0.046 |
Neg logit contributions | |
and | -0.090 |
ying | -0.086 |
as | -0.086 |
adows | -0.085 |
pt | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ying | +0.080 |
adows | +0.078 |
as | +0.077 |
pt | +0.076 |
and | +0.076 |
Neg logit contributions | |
� | -0.026 |
gust | -0.025 |
mouth | -0.024 |
sed | -0.022 |
stem | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
gust | +0.001 |
mouth | +0.001 |
sed | +0.001 |
cheeks | +0.001 |
tongue | +0.001 |
Neg logit contributions | |
and | -0.002 |
adows | -0.002 |
as | -0.002 |
ying | -0.002 |
ibr | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
and | +0.069 |
as | +0.065 |
ying | +0.065 |
adows | +0.064 |
os | +0.061 |
Neg logit contributions | |
gust | -0.043 |
sed | -0.041 |
mouth | -0.040 |
stem | -0.039 |
� | -0.039 |
Token | both |
Token ID | 1111 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
and | +0.075 |
ying | +0.070 |
adows | +0.068 |
as | +0.065 |
udd | +0.064 |
Neg logit contributions | |
gust | -0.046 |
sed | -0.042 |
mouth | -0.041 |
cheeks | -0.040 |
stem | -0.039 |
Token | stopped |
Token ID | 5025 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
gust | +0.044 |
mouth | +0.041 |
sed | +0.041 |
cheeks | +0.039 |
stem | +0.038 |
Neg logit contributions | |
and | -0.071 |
ying | -0.068 |
adows | -0.064 |
as | -0.063 |
inker | -0.063 |
Token | qu |
Token ID | 627 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
gust | +0.014 |
sed | +0.013 |
stem | +0.013 |
� | +0.013 |
mouth | +0.013 |
Neg logit contributions | |
and | -0.015 |
as | -0.014 |
ying | -0.014 |
adows | -0.013 |
os | -0.013 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
and | +0.012 |
ying | +0.011 |
as | +0.010 |
adows | +0.010 |
outage | +0.009 |
Neg logit contributions | |
gust | -0.034 |
mouth | -0.033 |
� | -0.033 |
sed | -0.033 |
stem | -0.033 |
Token | lling |
Token ID | 2680 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
and | +0.341 |
adows | +0.331 |
as | +0.319 |
iam | +0.309 |
pt | +0.302 |
Neg logit contributions | |
gust | -0.478 |
cheeks | -0.434 |
timer | -0.429 |
stem | -0.428 |
mouth | -0.419 |
Token | to |
Token ID | 284 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
and | +0.265 |
adows | +0.260 |
as | +0.255 |
ying | +0.254 |
iam | +0.251 |
Neg logit contributions | |
gust | -0.161 |
mouth | -0.160 |
sed | -0.154 |
cheeks | -0.145 |
tongue | -0.141 |
Token | look |
Token ID | 804 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
and | +0.025 |
as | +0.023 |
ying | +0.023 |
adows | +0.023 |
pt | +0.022 |
Neg logit contributions | |
gust | -0.024 |
sed | -0.023 |
� | -0.023 |
stem | -0.023 |
mouth | -0.023 |
Token | at |
Token ID | 379 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
and | +0.073 |
adows | +0.070 |
as | +0.069 |
iam | +0.067 |
inker | +0.067 |
Neg logit contributions | |
gust | -0.044 |
mouth | -0.042 |
sed | -0.035 |
lips | -0.034 |
cheeks | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
gust | +0.042 |
mouth | +0.041 |
sed | +0.040 |
stem | +0.038 |
� | +0.038 |
Neg logit contributions | |
and | -0.071 |
as | -0.066 |
adows | -0.066 |
ying | -0.065 |
aking | -0.064 |
Token | One |
Token ID | 3198 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
and | +0.080 |
ying | +0.080 |
adows | +0.078 |
pt | +0.078 |
as | +0.078 |
Neg logit contributions | |
gust | -0.059 |
� | -0.056 |
stem | -0.053 |
mouth | -0.052 |
timer | -0.050 |
Token | day |
Token ID | 1110 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
gust | +0.049 |
sed | +0.048 |
� | +0.046 |
stem | +0.046 |
mouth | +0.045 |
Neg logit contributions | |
and | -0.072 |
as | -0.068 |
ying | -0.068 |
adows | -0.067 |
os | -0.065 |
Token | they |
Token ID | 484 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
gust | +0.043 |
sed | +0.040 |
mouth | +0.040 |
� | +0.040 |
stem | +0.039 |
Neg logit contributions | |
and | -0.066 |
as | -0.063 |
ying | -0.063 |
adows | -0.062 |
udd | -0.059 |
Token | were |
Token ID | 547 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
and | +0.079 |
adows | +0.076 |
outage | +0.076 |
ying | +0.076 |
vern | +0.073 |
Neg logit contributions | |
gust | -0.052 |
mouth | -0.047 |
� | -0.046 |
stem | -0.044 |
sed | -0.043 |
Token | qu |
Token ID | 627 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
and | +0.039 |
as | +0.038 |
ying | +0.037 |
adows | +0.036 |
os | +0.035 |
Neg logit contributions | |
gust | -0.033 |
stem | -0.032 |
� | -0.032 |
sed | -0.031 |
mouth | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
and | +0.011 |
ying | +0.009 |
as | +0.009 |
adows | +0.009 |
pt | +0.008 |
Neg logit contributions | |
gust | -0.042 |
� | -0.040 |
stem | -0.040 |
mouth | -0.040 |
sed | -0.040 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
and | +0.398 |
adows | +0.378 |
as | +0.362 |
vern | +0.358 |
pt | +0.356 |
Neg logit contributions | |
gust | -0.423 |
cheeks | -0.371 |
stem | -0.370 |
timer | -0.367 |
mouth | -0.356 |
Token | over |
Token ID | 625 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
and | +0.049 |
as | +0.047 |
ying | +0.047 |
adows | +0.046 |
outage | +0.044 |
Neg logit contributions | |
gust | -0.040 |
mouth | -0.038 |
sed | -0.038 |
� | -0.037 |
stem | -0.036 |
Token | who |
Token ID | 508 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
and | +0.074 |
as | +0.069 |
ying | +0.069 |
adows | +0.068 |
os | +0.065 |
Neg logit contributions | |
gust | -0.066 |
sed | -0.064 |
stem | -0.063 |
� | -0.062 |
mouth | -0.062 |
Token | should |
Token ID | 815 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
gust | +0.003 |
sed | +0.003 |
mouth | +0.003 |
� | +0.003 |
stem | +0.003 |
Neg logit contributions | |
and | -0.005 |
ying | -0.004 |
adows | -0.004 |
as | -0.004 |
inker | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
gust | +0.014 |
sed | +0.013 |
stem | +0.013 |
� | +0.013 |
mouth | +0.013 |
Neg logit contributions | |
and | -0.020 |
as | -0.019 |
ying | -0.019 |
adows | -0.019 |
pt | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
and | +0.004 |
as | +0.004 |
ying | +0.004 |
adows | +0.004 |
udd | +0.004 |
Neg logit contributions | |
gust | -0.003 |
mouth | -0.003 |
stem | -0.003 |
sed | -0.003 |
� | -0.002 |
Token | birds |
Token ID | 10087 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
gust | +0.002 |
� | +0.002 |
sed | +0.002 |
mouth | +0.002 |
stem | +0.002 |
Neg logit contributions | |
and | -0.003 |
as | -0.003 |
udd | -0.003 |
adows | -0.003 |
ying | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
gust | +0.051 |
sed | +0.047 |
mouth | +0.047 |
� | +0.047 |
stem | +0.046 |
Neg logit contributions | |
and | -0.066 |
as | -0.059 |
iam | -0.059 |
adows | -0.059 |
inker | -0.058 |
Token | only |
Token ID | 691 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
and | +0.035 |
as | +0.032 |
adows | +0.032 |
ying | +0.032 |
os | +0.032 |
Neg logit contributions | |
gust | -0.026 |
sed | -0.025 |
mouth | -0.025 |
stem | -0.024 |
tongue | -0.022 |
Token | qu |
Token ID | 627 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
mouth | +0.078 |
gust | +0.077 |
sed | +0.076 |
stem | +0.073 |
tongue | +0.069 |
Neg logit contributions | |
and | -0.103 |
ying | -0.099 |
inker | -0.095 |
as | -0.095 |
adows | -0.095 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
and | +0.014 |
ying | +0.013 |
outage | +0.013 |
adows | +0.012 |
iam | +0.011 |
Neg logit contributions | |
gust | -0.041 |
� | -0.040 |
mouth | -0.039 |
stem | -0.039 |
sed | -0.038 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
and | +0.418 |
iam | +0.398 |
adows | +0.395 |
ibr | +0.393 |
asc | +0.381 |
Neg logit contributions | |
gust | -0.407 |
cheeks | -0.355 |
stem | -0.350 |
mouth | -0.339 |
tongue | -0.331 |
Token | like |
Token ID | 588 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
iam | +0.052 |
and | +0.052 |
inker | +0.050 |
ying | +0.050 |
asc | +0.050 |
Neg logit contributions | |
gust | -0.034 |
mouth | -0.033 |
sed | -0.030 |
stem | -0.030 |
cheeks | -0.030 |
Token | little |
Token ID | 1310 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
and | +0.030 |
as | +0.028 |
ying | +0.028 |
adows | +0.028 |
os | +0.027 |
Neg logit contributions | |
gust | -0.022 |
sed | -0.021 |
stem | -0.021 |
� | -0.021 |
mouth | -0.021 |
Token | children |
Token ID | 1751 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
gust | +0.020 |
sed | +0.019 |
� | +0.019 |
stem | +0.019 |
mouth | +0.018 |
Neg logit contributions | |
and | -0.031 |
as | -0.030 |
ying | -0.030 |
adows | -0.029 |
pt | -0.028 |
Token | do |
Token ID | 466 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
and | +0.103 |
inker | +0.100 |
iam | +0.098 |
ying | +0.097 |
asc | +0.096 |
Neg logit contributions | |
mouth | -0.062 |
gust | -0.060 |
sed | -0.057 |
cheeks | -0.056 |
� | -0.056 |
Token | but |
Token ID | 475 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
gust | +0.011 |
sed | +0.011 |
mouth | +0.011 |
stem | +0.011 |
� | +0.011 |
Neg logit contributions | |
and | -0.012 |
ying | -0.011 |
as | -0.011 |
adows | -0.011 |
pt | -0.011 |
Token | today |
Token ID | 1909 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
and | +0.016 |
as | +0.015 |
ying | +0.015 |
os | +0.015 |
sorts | +0.015 |
Neg logit contributions | |
gust | -0.016 |
� | -0.016 |
stem | -0.016 |
sed | -0.016 |
cheeks | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
and | +0.056 |
ying | +0.054 |
as | +0.053 |
adows | +0.052 |
os | +0.051 |
Neg logit contributions | |
gust | -0.045 |
sed | -0.045 |
stem | -0.044 |
� | -0.042 |
mouth | -0.041 |
Token | were |
Token ID | 547 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
and | +0.069 |
ying | +0.061 |
adows | +0.061 |
as | +0.060 |
outage | +0.058 |
Neg logit contributions | |
gust | -0.047 |
� | -0.044 |
sed | -0.044 |
mouth | -0.043 |
stem | -0.043 |
Token | qu |
Token ID | 627 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
and | +0.034 |
as | +0.032 |
ying | +0.032 |
adows | +0.031 |
os | +0.030 |
Neg logit contributions | |
gust | -0.032 |
sed | -0.031 |
� | -0.031 |
stem | -0.031 |
mouth | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
and | +0.014 |
ying | +0.012 |
adows | +0.012 |
outage | +0.011 |
as | +0.011 |
Neg logit contributions | |
gust | -0.042 |
� | -0.041 |
stem | -0.040 |
mouth | -0.040 |
sed | -0.039 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
and | +0.418 |
adows | +0.390 |
iam | +0.380 |
as | +0.378 |
pt | +0.375 |
Neg logit contributions | |
gust | -0.399 |
stem | -0.348 |
cheeks | -0.344 |
timer | -0.339 |
mouth | -0.324 |
Token | . |
Token ID | 13 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
and | +0.050 |
ying | +0.048 |
as | +0.047 |
inker | +0.046 |
adows | +0.046 |
Neg logit contributions | |
mouth | -0.033 |
gust | -0.033 |
sed | -0.031 |
cheeks | -0.030 |
stem | -0.029 |
Token | They |
Token ID | 1119 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
and | +0.047 |
os | +0.046 |
as | +0.045 |
adows | +0.045 |
sorts | +0.042 |
Neg logit contributions | |
gust | -0.050 |
stem | -0.047 |
� | -0.046 |
sed | -0.045 |
timer | -0.044 |
Token | were |
Token ID | 547 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
and | +0.017 |
ying | +0.015 |
as | +0.015 |
adows | +0.015 |
outage | +0.014 |
Neg logit contributions | |
gust | -0.014 |
sed | -0.013 |
stem | -0.013 |
mouth | -0.013 |
� | -0.013 |
Token | arguing |
Token ID | 11810 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
and | +0.033 |
as | +0.032 |
ying | +0.031 |
adows | +0.031 |
pt | +0.029 |
Neg logit contributions | |
gust | -0.031 |
sed | -0.030 |
� | -0.030 |
stem | -0.029 |
mouth | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
and | +0.002 |
as | +0.002 |
adows | +0.002 |
ying | +0.002 |
os | +0.002 |
Neg logit contributions | |
gust | -0.002 |
mouth | -0.002 |
sed | -0.002 |
stem | -0.002 |
� | -0.002 |
Token | why |
Token ID | 1521 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
gust | +0.015 |
mouth | +0.014 |
sed | +0.014 |
stem | +0.013 |
� | +0.013 |
Neg logit contributions | |
and | -0.030 |
adows | -0.028 |
as | -0.028 |
ying | -0.028 |
pt | -0.027 |
Token | are |
Token ID | 389 |
Feature activation | -6.61e-02 |
Pos logit contributions | |
and | +0.116 |
adows | +0.099 |
year | +0.098 |
col | +0.096 |
iam | +0.096 |
Neg logit contributions | |
mouth | -0.080 |
gust | -0.076 |
sed | -0.070 |
cheeks | -0.068 |
stem | -0.067 |
Token | you |
Token ID | 345 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
and | +0.146 |
as | +0.139 |
ying | +0.139 |
adows | +0.136 |
os | +0.131 |
Neg logit contributions | |
gust | -0.087 |
sed | -0.084 |
stem | -0.082 |
� | -0.082 |
mouth | -0.081 |
Token | qu |
Token ID | 627 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
gust | +0.015 |
mouth | +0.015 |
sed | +0.014 |
stem | +0.014 |
� | +0.014 |
Neg logit contributions | |
and | -0.021 |
adows | -0.019 |
as | -0.019 |
ying | -0.019 |
sorts | -0.018 |
Token | arre |
Token ID | 9624 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
and | +0.012 |
ying | +0.010 |
adows | +0.010 |
as | +0.009 |
outage | +0.009 |
Neg logit contributions | |
gust | -0.038 |
� | -0.037 |
mouth | -0.037 |
stem | -0.036 |
sed | -0.036 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
and | +0.409 |
adows | +0.377 |
ibr | +0.375 |
iam | +0.365 |
pt | +0.358 |
Neg logit contributions | |
gust | -0.393 |
cheeks | -0.346 |
stem | -0.345 |
lips | -0.337 |
mouth | -0.334 |
Token | ?" |
Token ID | 1701 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
and | +0.050 |
as | +0.045 |
adows | +0.045 |
ibr | +0.044 |
ying | +0.043 |
Neg logit contributions | |
mouth | -0.042 |
gust | -0.041 |
stem | -0.039 |
sed | -0.037 |
grape | -0.036 |
Token | But |
Token ID | 887 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
and | +0.107 |
os | +0.099 |
adows | +0.098 |
smart | +0.094 |
sorts | +0.093 |
Neg logit contributions | |
sed | -0.076 |
gust | -0.075 |
stem | -0.073 |
timer | -0.064 |
cheeks | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -2.85e-04 |
Pos logit contributions | |
gust | +0.067 |
sed | +0.067 |
stem | +0.066 |
� | +0.065 |
cheeks | +0.061 |
Neg logit contributions | |
and | -0.068 |
ying | -0.067 |
as | -0.064 |
adows | -0.064 |
pt | -0.062 |
Token | birds |
Token ID | 10087 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
as | +0.001 |
and | +0.001 |
adows | +0.000 |
ying | +0.000 |
aking | +0.000 |
Neg logit contributions | |
� | -0.000 |
sed | -0.000 |
gust | -0.000 |
mouth | -0.000 |
stem | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
gust | +0.069 |
sed | +0.067 |
stem | +0.065 |
cheeks | +0.061 |
timer | +0.060 |
Neg logit contributions | |
and | -0.102 |
ying | -0.092 |
as | -0.091 |
os | -0.090 |
iam | -0.089 |
Token | sp |
Token ID | 599 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
gust | +0.076 |
� | +0.075 |
stem | +0.069 |
sed | +0.067 |
cheeks | +0.064 |
Neg logit contributions | |
as | -0.065 |
pt | -0.064 |
and | -0.063 |
ying | -0.061 |
os | -0.061 |
Token | its |
Token ID | 896 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
and | +0.169 |
adows | +0.159 |
sorts | +0.151 |
outage | +0.149 |
smart | +0.148 |
Neg logit contributions | |
gust | -0.150 |
stem | -0.143 |
sed | -0.141 |
mouth | -0.139 |
cheeks | -0.138 |
Token | out |
Token ID | 503 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
and | +0.062 |
adows | +0.060 |
as | +0.058 |
ying | +0.058 |
inker | +0.057 |
Neg logit contributions | |
gust | -0.035 |
mouth | -0.034 |
stem | -0.032 |
sed | -0.031 |
tongue | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +3.39e-03 |
Pos logit contributions | |
mouth | +0.017 |
gust | +0.017 |
stem | +0.016 |
tongue | +0.015 |
grape | +0.015 |
Neg logit contributions | |
and | -0.034 |
adows | -0.033 |
as | -0.032 |
ying | -0.032 |
inker | -0.031 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
gust | +0.005 |
Really | +0.004 |
� | +0.004 |
sidelines | +0.004 |
stem | +0.004 |
Neg logit contributions | |
and | -0.007 |
as | -0.006 |
reat | -0.006 |
pt | -0.006 |
ont | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
gust | +0.216 |
sed | +0.209 |
stem | +0.205 |
mouth | +0.205 |
� | +0.204 |
Neg logit contributions | |
and | -0.231 |
as | -0.217 |
ying | -0.216 |
adows | -0.213 |
os | -0.202 |
Token | He |
Token ID | 679 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
gust | +0.075 |
sed | +0.072 |
stem | +0.070 |
cheeks | +0.066 |
� | +0.066 |
Neg logit contributions | |
and | -0.094 |
ying | -0.082 |
as | -0.081 |
os | -0.080 |
iam | -0.079 |
Token | says |
Token ID | 1139 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
gust | +0.072 |
� | +0.072 |
stem | +0.066 |
sed | +0.065 |
cheeks | +0.062 |
Neg logit contributions | |
as | -0.060 |
pt | -0.059 |
and | -0.059 |
ying | -0.058 |
udd | -0.057 |
Token | o |
Token ID | 267 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
gust | +0.111 |
� | +0.109 |
sed | +0.108 |
stem | +0.107 |
cheeks | +0.100 |
Neg logit contributions | |
and | -0.136 |
ying | -0.129 |
as | -0.128 |
pt | -0.126 |
os | -0.123 |
Token | uch |
Token ID | 794 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
gust | +0.004 |
sed | +0.004 |
stem | +0.004 |
mouth | +0.004 |
cheeks | +0.004 |
Neg logit contributions | |
and | -0.004 |
as | -0.004 |
ying | -0.003 |
adows | -0.003 |
os | -0.003 |
Token | pirate |
Token ID | 25868 |
Feature activation | +7.06e-04 |
Pos logit contributions | |
� | +0.021 |
gust | +0.021 |
stem | +0.021 |
sed | +0.021 |
mouth | +0.020 |
Neg logit contributions | |
and | -0.020 |
as | -0.019 |
adows | -0.019 |
ying | -0.018 |
udd | -0.018 |
Token | captain |
Token ID | 10654 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
mouth | +0.001 |
gust | +0.001 |
sed | +0.001 |
stem | +0.001 |
� | +0.001 |
Neg logit contributions | |
and | -0.001 |
ying | -0.001 |
as | -0.001 |
adows | -0.001 |
udd | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
and | +0.121 |
ying | +0.119 |
as | +0.115 |
udd | +0.114 |
adows | +0.112 |
Neg logit contributions | |
mouth | -0.089 |
gust | -0.088 |
sed | -0.084 |
stem | -0.083 |
� | -0.081 |
Token | The |
Token ID | 383 |
Feature activation | +4.65e-02 |
Pos logit contributions | |
and | +0.004 |
as | +0.003 |
ying | +0.003 |
adows | +0.003 |
os | +0.003 |
Neg logit contributions | |
gust | -0.003 |
sed | -0.003 |
stem | -0.003 |
cheeks | -0.002 |
mouth | -0.002 |
Token | par |
Token ID | 1582 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
gust | +0.080 |
� | +0.080 |
sed | +0.078 |
stem | +0.076 |
cheeks | +0.073 |
Neg logit contributions | |
and | -0.082 |
as | -0.078 |
iam | -0.076 |
ying | -0.075 |
adows | -0.075 |
Token | rot |
Token ID | 10599 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
gust | +0.127 |
stem | +0.118 |
sed | +0.117 |
mouth | +0.116 |
cheeks | +0.116 |
Neg logit contributions | |
and | -0.135 |
as | -0.133 |
ying | -0.123 |
adows | -0.119 |
inker | -0.119 |
Token | would |
Token ID | 561 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
mouth | +0.137 |
sed | +0.136 |
gust | +0.131 |
stem | +0.128 |
cheeks | +0.123 |
Neg logit contributions | |
and | -0.236 |
ying | -0.226 |
inker | -0.215 |
adows | -0.213 |
asc | -0.212 |
Token | act |
Token ID | 719 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
and | +0.061 |
ying | +0.060 |
as | +0.058 |
adows | +0.056 |
udd | +0.055 |
Neg logit contributions | |
gust | -0.034 |
stem | -0.034 |
sed | -0.033 |
mouth | -0.033 |
� | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
asc | +0.071 |
ying | +0.069 |
os | +0.065 |
beh | +0.064 |
and | +0.064 |
Neg logit contributions | |
gust | -0.052 |
mouth | -0.048 |
face | -0.045 |
cheeks | -0.043 |
lips | -0.042 |
Token | part |
Token ID | 636 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
and | +0.049 |
ying | +0.047 |
as | +0.046 |
adows | +0.044 |
os | +0.044 |
Neg logit contributions | |
gust | -0.035 |
sed | -0.035 |
mouth | -0.034 |
stem | -0.033 |
cheeks | -0.032 |
Token | too |
Token ID | 1165 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
and | +0.064 |
asc | +0.064 |
ying | +0.063 |
inker | +0.062 |
as | +0.062 |
Neg logit contributions | |
mouth | -0.064 |
gust | -0.062 |
stem | -0.060 |
sed | -0.059 |
cheeks | -0.058 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
� | +0.027 |
gust | +0.027 |
stem | +0.025 |
sed | +0.024 |
mouth | +0.022 |
Neg logit contributions | |
and | -0.047 |
as | -0.046 |
adows | -0.044 |
pt | -0.044 |
ying | -0.044 |
Token | found |
Token ID | 1043 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
and | +0.120 |
ying | +0.111 |
as | +0.111 |
inker | +0.108 |
outage | +0.108 |
Neg logit contributions | |
gust | -0.072 |
mouth | -0.068 |
sed | -0.065 |
� | -0.063 |
cheeks | -0.062 |
Token | him |
Token ID | 683 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
gust | +0.003 |
mouth | +0.003 |
sed | +0.003 |
stem | +0.003 |
� | +0.003 |
Neg logit contributions | |
and | -0.004 |
as | -0.004 |
adows | -0.004 |
ying | -0.004 |
outage | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
mouth | +0.074 |
gust | +0.072 |
sed | +0.071 |
stem | +0.068 |
� | +0.068 |
Neg logit contributions | |
and | -0.087 |
as | -0.086 |
ying | -0.085 |
inker | -0.082 |
adows | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
and | +0.059 |
as | +0.058 |
ying | +0.057 |
adows | +0.056 |
os | +0.053 |
Neg logit contributions | |
gust | -0.039 |
mouth | -0.037 |
� | -0.036 |
stem | -0.036 |
sed | -0.036 |
Token | branch |
Token ID | 8478 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
and | +0.003 |
adows | +0.003 |
outage | +0.003 |
as | +0.003 |
udd | +0.003 |
Neg logit contributions | |
� | -0.002 |
gust | -0.002 |
sed | -0.002 |
mouth | -0.002 |
Really | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
gust | +0.156 |
mouth | +0.155 |
� | +0.150 |
stem | +0.148 |
sed | +0.147 |
Neg logit contributions | |
ying | -0.200 |
and | -0.199 |
as | -0.196 |
inker | -0.192 |
iam | -0.192 |
Token | They |
Token ID | 1119 |
Feature activation | -4.79e-03 |
Pos logit contributions | |
and | +0.025 |
as | +0.023 |
ying | +0.023 |
adows | +0.023 |
os | +0.022 |
Neg logit contributions | |
gust | -0.015 |
sed | -0.014 |
stem | -0.014 |
� | -0.013 |
mouth | -0.013 |
Token | tried |
Token ID | 3088 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
and | +0.011 |
ying | +0.010 |
inker | +0.010 |
outage | +0.010 |
adows | +0.009 |
Neg logit contributions | |
gust | -0.007 |
mouth | -0.007 |
stem | -0.006 |
sed | -0.006 |
cheeks | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -8.70e-03 |
Pos logit contributions | |
mouth | +0.084 |
gust | +0.083 |
sed | +0.081 |
stem | +0.079 |
� | +0.078 |
Neg logit contributions | |
and | -0.083 |
as | -0.083 |
ying | -0.081 |
adows | -0.081 |
inker | -0.075 |
Token | wake |
Token ID | 7765 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
and | +0.018 |
as | +0.017 |
ying | +0.017 |
adows | +0.017 |
pt | +0.016 |
Neg logit contributions | |
gust | -0.013 |
sed | -0.012 |
stem | -0.012 |
� | -0.012 |
mouth | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +5.86e-02 |
Pos logit contributions | |
gust | +0.051 |
mouth | +0.049 |
� | +0.048 |
stem | +0.047 |
sed | +0.046 |
Neg logit contributions | |
and | -0.070 |
as | -0.070 |
ying | -0.068 |
adows | -0.067 |
inker | -0.065 |
Token | her |
Token ID | 607 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
gust | +0.084 |
mouth | +0.083 |
stem | +0.080 |
� | +0.079 |
sed | +0.077 |
Neg logit contributions | |
and | -0.122 |
ying | -0.120 |
as | -0.116 |
adows | -0.114 |
outage | -0.113 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
and | +0.010 |
as | +0.009 |
ying | +0.009 |
adows | +0.009 |
pt | +0.009 |
Neg logit contributions | |
gust | -0.007 |
sed | -0.007 |
stem | -0.006 |
� | -0.006 |
mouth | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
and | +0.100 |
ying | +0.096 |
as | +0.096 |
inker | +0.095 |
adows | +0.094 |
Neg logit contributions | |
gust | -0.067 |
mouth | -0.066 |
� | -0.066 |
stem | -0.063 |
sed | -0.062 |
Token | The |
Token ID | 383 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ying | +0.012 |
and | +0.012 |
as | +0.012 |
adows | +0.011 |
outage | +0.011 |
Neg logit contributions | |
mouth | -0.008 |
gust | -0.008 |
� | -0.007 |
stem | -0.007 |
sed | -0.007 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
sed | +0.066 |
gust | +0.065 |
� | +0.063 |
stem | +0.062 |
mouth | +0.061 |
Neg logit contributions | |
as | -0.081 |
and | -0.081 |
ying | -0.078 |
adows | -0.078 |
iam | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
gust | +0.174 |
sed | +0.168 |
stem | +0.164 |
� | +0.164 |
mouth | +0.163 |
Neg logit contributions | |
and | -0.205 |
as | -0.195 |
ying | -0.195 |
adows | -0.190 |
os | -0.183 |
Token | bright |
Token ID | 6016 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
gust | +0.002 |
sed | +0.002 |
stem | +0.002 |
mouth | +0.002 |
� | +0.002 |
Neg logit contributions | |
and | -0.003 |
as | -0.003 |
ying | -0.003 |
adows | -0.003 |
os | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
gust | +0.025 |
stem | +0.023 |
mouth | +0.023 |
� | +0.023 |
sed | +0.023 |
Neg logit contributions | |
and | -0.027 |
as | -0.025 |
ying | -0.025 |
adows | -0.024 |
inker | -0.024 |
Token | warm |
Token ID | 5814 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
and | +0.056 |
ying | +0.054 |
as | +0.053 |
adows | +0.052 |
inker | +0.051 |
Neg logit contributions | |
gust | -0.036 |
mouth | -0.033 |
stem | -0.032 |
sed | -0.031 |
� | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
and | +0.011 |
as | +0.010 |
ying | +0.010 |
adows | +0.010 |
os | +0.009 |
Neg logit contributions | |
gust | -0.010 |
sed | -0.010 |
� | -0.009 |
stem | -0.009 |
mouth | -0.009 |
Token | again |
Token ID | 757 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
mouth | +0.044 |
gust | +0.043 |
sed | +0.041 |
stem | +0.040 |
� | +0.040 |
Neg logit contributions | |
and | -0.059 |
ying | -0.059 |
as | -0.057 |
iam | -0.057 |
inker | -0.056 |
Token | ." |
Token ID | 526 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
mouth | +0.077 |
gust | +0.077 |
stem | +0.074 |
� | +0.072 |
sed | +0.071 |
Neg logit contributions | |
and | -0.085 |
ying | -0.084 |
as | -0.080 |
iam | -0.078 |
inker | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
and | +0.042 |
ying | +0.036 |
adows | +0.036 |
as | +0.036 |
os | +0.036 |
Neg logit contributions | |
gust | -0.032 |
sed | -0.031 |
stem | -0.031 |
� | -0.028 |
mouth | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
gust | +0.018 |
sed | +0.017 |
mouth | +0.017 |
� | +0.017 |
stem | +0.017 |
Neg logit contributions | |
and | -0.025 |
ying | -0.025 |
as | -0.024 |
adows | -0.024 |
os | -0.023 |
Token | The |
Token ID | 464 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
gust | +0.020 |
� | +0.019 |
stem | +0.019 |
mouth | +0.018 |
sed | +0.017 |
Neg logit contributions | |
ying | -0.021 |
adows | -0.021 |
and | -0.021 |
as | -0.020 |
os | -0.020 |
Token | end |
Token ID | 886 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
sed | +0.096 |
� | +0.093 |
gust | +0.093 |
stem | +0.092 |
mouth | +0.092 |
Neg logit contributions | |
and | -0.134 |
ying | -0.132 |
as | -0.131 |
adows | -0.126 |
pt | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
gust | +0.145 |
mouth | +0.143 |
sed | +0.133 |
� | +0.128 |
cheeks | +0.125 |
Neg logit contributions | |
and | -0.243 |
ying | -0.237 |
as | -0.232 |
adows | -0.228 |
udd | -0.224 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.75e-04 |
Pos logit contributions | |
gust | +0.038 |
sed | +0.037 |
stem | +0.037 |
mouth | +0.035 |
cheeks | +0.035 |
Neg logit contributions | |
and | -0.052 |
as | -0.048 |
ying | -0.048 |
adows | -0.047 |
os | -0.046 |
Token | Tom |
Token ID | 13787 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
gust | +0.000 |
� | +0.000 |
mouth | +0.000 |
sed | +0.000 |
stem | +0.000 |
Neg logit contributions | |
and | -0.000 |
as | -0.000 |
ying | -0.000 |
adows | -0.000 |
udd | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
and | +0.009 |
outage | +0.008 |
ying | +0.008 |
as | +0.008 |
vell | +0.007 |
Neg logit contributions | |
mouth | -0.007 |
sed | -0.007 |
ham | -0.007 |
stem | -0.006 |
tongue | -0.006 |
Token | Mia |
Token ID | 32189 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
and | +0.032 |
as | +0.030 |
ying | +0.030 |
adows | +0.029 |
udd | +0.028 |
Neg logit contributions | |
gust | -0.025 |
sed | -0.024 |
mouth | -0.024 |
stem | -0.024 |
� | -0.024 |
Token | did |
Token ID | 750 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
and | +0.049 |
ying | +0.044 |
adows | +0.041 |
inker | +0.040 |
outage | +0.040 |
Neg logit contributions | |
stem | -0.034 |
� | -0.033 |
sed | -0.033 |
gust | -0.032 |
mouth | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
gust | +0.019 |
mouth | +0.018 |
stem | +0.018 |
sed | +0.018 |
� | +0.018 |
Neg logit contributions | |
and | -0.031 |
ying | -0.029 |
as | -0.029 |
adows | -0.029 |
os | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
mouth | +0.050 |
gust | +0.049 |
� | +0.048 |
top | +0.048 |
stem | +0.047 |
Neg logit contributions | |
and | -0.054 |
adows | -0.052 |
as | -0.051 |
outage | -0.051 |
ying | -0.051 |
Token | love |
Token ID | 1842 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
gust | +0.112 |
mouth | +0.108 |
sed | +0.107 |
stem | +0.106 |
� | +0.103 |
Neg logit contributions | |
and | -0.130 |
ying | -0.124 |
as | -0.122 |
adows | -0.121 |
os | -0.113 |
Token | ." |
Token ID | 526 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
adows | +0.076 |
ying | +0.075 |
and | +0.075 |
iam | +0.073 |
pt | +0.072 |
Neg logit contributions | |
mouth | -0.068 |
gust | -0.068 |
stem | -0.066 |
� | -0.064 |
sed | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
and | +0.095 |
ying | +0.085 |
as | +0.084 |
adows | +0.083 |
udd | +0.083 |
Neg logit contributions | |
gust | -0.078 |
sed | -0.075 |
stem | -0.074 |
mouth | -0.069 |
� | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
and | +0.031 |
as | +0.029 |
ying | +0.029 |
adows | +0.029 |
os | +0.027 |
Neg logit contributions | |
gust | -0.020 |
sed | -0.019 |
stem | -0.018 |
� | -0.018 |
mouth | -0.018 |
Token | The |
Token ID | 464 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
and | +0.024 |
ying | +0.023 |
adows | +0.023 |
as | +0.023 |
pt | +0.022 |
Neg logit contributions | |
gust | -0.026 |
stem | -0.024 |
� | -0.024 |
sed | -0.024 |
mouth | -0.024 |
Token | pair |
Token ID | 5166 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
sed | +0.091 |
� | +0.091 |
gust | +0.090 |
mouth | +0.087 |
tongue | +0.086 |
Neg logit contributions | |
and | -0.102 |
as | -0.099 |
ying | -0.098 |
sorts | -0.097 |
inker | -0.095 |
Token | hugged |
Token ID | 41130 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
and | +0.104 |
as | +0.097 |
ying | +0.097 |
adows | +0.095 |
os | +0.090 |
Neg logit contributions | |
gust | -0.116 |
sed | -0.113 |
stem | -0.111 |
� | -0.111 |
mouth | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
gust | +0.017 |
sed | +0.017 |
stem | +0.017 |
� | +0.016 |
mouth | +0.016 |
Neg logit contributions | |
and | -0.018 |
ying | -0.016 |
as | -0.016 |
adows | -0.016 |
pt | -0.015 |
Token | ig |
Token ID | 328 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
and | +0.062 |
as | +0.061 |
ying | +0.060 |
adows | +0.059 |
inker | +0.055 |
Neg logit contributions | |
gust | -0.083 |
mouth | -0.080 |
sed | -0.080 |
stem | -0.079 |
� | -0.078 |
Token | zag |
Token ID | 50183 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
and | +0.028 |
ying | +0.026 |
as | +0.025 |
adows | +0.025 |
pt | +0.024 |
Neg logit contributions | |
gust | -0.035 |
sed | -0.035 |
stem | -0.035 |
mouth | -0.035 |
� | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
and | +0.206 |
as | +0.197 |
ying | +0.194 |
adows | +0.193 |
os | +0.184 |
Neg logit contributions | |
gust | -0.162 |
sed | -0.156 |
� | -0.156 |
stem | -0.153 |
mouth | -0.151 |
Token | so |
Token ID | 523 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
and | +0.003 |
ying | +0.003 |
as | +0.003 |
adows | +0.003 |
inker | +0.003 |
Neg logit contributions | |
gust | -0.003 |
mouth | -0.003 |
stem | -0.003 |
sed | -0.003 |
tongue | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
and | +0.016 |
ying | +0.015 |
as | +0.015 |
adows | +0.015 |
outage | +0.015 |
Neg logit contributions | |
gust | -0.010 |
mouth | -0.009 |
stem | -0.009 |
sed | -0.009 |
� | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
and | +0.005 |
as | +0.005 |
ying | +0.005 |
adows | +0.005 |
udd | +0.005 |
Neg logit contributions | |
gust | -0.004 |
mouth | -0.004 |
sed | -0.004 |
� | -0.004 |
stem | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
gust | +0.012 |
sed | +0.012 |
stem | +0.011 |
mouth | +0.011 |
� | +0.011 |
Neg logit contributions | |
and | -0.020 |
ying | -0.019 |
as | -0.019 |
adows | -0.018 |
os | -0.018 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
gust | +0.046 |
mouth | +0.043 |
sed | +0.043 |
stem | +0.042 |
cheeks | +0.038 |
Neg logit contributions | |
and | -0.095 |
ying | -0.092 |
as | -0.089 |
adows | -0.088 |
inker | -0.086 |
Token | around |
Token ID | 1088 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
as | +0.039 |
adows | +0.039 |
ying | +0.038 |
and | +0.038 |
os | +0.037 |
Neg logit contributions | |
gust | -0.040 |
mouth | -0.037 |
sed | -0.036 |
top | -0.035 |
stem | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
and | +0.114 |
as | +0.112 |
ying | +0.110 |
adows | +0.108 |
udd | +0.105 |
Neg logit contributions | |
gust | -0.082 |
sed | -0.078 |
mouth | -0.077 |
stem | -0.077 |
� | -0.076 |
Token | room |
Token ID | 2119 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
and | +0.003 |
as | +0.003 |
ying | +0.003 |
adows | +0.003 |
os | +0.003 |
Neg logit contributions | |
gust | -0.002 |
sed | -0.002 |
stem | -0.002 |
mouth | -0.002 |
� | -0.002 |
Token | One |
Token ID | 3198 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
and | +0.068 |
as | +0.064 |
ying | +0.063 |
adows | +0.062 |
os | +0.058 |
Neg logit contributions | |
gust | -0.066 |
sed | -0.066 |
mouth | -0.064 |
� | -0.063 |
stem | -0.063 |
Token | day |
Token ID | 1110 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
sed | +0.054 |
gust | +0.053 |
� | +0.053 |
stem | +0.051 |
mouth | +0.050 |
Neg logit contributions | |
and | -0.070 |
as | -0.066 |
ying | -0.065 |
adows | -0.064 |
sorts | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
sed | +0.057 |
stem | +0.055 |
� | +0.054 |
timer | +0.053 |
gust | +0.052 |
Neg logit contributions | |
ying | -0.036 |
and | -0.035 |
pt | -0.034 |
as | -0.033 |
adows | -0.033 |
Token | she |
Token ID | 673 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
sed | +0.007 |
� | +0.007 |
stem | +0.006 |
sidelines | +0.006 |
tongue | +0.006 |
Neg logit contributions | |
if | -0.003 |
sorts | -0.003 |
and | -0.003 |
along | -0.003 |
sure | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
and | +0.036 |
ying | +0.035 |
adows | +0.034 |
as | +0.033 |
outage | +0.032 |
Neg logit contributions | |
mouth | -0.023 |
gust | -0.023 |
sed | -0.022 |
stem | -0.022 |
� | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
and | +0.020 |
as | +0.019 |
ying | +0.019 |
adows | +0.018 |
os | +0.017 |
Neg logit contributions | |
gust | -0.015 |
sed | -0.015 |
mouth | -0.014 |
stem | -0.014 |
� | -0.014 |
Token | box |
Token ID | 3091 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
� | +0.009 |
sed | +0.009 |
cheeks | +0.009 |
gust | +0.009 |
stem | +0.008 |
Neg logit contributions | |
and | -0.009 |
as | -0.008 |
outage | -0.008 |
sorts | -0.008 |
washer | -0.008 |
Token | full |
Token ID | 1336 |
Feature activation | +4.95e-03 |
Pos logit contributions | |
and | +0.062 |
as | +0.057 |
ying | +0.057 |
adows | +0.056 |
os | +0.053 |
Neg logit contributions | |
gust | -0.074 |
sed | -0.072 |
stem | -0.071 |
� | -0.071 |
mouth | -0.070 |
Token | of |
Token ID | 286 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
sed | +0.011 |
gust | +0.011 |
� | +0.011 |
stem | +0.011 |
mouth | +0.011 |
Neg logit contributions | |
and | -0.006 |
as | -0.006 |
ying | -0.006 |
adows | -0.005 |
pt | -0.005 |
Token | screws |
Token ID | 23742 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
and | +0.010 |
ying | +0.010 |
as | +0.010 |
adows | +0.010 |
os | +0.009 |
Neg logit contributions | |
gust | -0.009 |
sed | -0.008 |
mouth | -0.008 |
stem | -0.008 |
� | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
and | +0.146 |
asc | +0.143 |
adows | +0.143 |
inker | +0.141 |
iam | +0.139 |
Neg logit contributions | |
mouth | -0.080 |
stem | -0.079 |
gust | -0.077 |
� | -0.076 |
cheeks | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
gust | +0.015 |
mouth | +0.013 |
� | +0.013 |
stem | +0.012 |
tongue | +0.011 |
Neg logit contributions | |
asc | -0.028 |
ibr | -0.028 |
inker | -0.027 |
adows | -0.027 |
as | -0.027 |
Token | started |
Token ID | 2067 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
and | +0.077 |
ying | +0.073 |
as | +0.073 |
adows | +0.071 |
inker | +0.068 |
Neg logit contributions | |
gust | -0.053 |
sed | -0.050 |
mouth | -0.049 |
stem | -0.049 |
� | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
gust | +0.046 |
sed | +0.044 |
mouth | +0.044 |
stem | +0.043 |
� | +0.042 |
Neg logit contributions | |
and | -0.046 |
as | -0.044 |
ying | -0.044 |
adows | -0.042 |
iam | -0.041 |
Token | sing |
Token ID | 1702 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
and | +0.033 |
as | +0.032 |
ying | +0.032 |
adows | +0.031 |
os | +0.030 |
Neg logit contributions | |
gust | -0.015 |
sed | -0.015 |
stem | -0.014 |
mouth | -0.014 |
� | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ying | +0.058 |
as | +0.056 |
and | +0.056 |
iam | +0.056 |
outage | +0.055 |
Neg logit contributions | |
gust | -0.040 |
mouth | -0.036 |
stem | -0.035 |
cheeks | -0.033 |
lips | -0.033 |
Token | As |
Token ID | 1081 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
and | +0.041 |
adows | +0.037 |
sorts | +0.036 |
os | +0.036 |
ying | +0.035 |
Neg logit contributions | |
sed | -0.031 |
gust | -0.030 |
timer | -0.029 |
mouth | -0.028 |
stem | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
sed | +0.051 |
gust | +0.049 |
mouth | +0.048 |
stem | +0.048 |
� | +0.048 |
Neg logit contributions | |
and | -0.083 |
ying | -0.079 |
as | -0.079 |
adows | -0.077 |
pt | -0.074 |
Token | sang |
Token ID | 25889 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
and | +0.030 |
as | +0.029 |
ying | +0.029 |
adows | +0.028 |
os | +0.027 |
Neg logit contributions | |
gust | -0.024 |
sed | -0.023 |
stem | -0.023 |
� | -0.022 |
mouth | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
and | +0.034 |
as | +0.034 |
ying | +0.034 |
iam | +0.033 |
adows | +0.032 |
Neg logit contributions | |
gust | -0.019 |
mouth | -0.016 |
stem | -0.015 |
cheeks | -0.015 |
sed | -0.014 |
Token | song |
Token ID | 3496 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
and | +0.015 |
as | +0.014 |
adows | +0.014 |
ying | +0.014 |
pt | +0.014 |
Neg logit contributions | |
gust | -0.010 |
� | -0.010 |
sed | -0.010 |
stem | -0.010 |
mouth | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
gust | +0.039 |
sed | +0.036 |
mouth | +0.036 |
stem | +0.035 |
� | +0.035 |
Neg logit contributions | |
and | -0.056 |
ying | -0.053 |
as | -0.053 |
adows | -0.052 |
iam | -0.051 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
sed | +0.057 |
gust | +0.056 |
stem | +0.055 |
� | +0.053 |
mouth | +0.051 |
Neg logit contributions | |
and | -0.071 |
ying | -0.067 |
as | -0.066 |
adows | -0.063 |
pt | -0.063 |
Token | began |
Token ID | 2540 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
mouth | +0.008 |
gust | +0.008 |
cheeks | +0.007 |
be | +0.007 |
head | +0.007 |
Neg logit contributions | |
and | -0.021 |
outage | -0.021 |
auc | -0.021 |
vell | -0.021 |
ying | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
mouth | +0.032 |
gust | +0.032 |
cheeks | +0.028 |
tongue | +0.028 |
� | +0.028 |
Neg logit contributions | |
as | -0.049 |
vell | -0.048 |
ying | -0.048 |
and | -0.047 |
auc | -0.046 |
Token | jog |
Token ID | 48342 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
and | +0.038 |
as | +0.037 |
ying | +0.037 |
auc | +0.035 |
os | +0.035 |
Neg logit contributions | |
gust | -0.022 |
mouth | -0.021 |
� | -0.021 |
stem | -0.020 |
cheeks | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
as | +0.165 |
ying | +0.162 |
ibr | +0.159 |
os | +0.157 |
and | +0.156 |
Neg logit contributions | |
gust | -0.108 |
� | -0.104 |
top | -0.104 |
mouth | -0.100 |
cheeks | -0.092 |
Token | He |
Token ID | 679 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
and | +0.047 |
adows | +0.042 |
ying | +0.041 |
as | +0.041 |
os | +0.040 |
Neg logit contributions | |
gust | -0.034 |
sed | -0.033 |
stem | -0.033 |
� | -0.031 |
mouth | -0.030 |
Token | could |
Token ID | 714 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
and | +0.030 |
ying | +0.029 |
outage | +0.028 |
asc | +0.027 |
as | +0.027 |
Neg logit contributions | |
gust | -0.016 |
mouth | -0.016 |
sed | -0.015 |
cheeks | -0.014 |
stem | -0.013 |
Token | feel |
Token ID | 1254 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
gust | +0.017 |
sed | +0.016 |
� | +0.016 |
mouth | +0.016 |
stem | +0.015 |
Neg logit contributions | |
and | -0.026 |
ying | -0.025 |
as | -0.025 |
adows | -0.024 |
os | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
as | +0.087 |
and | +0.086 |
os | +0.085 |
asc | +0.084 |
auc | +0.083 |
Neg logit contributions | |
gust | -0.034 |
mouth | -0.029 |
fle | -0.026 |
top | -0.022 |
sun | -0.021 |
Token | wind |
Token ID | 2344 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
and | +0.017 |
ying | +0.016 |
as | +0.016 |
adows | +0.016 |
os | +0.015 |
Neg logit contributions | |
gust | -0.006 |
mouth | -0.006 |
sed | -0.006 |
stem | -0.006 |
� | -0.005 |
Token | blowing |
Token ID | 19280 |
Feature activation | -5.96e-05 |
Pos logit contributions | |
gust | +0.072 |
stem | +0.066 |
mouth | +0.066 |
� | +0.065 |
sed | +0.063 |
Neg logit contributions | |
and | -0.080 |
as | -0.074 |
adows | -0.073 |
inker | -0.071 |
ying | -0.071 |
Token | But |
Token ID | 887 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
gust | +0.021 |
stem | +0.019 |
timer | +0.018 |
sed | +0.018 |
� | +0.018 |
Neg logit contributions | |
and | -0.024 |
os | -0.021 |
as | -0.021 |
adows | -0.021 |
smart | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
gust | +0.083 |
� | +0.080 |
sed | +0.076 |
stem | +0.072 |
cheeks | +0.070 |
Neg logit contributions | |
and | -0.117 |
ying | -0.116 |
as | -0.111 |
reat | -0.108 |
if | -0.107 |
Token | have |
Token ID | 423 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
gust | +0.038 |
sed | +0.036 |
mouth | +0.036 |
� | +0.036 |
stem | +0.035 |
Neg logit contributions | |
and | -0.063 |
ying | -0.060 |
as | -0.060 |
adows | -0.059 |
udd | -0.056 |
Token | to |
Token ID | 284 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
gust | +0.066 |
mouth | +0.065 |
sed | +0.065 |
stem | +0.063 |
� | +0.061 |
Neg logit contributions | |
and | -0.059 |
ying | -0.058 |
adows | -0.056 |
as | -0.056 |
inker | -0.053 |
Token | follow |
Token ID | 1061 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
gust | +0.011 |
sed | +0.010 |
stem | +0.010 |
� | +0.010 |
mouth | +0.010 |
Neg logit contributions | |
and | -0.021 |
as | -0.020 |
ying | -0.020 |
adows | -0.020 |
os | -0.019 |
Token | my |
Token ID | 616 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
and | +0.102 |
as | +0.098 |
ying | +0.098 |
adows | +0.097 |
udd | +0.092 |
Neg logit contributions | |
gust | -0.054 |
mouth | -0.051 |
sed | -0.051 |
stem | -0.050 |
� | -0.049 |
Token | rules |
Token ID | 3173 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
and | +0.060 |
as | +0.058 |
ying | +0.057 |
adows | +0.056 |
inker | +0.055 |
Neg logit contributions | |
gust | -0.032 |
� | -0.030 |
sed | -0.029 |
stem | -0.029 |
mouth | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
beh | +0.182 |
adows | +0.176 |
inker | +0.175 |
vell | +0.174 |
lled | +0.173 |
Neg logit contributions | |
mouth | -0.066 |
top | -0.054 |
stem | -0.052 |
mom | -0.052 |
� | -0.051 |
Token | You |
Token ID | 921 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
gust | +0.024 |
sed | +0.023 |
stem | +0.023 |
� | +0.021 |
cheeks | +0.021 |
Neg logit contributions | |
and | -0.034 |
as | -0.031 |
adows | -0.031 |
os | -0.030 |
ying | -0.030 |
Token | have |
Token ID | 423 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
gust | +0.042 |
mouth | +0.042 |
� | +0.042 |
sed | +0.040 |
stem | +0.039 |
Neg logit contributions | |
and | -0.075 |
ying | -0.070 |
adows | -0.068 |
iam | -0.066 |
udd | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | +9.83e-03 |
Pos logit contributions | |
mouth | +0.061 |
sed | +0.058 |
gust | +0.055 |
stem | +0.054 |
tongue | +0.052 |
Neg logit contributions | |
ying | -0.074 |
and | -0.070 |
adows | -0.069 |
inker | -0.069 |
as | -0.066 |
Token | little |
Token ID | 1310 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
� | +0.051 |
sed | +0.050 |
gust | +0.044 |
mouths | +0.044 |
tongue | +0.044 |
Neg logit contributions | |
ying | -0.049 |
and | -0.048 |
as | -0.045 |
aking | -0.044 |
adows | -0.044 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
sed | +0.012 |
� | +0.011 |
gust | +0.010 |
cheeks | +0.010 |
tongue | +0.010 |
Neg logit contributions | |
ying | -0.013 |
and | -0.013 |
aking | -0.012 |
sorts | -0.012 |
as | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
gust | +0.048 |
� | +0.046 |
sed | +0.046 |
stem | +0.045 |
mouth | +0.043 |
Neg logit contributions | |
and | -0.048 |
as | -0.046 |
adows | -0.044 |
os | -0.044 |
ying | -0.044 |
Token | not |
Token ID | 407 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
and | +0.019 |
ying | +0.018 |
as | +0.018 |
adows | +0.018 |
inker | +0.017 |
Neg logit contributions | |
gust | -0.017 |
mouth | -0.016 |
sed | -0.016 |
stem | -0.015 |
� | -0.015 |
Token | so |
Token ID | 523 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
and | +0.059 |
udd | +0.057 |
as | +0.056 |
ying | +0.055 |
os | +0.055 |
Neg logit contributions | |
gust | -0.057 |
mouth | -0.051 |
stem | -0.050 |
sed | -0.049 |
tongue | -0.047 |
Token | scared |
Token ID | 12008 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
and | +0.024 |
as | +0.023 |
inker | +0.022 |
iam | +0.022 |
adows | +0.022 |
Neg logit contributions | |
gust | -0.017 |
mouth | -0.013 |
grape | -0.012 |
stem | -0.012 |
sed | -0.012 |
Token | any |
Token ID | 597 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
and | +0.117 |
adows | +0.116 |
as | +0.116 |
iam | +0.111 |
inker | +0.110 |
Neg logit contributions | |
gust | -0.078 |
mouth | -0.068 |
stem | -0.064 |
� | -0.063 |
cheeks | -0.063 |
Token | more |
Token ID | 517 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
and | +0.081 |
ying | +0.077 |
as | +0.076 |
adows | +0.074 |
outage | +0.071 |
Neg logit contributions | |
sed | -0.082 |
� | -0.080 |
gust | -0.080 |
stem | -0.079 |
mouth | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
gust | +0.057 |
mouth | +0.052 |
stem | +0.050 |
sed | +0.050 |
cheeks | +0.050 |
Neg logit contributions | |
and | -0.076 |
as | -0.071 |
adows | -0.069 |
asc | -0.068 |
udd | -0.068 |
Token | The |
Token ID | 383 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
and | +0.051 |
ying | +0.046 |
adows | +0.046 |
as | +0.045 |
os | +0.044 |
Neg logit contributions | |
gust | -0.038 |
sed | -0.036 |
stem | -0.035 |
� | -0.033 |
timer | -0.033 |
Token | old |
Token ID | 1468 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
� | +0.055 |
sed | +0.054 |
tongue | +0.050 |
mouths | +0.049 |
gust | +0.049 |
Neg logit contributions | |
ying | -0.052 |
aking | -0.044 |
adows | -0.044 |
as | -0.043 |
udd | -0.043 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
gust | +0.056 |
sed | +0.053 |
stem | +0.052 |
� | +0.050 |
mouth | +0.049 |
Neg logit contributions | |
and | -0.079 |
as | -0.073 |
ying | -0.072 |
adows | -0.071 |
os | -0.069 |
Token | should |
Token ID | 815 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
mouth | +0.018 |
sed | +0.018 |
gust | +0.017 |
cheeks | +0.016 |
stem | +0.016 |
Neg logit contributions | |
and | -0.027 |
ying | -0.026 |
adows | -0.025 |
as | -0.025 |
sorts | -0.024 |
Token | not |
Token ID | 407 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
gust | +0.040 |
mouth | +0.040 |
stem | +0.040 |
sed | +0.040 |
� | +0.039 |
Neg logit contributions | |
and | -0.072 |
as | -0.066 |
ying | -0.065 |
adows | -0.064 |
os | -0.063 |
Token | have |
Token ID | 423 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
and | +0.003 |
as | +0.003 |
ying | +0.003 |
adows | +0.003 |
pt | +0.003 |
Neg logit contributions | |
gust | -0.002 |
sed | -0.002 |
� | -0.002 |
mouth | -0.002 |
stem | -0.002 |
Token | been |
Token ID | 587 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
gust | +0.072 |
sed | +0.070 |
mouth | +0.069 |
stem | +0.069 |
� | +0.068 |
Neg logit contributions | |
and | -0.059 |
ying | -0.055 |
as | -0.055 |
adows | -0.054 |
os | -0.050 |
Token | naughty |
Token ID | 45128 |
Feature activation | -6.45e-02 |
Pos logit contributions | |
gust | +0.129 |
mouth | +0.127 |
sed | +0.122 |
stem | +0.116 |
tongue | +0.113 |
Neg logit contributions | |
and | -0.156 |
ying | -0.151 |
adows | -0.149 |
inker | -0.146 |
as | -0.146 |
Token | . |
Token ID | 13 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
adows | +0.145 |
and | +0.139 |
os | +0.137 |
asc | +0.137 |
sorts | +0.136 |
Neg logit contributions | |
gust | -0.076 |
mouth | -0.074 |
cheeks | -0.071 |
sed | -0.068 |
tongue | -0.065 |
Token | She |
Token ID | 1375 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
gust | +0.048 |
sed | +0.046 |
stem | +0.045 |
� | +0.044 |
mouth | +0.044 |
Neg logit contributions | |
and | -0.083 |
as | -0.078 |
ying | -0.078 |
adows | -0.077 |
os | -0.074 |
Token | should |
Token ID | 815 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
gust | +0.039 |
sed | +0.039 |
mouth | +0.038 |
stem | +0.037 |
� | +0.037 |
Neg logit contributions | |
and | -0.041 |
ying | -0.038 |
as | -0.037 |
adows | -0.037 |
os | -0.035 |
Token | not |
Token ID | 407 |
Feature activation | -1.14e-03 |
Pos logit contributions | |
gust | +0.044 |
sed | +0.043 |
stem | +0.042 |
mouth | +0.042 |
� | +0.042 |
Neg logit contributions | |
and | -0.070 |
as | -0.066 |
ying | -0.065 |
adows | -0.064 |
os | -0.062 |
Token | have |
Token ID | 423 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
and | +0.002 |
as | +0.002 |
ying | +0.002 |
adows | +0.002 |
pt | +0.002 |
Neg logit contributions | |
gust | -0.002 |
sed | -0.002 |
� | -0.002 |
stem | -0.002 |
mouth | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
mouth | +0.106 |
sed | +0.102 |
� | +0.094 |
tongue | +0.094 |
cheeks | +0.093 |
Neg logit contributions | |
and | -0.131 |
ying | -0.131 |
inker | -0.127 |
adows | -0.125 |
iam | -0.124 |
Token | be |
Token ID | 307 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
gust | +0.019 |
sed | +0.018 |
� | +0.018 |
stem | +0.017 |
mouth | +0.017 |
Neg logit contributions | |
and | -0.029 |
as | -0.028 |
adows | -0.027 |
ying | -0.027 |
pt | -0.026 |
Token | safe |
Token ID | 3338 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
mouth | +0.129 |
gust | +0.124 |
stem | +0.118 |
sed | +0.116 |
tongue | +0.115 |
Neg logit contributions | |
and | -0.165 |
ying | -0.158 |
inker | -0.153 |
outage | -0.153 |
as | -0.151 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
mouth | +0.006 |
stem | +0.006 |
sed | +0.005 |
gust | +0.005 |
tongue | +0.005 |
Neg logit contributions | |
and | -0.010 |
inker | -0.010 |
adows | -0.010 |
ying | -0.010 |
ibr | -0.010 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
gust | +0.025 |
� | +0.024 |
sed | +0.024 |
stem | +0.024 |
mouth | +0.023 |
Neg logit contributions | |
and | -0.025 |
as | -0.024 |
ying | -0.023 |
adows | -0.023 |
pt | -0.022 |
Token | ." |
Token ID | 526 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
gust | +0.045 |
sed | +0.044 |
mouth | +0.044 |
stem | +0.043 |
� | +0.042 |
Neg logit contributions | |
and | -0.043 |
as | -0.041 |
ying | -0.040 |
adows | -0.040 |
inker | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
and | +0.027 |
as | +0.024 |
os | +0.024 |
ying | +0.023 |
adows | +0.022 |
Neg logit contributions | |
gust | -0.033 |
sed | -0.031 |
stem | -0.030 |
� | -0.029 |
timer | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
gust | +0.031 |
sed | +0.030 |
stem | +0.029 |
� | +0.029 |
mouth | +0.028 |
Neg logit contributions | |
and | -0.038 |
as | -0.036 |
ying | -0.035 |
adows | -0.034 |
os | -0.033 |
Token | They |
Token ID | 2990 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
gust | +0.037 |
sed | +0.036 |
mouth | +0.035 |
stem | +0.035 |
� | +0.035 |
Neg logit contributions | |
and | -0.028 |
as | -0.026 |
ying | -0.025 |
adows | -0.024 |
os | -0.023 |
Token | waited |
Token ID | 13488 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
gust | +0.029 |
sed | +0.028 |
mouth | +0.028 |
stem | +0.028 |
� | +0.027 |
Neg logit contributions | |
and | -0.045 |
ying | -0.042 |
outage | -0.040 |
adows | -0.040 |
as | -0.040 |
Token | for |
Token ID | 329 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
gust | +0.024 |
sed | +0.023 |
mouth | +0.023 |
stem | +0.023 |
� | +0.022 |
Neg logit contributions | |
and | -0.028 |
as | -0.027 |
ying | -0.026 |
adows | -0.026 |
os | -0.026 |
Token | tell |
Token ID | 1560 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
and | +0.021 |
as | +0.020 |
ying | +0.020 |
adows | +0.019 |
os | +0.019 |
Neg logit contributions | |
gust | -0.014 |
stem | -0.013 |
mouth | -0.013 |
sed | -0.013 |
� | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
and | +0.098 |
ying | +0.094 |
as | +0.094 |
adows | +0.093 |
aking | +0.091 |
Neg logit contributions | |
gust | -0.058 |
mouth | -0.058 |
stem | -0.054 |
sed | -0.054 |
cheeks | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | +5.18e-04 |
Pos logit contributions | |
mouth | +0.018 |
stem | +0.016 |
top | +0.016 |
cheeks | +0.015 |
gust | +0.015 |
Neg logit contributions | |
iam | -0.020 |
and | -0.020 |
asc | -0.020 |
idget | -0.020 |
auc | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
gust | +0.001 |
mouth | +0.001 |
sed | +0.001 |
stem | +0.001 |
� | +0.001 |
Neg logit contributions | |
and | -0.001 |
as | -0.001 |
ying | -0.001 |
adows | -0.001 |
udd | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
and | +0.069 |
iam | +0.064 |
as | +0.063 |
ying | +0.063 |
udd | +0.062 |
Neg logit contributions | |
mouth | -0.051 |
gust | -0.050 |
stem | -0.048 |
sed | -0.048 |
� | -0.046 |
Token | nothing |
Token ID | 2147 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
and | +0.098 |
ying | +0.093 |
as | +0.092 |
adows | +0.089 |
inker | +0.087 |
Neg logit contributions | |
gust | -0.073 |
mouth | -0.071 |
sed | -0.071 |
stem | -0.069 |
� | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
inker | +0.042 |
iam | +0.041 |
and | +0.041 |
adows | +0.039 |
asc | +0.039 |
Neg logit contributions | |
gust | -0.033 |
mouth | -0.032 |
stem | -0.029 |
sed | -0.029 |
grape | -0.028 |
Token | be |
Token ID | 307 |
Feature activation | +6.06e-02 |
Pos logit contributions | |
and | +0.019 |
ying | +0.018 |
as | +0.018 |
adows | +0.017 |
pt | +0.017 |
Neg logit contributions | |
gust | -0.013 |
sed | -0.013 |
� | -0.012 |
mouth | -0.012 |
stem | -0.012 |
Token | scared |
Token ID | 12008 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
mouth | +0.100 |
gust | +0.098 |
stem | +0.091 |
sed | +0.090 |
tongue | +0.087 |
Neg logit contributions | |
and | -0.118 |
ying | -0.111 |
iam | -0.109 |
inker | -0.107 |
as | -0.105 |
Token | of |
Token ID | 286 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
iam | +0.081 |
zzy | +0.079 |
adows | +0.078 |
and | +0.078 |
ibr | +0.078 |
Neg logit contributions | |
gust | -0.070 |
mouth | -0.063 |
stem | -0.059 |
cheeks | -0.056 |
sun | -0.056 |
Token | ". |
Token ID | 1911 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
gust | +0.005 |
mouth | +0.005 |
stem | +0.004 |
sed | +0.004 |
cheeks | +0.004 |
Neg logit contributions | |
and | -0.006 |
as | -0.006 |
ying | -0.005 |
adows | -0.005 |
iam | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
and | +0.125 |
ying | +0.115 |
adows | +0.113 |
as | +0.113 |
outage | +0.111 |
Neg logit contributions | |
gust | -0.067 |
sed | -0.064 |
mouth | -0.063 |
stem | -0.063 |
� | -0.061 |
Token | playing |
Token ID | 2712 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
and | +0.024 |
as | +0.023 |
ying | +0.023 |
adows | +0.022 |
aking | +0.021 |
Neg logit contributions | |
gust | -0.022 |
sed | -0.021 |
stem | -0.021 |
� | -0.020 |
mouth | -0.020 |
Token | near |
Token ID | 1474 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
and | +0.011 |
as | +0.011 |
ying | +0.011 |
adows | +0.011 |
outage | +0.011 |
Neg logit contributions | |
gust | -0.009 |
stem | -0.008 |
mouth | -0.008 |
� | -0.008 |
sed | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
sed | +0.119 |
gust | +0.117 |
� | +0.113 |
stem | +0.109 |
mouth | +0.108 |
Neg logit contributions | |
and | -0.118 |
as | -0.110 |
ying | -0.110 |
adows | -0.107 |
os | -0.105 |
Token | f |
Token ID | 277 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
and | +0.018 |
as | +0.017 |
ying | +0.017 |
adows | +0.017 |
os | +0.016 |
Neg logit contributions | |
gust | -0.013 |
sed | -0.012 |
stem | -0.012 |
� | -0.012 |
mouth | -0.012 |
Token | auc |
Token ID | 14272 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
and | +0.138 |
adows | +0.118 |
ust | +0.109 |
pt | +0.107 |
lled | +0.104 |
Neg logit contributions | |
� | -0.390 |
stem | -0.369 |
gust | -0.357 |
mouth | -0.357 |
sed | -0.352 |
Token | et |
Token ID | 316 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
and | +0.366 |
as | +0.342 |
ying | +0.334 |
adows | +0.324 |
outage | +0.322 |
Neg logit contributions | |
stem | -0.378 |
sed | -0.378 |
mouth | -0.378 |
gust | -0.364 |
cheeks | -0.360 |
Token | with |
Token ID | 351 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
and | +0.086 |
as | +0.081 |
ying | +0.080 |
adows | +0.079 |
pt | +0.075 |
Neg logit contributions | |
gust | -0.074 |
� | -0.071 |
sed | -0.071 |
stem | -0.071 |
mouth | -0.071 |
Token | her |
Token ID | 607 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
gust | +0.079 |
sed | +0.075 |
stem | +0.074 |
mouth | +0.074 |
� | +0.073 |
Neg logit contributions | |
and | -0.091 |
ying | -0.087 |
as | -0.086 |
adows | -0.085 |
udd | -0.081 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.07e-02 |
Pos logit contributions | |
and | +0.034 |
as | +0.032 |
ying | +0.032 |
adows | +0.031 |
pt | +0.030 |
Neg logit contributions | |
gust | -0.023 |
sed | -0.022 |
stem | -0.022 |
� | -0.022 |
mouth | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
and | +0.128 |
adows | +0.121 |
ying | +0.121 |
as | +0.121 |
inker | +0.119 |
Neg logit contributions | |
gust | -0.083 |
mouth | -0.082 |
stem | -0.079 |
� | -0.079 |
sed | -0.078 |
Token | it |
Token ID | 340 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
and | +0.089 |
as | +0.085 |
ying | +0.085 |
adows | +0.083 |
pt | +0.080 |
Neg logit contributions | |
gust | -0.065 |
sed | -0.063 |
� | -0.062 |
stem | -0.061 |
mouth | -0.060 |
Token | had |
Token ID | 550 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
gust | +0.014 |
mouth | +0.014 |
stem | +0.014 |
sed | +0.013 |
� | +0.013 |
Neg logit contributions | |
and | -0.022 |
adows | -0.021 |
as | -0.021 |
ying | -0.020 |
inker | -0.020 |
Token | made |
Token ID | 925 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
gust | +0.031 |
sed | +0.030 |
mouth | +0.029 |
stem | +0.029 |
� | +0.028 |
Neg logit contributions | |
and | -0.038 |
ying | -0.037 |
as | -0.036 |
adows | -0.036 |
os | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +7.57e-04 |
Pos logit contributions | |
and | +0.073 |
as | +0.070 |
ying | +0.070 |
adows | +0.069 |
outage | +0.066 |
Neg logit contributions | |
gust | -0.058 |
mouth | -0.054 |
stem | -0.054 |
� | -0.053 |
sed | -0.052 |
Token | huge |
Token ID | 3236 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
� | +0.001 |
sed | +0.001 |
gust | +0.001 |
cheeks | +0.001 |
stem | +0.001 |
Neg logit contributions | |
and | -0.001 |
outage | -0.001 |
as | -0.001 |
pt | -0.001 |
udd | -0.001 |
Token | mess |
Token ID | 2085 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
sorts | +0.038 |
and | +0.037 |
pt | +0.037 |
outage | +0.037 |
udd | +0.037 |
Neg logit contributions | |
sed | -0.070 |
� | -0.070 |
gust | -0.065 |
stem | -0.063 |
Really | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
adows | +0.319 |
and | +0.310 |
inker | +0.298 |
udd | +0.296 |
as | +0.295 |
Neg logit contributions | |
gust | -0.149 |
mouth | -0.135 |
� | -0.134 |
stem | -0.132 |
cheeks | -0.128 |
Token | She |
Token ID | 1375 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
and | +0.073 |
adows | +0.060 |
os | +0.059 |
sorts | +0.057 |
ying | +0.057 |
Neg logit contributions | |
sed | -0.075 |
gust | -0.072 |
timer | -0.071 |
stem | -0.067 |
tongue | -0.065 |
Token | tried |
Token ID | 3088 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
and | +0.043 |
as | +0.041 |
ying | +0.040 |
adows | +0.039 |
pt | +0.039 |
Neg logit contributions | |
gust | -0.041 |
sed | -0.039 |
� | -0.039 |
stem | -0.039 |
mouth | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
gust | +0.064 |
mouth | +0.062 |
stem | +0.060 |
� | +0.060 |
sed | +0.059 |
Neg logit contributions | |
adows | -0.062 |
as | -0.062 |
and | -0.061 |
ying | -0.060 |
asc | -0.057 |
Token | clean |
Token ID | 3424 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
and | +0.034 |
as | +0.032 |
ying | +0.032 |
adows | +0.031 |
os | +0.030 |
Neg logit contributions | |
gust | -0.032 |
stem | -0.031 |
sed | -0.031 |
mouth | -0.030 |
� | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
and | +0.145 |
ying | +0.136 |
as | +0.136 |
adows | +0.135 |
inker | +0.128 |
Neg logit contributions | |
gust | -0.106 |
sed | -0.102 |
mouth | -0.102 |
� | -0.100 |
stem | -0.099 |
Token | made |
Token ID | 925 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
gust | +0.053 |
mouth | +0.052 |
sed | +0.051 |
stem | +0.050 |
� | +0.049 |
Neg logit contributions | |
and | -0.058 |
ying | -0.057 |
adows | -0.057 |
as | -0.054 |
inker | -0.052 |
Token | such |
Token ID | 884 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
and | +0.062 |
as | +0.062 |
adows | +0.060 |
ying | +0.059 |
os | +0.057 |
Neg logit contributions | |
gust | -0.044 |
mouth | -0.043 |
� | -0.039 |
sed | -0.039 |
stem | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
gust | +0.042 |
mouth | +0.041 |
sed | +0.040 |
stem | +0.039 |
� | +0.038 |
Neg logit contributions | |
and | -0.059 |
ying | -0.056 |
as | -0.055 |
adows | -0.054 |
os | -0.053 |
Token | huge |
Token ID | 3236 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
sed | +0.024 |
� | +0.023 |
gust | +0.023 |
cheeks | +0.023 |
stem | +0.022 |
Neg logit contributions | |
and | -0.019 |
as | -0.018 |
udd | -0.018 |
ying | -0.017 |
outage | -0.017 |
Token | mess |
Token ID | 2085 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
and | +0.042 |
udd | +0.041 |
sorts | +0.040 |
ying | +0.040 |
as | +0.039 |
Neg logit contributions | |
sed | -0.043 |
� | -0.043 |
gust | -0.042 |
stem | -0.039 |
cheeks | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
adows | +0.296 |
and | +0.283 |
inker | +0.277 |
as | +0.274 |
asc | +0.272 |
Neg logit contributions | |
gust | -0.159 |
� | -0.154 |
mouth | -0.152 |
cheeks | -0.144 |
tongue | -0.139 |
Token | made |
Token ID | 925 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
and | +0.076 |
as | +0.073 |
adows | +0.073 |
ying | +0.073 |
inker | +0.069 |
Neg logit contributions | |
gust | -0.046 |
mouth | -0.044 |
sed | -0.043 |
stem | -0.041 |
cheeks | -0.040 |
Token | him |
Token ID | 683 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
and | +0.056 |
as | +0.055 |
ying | +0.054 |
adows | +0.054 |
os | +0.051 |
Neg logit contributions | |
gust | -0.047 |
mouth | -0.045 |
sed | -0.043 |
� | -0.043 |
stem | -0.042 |
Token | clean |
Token ID | 3424 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
gust | +0.056 |
mouth | +0.055 |
stem | +0.050 |
cheeks | +0.050 |
tongue | +0.050 |
Neg logit contributions | |
and | -0.088 |
ying | -0.087 |
as | -0.087 |
adows | -0.084 |
inker | -0.082 |
Token | it |
Token ID | 340 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
as | +0.143 |
and | +0.138 |
adows | +0.133 |
ibr | +0.130 |
ying | +0.129 |
Neg logit contributions | |
mouth | -0.095 |
gust | -0.091 |
stem | -0.086 |
cheeks | -0.085 |
tongue | -0.084 |
Token | better |
Token ID | 1365 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
and | +0.067 |
as | +0.067 |
inker | +0.066 |
os | +0.066 |
asc | +0.063 |
Neg logit contributions | |
gust | -0.048 |
mouth | -0.045 |
stem | -0.041 |
� | -0.040 |
tum | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
mouth | +0.004 |
� | +0.003 |
cheeks | +0.003 |
stem | +0.003 |
gust | +0.003 |
Neg logit contributions | |
and | -0.006 |
as | -0.006 |
asc | -0.006 |
inker | -0.006 |
ying | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
and | +0.021 |
ying | +0.021 |
as | +0.021 |
adows | +0.020 |
pt | +0.020 |
Neg logit contributions | |
mouth | -0.020 |
gust | -0.020 |
stem | -0.020 |
� | -0.019 |
sed | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
ying | +0.060 |
adows | +0.059 |
as | +0.059 |
and | +0.059 |
asc | +0.058 |
Neg logit contributions | |
gust | -0.020 |
� | -0.020 |
mouth | -0.019 |
stem | -0.019 |
top | -0.016 |
Token | J |
Token ID | 41 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
ying | +0.048 |
adows | +0.047 |
asc | +0.046 |
and | +0.045 |
pt | +0.045 |
Neg logit contributions | |
gust | -0.033 |
stem | -0.032 |
� | -0.030 |
mouth | -0.030 |
top | -0.029 |
Token | os |
Token ID | 418 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
upstream | +0.078 |
beh | +0.076 |
responsibly | +0.075 |
outage | +0.074 |
ying | +0.074 |
Neg logit contributions | |
stem | -0.137 |
mouth | -0.136 |
gust | -0.133 |
cheeks | -0.133 |
sed | -0.132 |
Token | ie |
Token ID | 494 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
and | +0.361 |
as | +0.321 |
adows | +0.316 |
outage | +0.311 |
inker | +0.310 |
Neg logit contributions | |
gust | -0.306 |
stem | -0.296 |
cheeks | -0.293 |
mouth | -0.283 |
� | -0.281 |
Token | took |
Token ID | 1718 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
and | +0.081 |
ying | +0.076 |
as | +0.076 |
adows | +0.074 |
inker | +0.071 |
Neg logit contributions | |
gust | -0.063 |
sed | -0.061 |
mouth | -0.060 |
stem | -0.060 |
� | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
and | +0.047 |
ying | +0.047 |
outage | +0.046 |
as | +0.046 |
adows | +0.045 |
Neg logit contributions | |
gust | -0.035 |
mouth | -0.034 |
stem | -0.032 |
cheeks | -0.032 |
� | -0.031 |
Token | medicine |
Token ID | 9007 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
and | +0.011 |
as | +0.011 |
ying | +0.010 |
adows | +0.010 |
udd | +0.010 |
Neg logit contributions | |
gust | -0.009 |
sed | -0.009 |
� | -0.009 |
stem | -0.009 |
mouth | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
mouth | +0.027 |
gust | +0.026 |
� | +0.026 |
stem | +0.026 |
sed | +0.024 |
Neg logit contributions | |
asc | -0.037 |
and | -0.037 |
inker | -0.036 |
adows | -0.036 |
as | -0.036 |
Token | store |
Token ID | 3650 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
gust | +0.033 |
sed | +0.032 |
stem | +0.032 |
� | +0.031 |
mouth | +0.028 |
Neg logit contributions | |
and | -0.051 |
as | -0.048 |
iam | -0.048 |
washer | -0.048 |
ying | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
and | +0.010 |
as | +0.009 |
ying | +0.009 |
os | +0.009 |
adows | +0.009 |
Neg logit contributions | |
gust | -0.008 |
stem | -0.008 |
� | -0.008 |
sed | -0.008 |
mouth | -0.007 |
Token | full |
Token ID | 1336 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
and | +0.026 |
as | +0.025 |
ying | +0.025 |
adows | +0.024 |
os | +0.023 |
Neg logit contributions | |
gust | -0.024 |
sed | -0.023 |
stem | -0.023 |
mouth | -0.023 |
� | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
gust | +0.009 |
mouth | +0.009 |
sed | +0.009 |
stem | +0.009 |
� | +0.009 |
Neg logit contributions | |
and | -0.007 |
as | -0.007 |
ying | -0.007 |
adows | -0.007 |
inker | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | -9.32e-02 |
Pos logit contributions | |
and | +0.018 |
as | +0.017 |
ying | +0.017 |
adows | +0.017 |
sorts | +0.016 |
Neg logit contributions | |
gust | -0.015 |
sed | -0.015 |
� | -0.015 |
stem | -0.014 |
mouth | -0.014 |
Token | kinds |
Token ID | 6982 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
and | +0.181 |
inker | +0.181 |
adows | +0.181 |
as | +0.175 |
ibr | +0.173 |
Neg logit contributions | |
mouth | -0.144 |
grape | -0.139 |
gust | -0.135 |
stem | -0.126 |
gu | -0.126 |
Token | of |
Token ID | 286 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
and | +0.214 |
adows | +0.211 |
ying | +0.205 |
as | +0.203 |
inker | +0.202 |
Neg logit contributions | |
gust | -0.268 |
mouth | -0.257 |
� | -0.253 |
sed | -0.251 |
cheeks | -0.249 |
Token | snacks |
Token ID | 28487 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
and | +0.019 |
ying | +0.018 |
as | +0.018 |
adows | +0.017 |
sorts | +0.017 |
Neg logit contributions | |
sed | -0.018 |
gust | -0.018 |
� | -0.017 |
stem | -0.017 |
mouth | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
and | +0.023 |
adows | +0.022 |
as | +0.022 |
inker | +0.021 |
ying | +0.021 |
Neg logit contributions | |
mouth | -0.015 |
gust | -0.015 |
� | -0.015 |
sed | -0.015 |
stem | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
and | +0.011 |
as | +0.010 |
ying | +0.010 |
adows | +0.010 |
os | +0.009 |
Neg logit contributions | |
gust | -0.009 |
sed | -0.008 |
stem | -0.008 |
mouth | -0.008 |
� | -0.008 |
Token | were |
Token ID | 547 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
and | +0.082 |
as | +0.079 |
ying | +0.077 |
adows | +0.075 |
pt | +0.073 |
Neg logit contributions | |
sed | -0.064 |
gust | -0.064 |
� | -0.062 |
stem | -0.062 |
mouth | -0.059 |