Token | elephants |
Token ID | 25368 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
pole | +0.007 |
lves | +0.007 |
chard | +0.007 |
none | +0.007 |
One | +0.007 |
Neg logit contributions | |
kiss | -0.007 |
ment | -0.007 |
less | -0.006 |
bless | -0.006 |
forgiveness | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
pole | +0.262 |
none | +0.248 |
lves | +0.246 |
chard | +0.243 |
One | +0.242 |
Neg logit contributions | |
kiss | -0.189 |
ment | -0.184 |
forgiveness | -0.165 |
less | -0.163 |
bless | -0.160 |
Token | lions |
Token ID | 31420 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
pole | +0.013 |
none | +0.013 |
pads | +0.013 |
chard | +0.012 |
One | +0.012 |
Neg logit contributions | |
kiss | -0.010 |
ment | -0.010 |
less | -0.010 |
forgiveness | -0.009 |
bless | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
pole | +0.213 |
none | +0.202 |
lves | +0.199 |
opes | +0.196 |
chard | +0.196 |
Neg logit contributions | |
kiss | -0.163 |
ment | -0.157 |
forgiveness | -0.143 |
less | -0.141 |
bless | -0.139 |
Token | ac |
Token ID | 936 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
kiss | +0.007 |
ment | +0.007 |
less | +0.007 |
bless | +0.007 |
forgiveness | +0.006 |
Neg logit contributions | |
pole | -0.006 |
lves | -0.006 |
none | -0.006 |
chard | -0.006 |
One | -0.005 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
pole | +0.043 |
lves | +0.039 |
none | +0.039 |
chard | +0.039 |
One | +0.036 |
Neg logit contributions | |
kiss | -0.107 |
ment | -0.104 |
less | -0.098 |
bless | -0.097 |
forgiveness | -0.096 |
Token | ats |
Token ID | 1381 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
chard | +0.619 |
pole | +0.535 |
nam | +0.530 |
lves | +0.513 |
One | +0.504 |
Neg logit contributions | |
ment | -0.430 |
kiss | -0.415 |
- | -0.396 |
iness | -0.382 |
band | -0.376 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-02 |
Pos logit contributions | |
pole | +0.122 |
lves | +0.121 |
chard | +0.119 |
none | +0.118 |
favourites | +0.115 |
Neg logit contributions | |
kiss | -0.068 |
ment | -0.063 |
less | -0.056 |
bless | -0.055 |
forgiveness | -0.052 |
Token | They |
Token ID | 1119 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
pole | +0.004 |
lves | +0.003 |
opes | +0.003 |
chard | +0.003 |
nam | +0.003 |
Neg logit contributions | |
kiss | -0.003 |
ment | -0.003 |
of | -0.002 |
prayer | -0.002 |
from | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
pole | +0.037 |
lves | +0.036 |
chard | +0.035 |
none | +0.035 |
pads | +0.034 |
Neg logit contributions | |
kiss | -0.021 |
ment | -0.018 |
bless | -0.016 |
prayer | -0.016 |
forgiveness | -0.015 |
Token | amazed |
Token ID | 24562 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.022 |
less | +0.021 |
prayer | +0.021 |
bless | +0.021 |
Neg logit contributions | |
lves | -0.027 |
pole | -0.026 |
chard | -0.025 |
One | -0.025 |
none | -0.025 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
pole | +0.037 |
lves | +0.035 |
none | +0.035 |
chard | +0.035 |
One | +0.033 |
Neg logit contributions | |
kiss | -0.041 |
ment | -0.040 |
less | -0.037 |
bless | -0.037 |
forgiveness | -0.036 |
Token | clown |
Token ID | 25573 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
pole | +0.021 |
none | +0.020 |
lves | +0.020 |
chard | +0.020 |
One | +0.019 |
Neg logit contributions | |
kiss | -0.020 |
ment | -0.019 |
less | -0.018 |
bless | -0.017 |
prayer | -0.017 |
Token | s |
Token ID | 82 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
pole | +0.193 |
lves | +0.181 |
none | +0.177 |
chard | +0.176 |
pads | +0.171 |
Neg logit contributions | |
kiss | -0.223 |
ment | -0.219 |
forgiveness | -0.201 |
less | -0.197 |
bless | -0.196 |
Token | and |
Token ID | 290 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
pole | +0.108 |
none | +0.106 |
chard | +0.102 |
One | +0.100 |
pads | +0.099 |
Neg logit contributions | |
kiss | -0.076 |
ment | -0.076 |
forgiveness | -0.069 |
bless | -0.069 |
less | -0.067 |
Token | ac |
Token ID | 936 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
kiss | +0.001 |
ment | +0.001 |
less | +0.001 |
bless | +0.001 |
forgiveness | +0.001 |
Neg logit contributions | |
pole | -0.001 |
none | -0.001 |
chard | -0.001 |
lves | -0.001 |
One | -0.001 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
pole | +0.036 |
lves | +0.034 |
chard | +0.031 |
none | +0.031 |
pads | +0.030 |
Neg logit contributions | |
kiss | -0.110 |
ment | -0.106 |
less | -0.100 |
prayer | -0.100 |
bless | -0.099 |
Token | ats |
Token ID | 1381 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
chard | +0.567 |
pole | +0.511 |
nam | +0.487 |
lves | +0.471 |
One | +0.467 |
Neg logit contributions | |
ment | -0.445 |
kiss | -0.415 |
iness | -0.394 |
- | -0.393 |
less | -0.391 |
Token | and |
Token ID | 290 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
pole | +0.109 |
none | +0.103 |
lves | +0.102 |
chard | +0.102 |
One | +0.101 |
Neg logit contributions | |
kiss | -0.065 |
ment | -0.063 |
forgiveness | -0.056 |
bless | -0.055 |
less | -0.055 |
Token | lions |
Token ID | 31420 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
pole | +0.011 |
none | +0.011 |
chard | +0.011 |
lves | +0.011 |
pads | +0.010 |
Neg logit contributions | |
kiss | -0.014 |
ment | -0.014 |
less | -0.014 |
bless | -0.013 |
forgiveness | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
pole | +0.246 |
none | +0.233 |
pads | +0.232 |
lves | +0.228 |
opes | +0.228 |
Neg logit contributions | |
kiss | -0.184 |
ment | -0.178 |
forgiveness | -0.163 |
less | -0.160 |
bless | -0.159 |
Token | elephants |
Token ID | 25368 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
pole | +0.008 |
none | +0.008 |
chard | +0.007 |
lves | +0.007 |
nam | +0.007 |
Neg logit contributions | |
kiss | -0.011 |
ment | -0.011 |
less | -0.011 |
bless | -0.010 |
forgiveness | -0.010 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
kiss | +0.024 |
band | +0.022 |
fairy | +0.019 |
bless | +0.019 |
ment | +0.019 |
Neg logit contributions | |
pole | -0.031 |
chard | -0.031 |
lves | -0.030 |
nam | -0.029 |
none | -0.029 |
Token | they |
Token ID | 484 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
kiss | +0.088 |
ment | +0.087 |
bless | +0.079 |
less | +0.078 |
guard | +0.075 |
Neg logit contributions | |
none | -0.076 |
One | -0.072 |
pole | -0.071 |
favourites | -0.066 |
nam | -0.066 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
pole | +0.083 |
lves | +0.080 |
chard | +0.079 |
uries | +0.074 |
none | +0.074 |
Neg logit contributions | |
kiss | -0.082 |
ment | -0.071 |
less | -0.070 |
band | -0.070 |
prayer | -0.068 |
Token | like |
Token ID | 588 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
pole | +0.094 |
opes | +0.088 |
chard | +0.088 |
lves | +0.087 |
none | +0.086 |
Neg logit contributions | |
kiss | -0.073 |
less | -0.066 |
ment | -0.063 |
cleaner | -0.062 |
band | -0.061 |
Token | ac |
Token ID | 936 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
kiss | +0.040 |
ment | +0.040 |
less | +0.036 |
bless | +0.035 |
prayer | +0.034 |
Neg logit contributions | |
none | -0.042 |
pole | -0.042 |
chard | -0.040 |
lves | -0.040 |
One | -0.039 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
pole | +0.027 |
lves | +0.027 |
chard | +0.024 |
none | +0.024 |
pads | +0.024 |
Neg logit contributions | |
kiss | -0.067 |
ment | -0.064 |
prayer | -0.061 |
less | -0.060 |
bless | -0.060 |
Token | ats |
Token ID | 1381 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
chard | +0.513 |
pole | +0.481 |
lves | +0.446 |
One | +0.444 |
nam | +0.436 |
Neg logit contributions | |
ment | -0.459 |
kiss | -0.458 |
iness | -0.427 |
less | -0.425 |
band | -0.421 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
pole | +0.091 |
none | +0.087 |
lves | +0.084 |
chard | +0.084 |
pads | +0.084 |
Neg logit contributions | |
ment | -0.062 |
kiss | -0.061 |
bless | -0.054 |
forgiveness | -0.053 |
less | -0.053 |
Token | She |
Token ID | 1375 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
kiss | +0.016 |
prayer | +0.014 |
ment | +0.014 |
less | +0.013 |
next | +0.013 |
Neg logit contributions | |
pole | -0.022 |
lves | -0.022 |
chard | -0.021 |
none | -0.020 |
nam | -0.020 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
pole | +0.019 |
lves | +0.018 |
chard | +0.018 |
uries | +0.018 |
none | +0.017 |
Neg logit contributions | |
kiss | -0.017 |
band | -0.015 |
fairy | -0.014 |
ment | -0.014 |
bless | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
kiss | +0.029 |
ment | +0.028 |
less | +0.026 |
prayer | +0.025 |
bless | +0.025 |
Neg logit contributions | |
none | -0.022 |
pole | -0.022 |
lves | -0.022 |
chard | -0.022 |
One | -0.021 |
Token | clown |
Token ID | 25573 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
kiss | +0.008 |
ment | +0.008 |
less | +0.007 |
bless | +0.007 |
forgiveness | +0.007 |
Neg logit contributions | |
pole | -0.009 |
lves | -0.008 |
none | -0.008 |
chard | -0.008 |
One | -0.008 |
Token | s |
Token ID | 82 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
pole | +0.178 |
lves | +0.171 |
none | +0.168 |
chard | +0.168 |
One | +0.162 |
Neg logit contributions | |
kiss | -0.190 |
ment | -0.182 |
less | -0.168 |
bless | -0.166 |
forgiveness | -0.163 |
Token | juggling |
Token ID | 48097 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
pole | +0.075 |
none | +0.072 |
chard | +0.071 |
lves | +0.069 |
One | +0.069 |
Neg logit contributions | |
kiss | -0.053 |
ment | -0.052 |
forgiveness | -0.046 |
less | -0.045 |
bless | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
pole | +0.192 |
lves | +0.187 |
chard | +0.183 |
none | +0.182 |
One | +0.175 |
Neg logit contributions | |
kiss | -0.166 |
ment | -0.158 |
less | -0.143 |
bless | -0.140 |
forgiveness | -0.139 |
Token | ac |
Token ID | 936 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
kiss | +0.004 |
ment | +0.004 |
band | +0.003 |
bless | +0.003 |
ful | +0.003 |
Neg logit contributions | |
lves | -0.005 |
pole | -0.005 |
favorites | -0.005 |
uries | -0.005 |
favourites | -0.005 |
Token | rob |
Token ID | 22609 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
pole | +0.034 |
none | +0.032 |
chard | +0.032 |
lves | +0.031 |
One | +0.031 |
Neg logit contributions | |
kiss | -0.067 |
ment | -0.066 |
less | -0.062 |
band | -0.062 |
guard | -0.061 |
Token | ats |
Token ID | 1381 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
chard | +0.586 |
pole | +0.502 |
One | +0.495 |
lves | +0.489 |
nam | +0.489 |
Neg logit contributions | |
ment | -0.406 |
iness | -0.379 |
- | -0.376 |
kiss | -0.376 |
band | -0.360 |
Token | doing |
Token ID | 1804 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
pole | +0.082 |
lves | +0.080 |
chard | +0.079 |
none | +0.079 |
One | +0.077 |
Neg logit contributions | |
kiss | -0.053 |
ment | -0.050 |
less | -0.044 |
bless | -0.043 |
forgiveness | -0.043 |
Token | flips |
Token ID | 45971 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
pole | +0.013 |
lves | +0.013 |
chard | +0.013 |
none | +0.012 |
One | +0.012 |
Neg logit contributions | |
kiss | -0.011 |
ment | -0.011 |
band | -0.010 |
less | -0.010 |
forgiveness | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
pole | +0.018 |
lves | +0.017 |
none | +0.017 |
chard | +0.017 |
One | +0.016 |
Neg logit contributions | |
kiss | -0.013 |
ment | -0.013 |
bless | -0.011 |
forgiveness | -0.011 |
less | -0.011 |
Token | But |
Token ID | 887 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
kiss | +0.009 |
ment | +0.007 |
prayer | +0.006 |
band | +0.006 |
nurse | +0.006 |
Neg logit contributions | |
lves | -0.013 |
pole | -0.013 |
uries | -0.013 |
opes | -0.013 |
edy | -0.013 |
Token | who |
Token ID | 508 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
pole | +0.031 |
lves | +0.029 |
chard | +0.028 |
none | +0.028 |
One | +0.026 |
Neg logit contributions | |
kiss | -0.076 |
ment | -0.074 |
less | -0.069 |
bless | -0.069 |
forgiveness | -0.068 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
One | +0.063 |
lves | +0.062 |
pole | +0.061 |
favourites | +0.058 |
chard | +0.057 |
Neg logit contributions | |
ment | -0.224 |
kiss | -0.222 |
forgiveness | -0.211 |
less | -0.205 |
guard | -0.205 |
Token | to |
Token ID | 284 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
chard | +0.052 |
pole | +0.050 |
nam | +0.050 |
none | +0.050 |
One | +0.049 |
Neg logit contributions | |
ment | -0.043 |
kiss | -0.043 |
less | -0.038 |
bless | -0.038 |
forgiveness | -0.037 |
Token | collect |
Token ID | 2824 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
One | +0.008 |
pole | +0.008 |
chard | +0.008 |
none | +0.007 |
favourites | +0.007 |
Neg logit contributions | |
ment | -0.007 |
less | -0.007 |
kiss | -0.006 |
guard | -0.006 |
accidents | -0.006 |
Token | or |
Token ID | 393 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
pole | +0.074 |
lves | +0.071 |
chard | +0.070 |
none | +0.070 |
One | +0.068 |
Neg logit contributions | |
kiss | -0.058 |
ment | -0.055 |
less | -0.050 |
bless | -0.049 |
forgiveness | -0.049 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
pole | +0.022 |
lves | +0.019 |
none | +0.015 |
chard | +0.014 |
One | +0.013 |
Neg logit contributions | |
kiss | -0.173 |
ment | -0.168 |
less | -0.160 |
bless | -0.159 |
forgiveness | -0.159 |
Token | ents |
Token ID | 658 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
lves | +0.304 |
none | +0.302 |
chard | +0.294 |
uries | +0.291 |
opes | +0.291 |
Neg logit contributions | |
kiss | -0.532 |
ment | -0.528 |
less | -0.515 |
of | -0.513 |
ful | -0.508 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
pole | +0.213 |
none | +0.204 |
chard | +0.203 |
lves | +0.201 |
One | +0.195 |
Neg logit contributions | |
kiss | -0.141 |
ment | -0.130 |
bless | -0.119 |
forgiveness | -0.117 |
prayer | -0.117 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
lves | +0.014 |
pole | +0.014 |
chard | +0.013 |
none | +0.013 |
opes | +0.013 |
Neg logit contributions | |
kiss | -0.016 |
ment | -0.014 |
prayer | -0.014 |
less | -0.013 |
bless | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
pole | +0.114 |
lves | +0.110 |
uries | +0.107 |
chard | +0.106 |
opes | +0.106 |
Neg logit contributions | |
kiss | -0.057 |
ment | -0.052 |
bless | -0.045 |
band | -0.044 |
less | -0.044 |
Token | went |
Token ID | 1816 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
pole | +0.018 |
lves | +0.017 |
none | +0.017 |
chard | +0.017 |
One | +0.016 |
Neg logit contributions | |
kiss | -0.018 |
ment | -0.018 |
less | -0.016 |
bless | -0.016 |
forgiveness | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
kiss | +0.004 |
ment | +0.003 |
less | +0.003 |
bless | +0.003 |
forgiveness | +0.003 |
Neg logit contributions | |
pole | -0.006 |
lves | -0.006 |
none | -0.006 |
chard | -0.006 |
One | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
lves | +0.006 |
pole | +0.005 |
riages | +0.005 |
opes | +0.005 |
nam | +0.005 |
Neg logit contributions | |
kiss | -0.009 |
shower | -0.008 |
of | -0.008 |
moment | -0.008 |
prayer | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
lves | +0.026 |
pole | +0.024 |
opes | +0.024 |
uries | +0.023 |
osures | +0.023 |
Neg logit contributions | |
kiss | -0.024 |
band | -0.019 |
fairy | -0.019 |
ot | -0.019 |
cheer | -0.018 |
Token | called |
Token ID | 1444 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
lves | +0.028 |
pole | +0.027 |
uries | +0.026 |
astically | +0.026 |
pads | +0.026 |
Neg logit contributions | |
kiss | -0.016 |
from | -0.015 |
cheer | -0.015 |
next | -0.015 |
fairy | -0.014 |
Token | or |
Token ID | 393 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
pole | +0.124 |
lves | +0.119 |
none | +0.119 |
chard | +0.118 |
One | +0.115 |
Neg logit contributions | |
kiss | -0.114 |
ment | -0.110 |
less | -0.100 |
bless | -0.098 |
forgiveness | -0.098 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
pole | +0.005 |
chard | +0.005 |
none | +0.004 |
nam | +0.003 |
lves | +0.001 |
Neg logit contributions | |
kiss | -0.170 |
ment | -0.168 |
less | -0.160 |
bless | -0.159 |
forgiveness | -0.158 |
Token | ents |
Token ID | 658 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
none | +0.286 |
chard | +0.285 |
pole | +0.282 |
lves | +0.278 |
One | +0.269 |
Neg logit contributions | |
kiss | -0.553 |
ment | -0.539 |
less | -0.539 |
ful | -0.536 |
of | -0.512 |
Token | and |
Token ID | 290 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
pole | +0.197 |
none | +0.191 |
chard | +0.179 |
pads | +0.172 |
lves | +0.172 |
Neg logit contributions | |
kiss | -0.142 |
ment | -0.131 |
forgiveness | -0.125 |
bless | -0.123 |
prayer | -0.120 |
Token | they |
Token ID | 484 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
pole | +0.016 |
lves | +0.015 |
chard | +0.014 |
none | +0.014 |
One | +0.014 |
Neg logit contributions | |
kiss | -0.017 |
ment | -0.016 |
less | -0.015 |
bless | -0.015 |
forgiveness | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
lves | +0.080 |
pole | +0.077 |
opes | +0.073 |
pads | +0.073 |
chard | +0.072 |
Neg logit contributions | |
kiss | -0.081 |
band | -0.066 |
fairy | -0.066 |
bless | -0.065 |
cheer | -0.063 |
Token | very |
Token ID | 845 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
lves | +0.087 |
While | +0.084 |
banks | +0.084 |
pads | +0.083 |
opes | +0.083 |
Neg logit contributions | |
kiss | -0.053 |
fairy | -0.048 |
from | -0.047 |
gift | -0.045 |
band | -0.045 |
Token | tree |
Token ID | 5509 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
ment | +0.090 |
kiss | +0.077 |
less | +0.077 |
ful | +0.074 |
bless | +0.073 |
Neg logit contributions | |
pole | -0.071 |
chard | -0.070 |
One | -0.067 |
none | -0.066 |
bank | -0.066 |
Token | with |
Token ID | 351 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
pole | +0.041 |
chard | +0.038 |
none | +0.037 |
One | +0.037 |
lves | +0.036 |
Neg logit contributions | |
kiss | -0.030 |
ment | -0.029 |
bless | -0.027 |
forgiveness | -0.027 |
less | -0.025 |
Token | lights |
Token ID | 7588 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
pole | +0.048 |
lves | +0.047 |
uries | +0.046 |
chard | +0.044 |
edy | +0.043 |
Neg logit contributions | |
kiss | -0.050 |
ment | -0.048 |
band | -0.043 |
less | -0.043 |
forgiveness | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
pole | +0.026 |
none | +0.024 |
pads | +0.023 |
chard | +0.023 |
One | +0.023 |
Neg logit contributions | |
kiss | -0.018 |
ment | -0.017 |
forgiveness | -0.017 |
bless | -0.016 |
prayer | -0.015 |
Token | or |
Token ID | 393 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
pole | +0.044 |
lves | +0.042 |
none | +0.041 |
chard | +0.041 |
One | +0.040 |
Neg logit contributions | |
kiss | -0.044 |
ment | -0.042 |
less | -0.039 |
bless | -0.038 |
forgiveness | -0.038 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.44e+00 |
Pos logit contributions | |
pole | +0.123 |
none | +0.122 |
chard | +0.122 |
nam | +0.119 |
lves | +0.119 |
Neg logit contributions | |
kiss | -0.128 |
ment | -0.125 |
less | -0.118 |
bless | -0.113 |
forgiveness | -0.111 |
Token | ents |
Token ID | 658 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
chard | +0.299 |
none | +0.292 |
One | +0.292 |
pole | +0.286 |
lves | +0.286 |
Neg logit contributions | |
ment | -0.521 |
kiss | -0.514 |
less | -0.508 |
ful | -0.504 |
of | -0.488 |
Token | . |
Token ID | 13 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
pole | +0.193 |
none | +0.183 |
chard | +0.178 |
lves | +0.173 |
pads | +0.171 |
Neg logit contributions | |
kiss | -0.141 |
ment | -0.129 |
forgiveness | -0.124 |
bless | -0.124 |
prayer | -0.121 |
Token | They |
Token ID | 1119 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
pole | +0.038 |
lves | +0.037 |
pads | +0.034 |
opes | +0.034 |
chard | +0.033 |
Neg logit contributions | |
kiss | -0.026 |
ment | -0.026 |
prayer | -0.023 |
voice | -0.023 |
shower | -0.022 |
Token | also |
Token ID | 635 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
lves | +0.041 |
pole | +0.040 |
uries | +0.039 |
pads | +0.038 |
opes | +0.037 |
Neg logit contributions | |
kiss | -0.038 |
fairy | -0.032 |
band | -0.031 |
ful | -0.030 |
ment | -0.030 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
lves | +0.088 |
pole | +0.087 |
opes | +0.082 |
uries | +0.081 |
pads | +0.079 |
Neg logit contributions | |
kiss | -0.080 |
ment | -0.070 |
bless | -0.066 |
fairy | -0.066 |
cheer | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
pole | +0.101 |
lves | +0.097 |
none | +0.097 |
chard | +0.096 |
One | +0.093 |
Neg logit contributions | |
kiss | -0.081 |
ment | -0.078 |
less | -0.070 |
bless | -0.069 |
forgiveness | -0.068 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
pole | +0.011 |
lves | +0.011 |
none | +0.010 |
chard | +0.010 |
uries | +0.010 |
Neg logit contributions | |
kiss | -0.009 |
ment | -0.008 |
fairy | -0.008 |
band | -0.008 |
bless | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
pole | +0.086 |
lves | +0.086 |
none | +0.083 |
chard | +0.083 |
favourites | +0.081 |
Neg logit contributions | |
kiss | -0.066 |
ment | -0.062 |
less | -0.057 |
bless | -0.055 |
prayer | -0.054 |
Token | regular |
Token ID | 3218 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
pole | +0.093 |
lves | +0.090 |
chard | +0.087 |
none | +0.086 |
One | +0.084 |
Neg logit contributions | |
kiss | -0.074 |
ment | -0.069 |
bless | -0.063 |
less | -0.063 |
forgiveness | -0.062 |
Token | or |
Token ID | 393 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
pole | +0.049 |
none | +0.046 |
lves | +0.046 |
One | +0.046 |
chard | +0.045 |
Neg logit contributions | |
kiss | -0.049 |
ment | -0.048 |
less | -0.044 |
bless | -0.043 |
forgiveness | -0.043 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
pole | +0.043 |
lves | +0.040 |
none | +0.038 |
chard | +0.038 |
One | +0.037 |
Neg logit contributions | |
kiss | -0.091 |
ment | -0.088 |
less | -0.083 |
bless | -0.082 |
forgiveness | -0.082 |
Token | ents |
Token ID | 658 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
lves | +0.280 |
none | +0.280 |
chard | +0.274 |
pole | +0.273 |
opes | +0.263 |
Neg logit contributions | |
ment | -0.551 |
kiss | -0.546 |
less | -0.530 |
ful | -0.517 |
of | -0.506 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
pole | +0.157 |
none | +0.147 |
chard | +0.142 |
lves | +0.141 |
pads | +0.138 |
Neg logit contributions | |
kiss | -0.164 |
ment | -0.155 |
forgiveness | -0.147 |
bless | -0.144 |
prayer | -0.143 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
pole | +0.065 |
lves | +0.060 |
none | +0.059 |
chard | +0.058 |
One | +0.055 |
Neg logit contributions | |
kiss | -0.149 |
ment | -0.144 |
less | -0.136 |
bless | -0.135 |
forgiveness | -0.134 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
kiss | +0.123 |
ment | +0.118 |
less | +0.107 |
bless | +0.106 |
forgiveness | +0.105 |
Neg logit contributions | |
pole | -0.134 |
lves | -0.130 |
none | -0.127 |
chard | -0.127 |
nam | -0.121 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
pole | +0.067 |
lves | +0.066 |
chard | +0.064 |
none | +0.064 |
uries | +0.063 |
Neg logit contributions | |
kiss | -0.044 |
ment | -0.042 |
less | -0.039 |
bless | -0.036 |
forgiveness | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
kiss | +0.040 |
ment | +0.037 |
prayer | +0.035 |
from | +0.031 |
less | +0.031 |
Neg logit contributions | |
pole | -0.044 |
lves | -0.043 |
nam | -0.041 |
chard | -0.041 |
none | -0.039 |
Token | give |
Token ID | 1577 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
pole | +0.010 |
lves | +0.010 |
none | +0.010 |
chard | +0.010 |
One | +0.010 |
Neg logit contributions | |
kiss | -0.006 |
ment | -0.006 |
less | -0.005 |
bless | -0.005 |
forgiveness | -0.005 |
Token | Spot |
Token ID | 15899 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.023 |
less | +0.021 |
bless | +0.021 |
forgiveness | +0.020 |
Neg logit contributions | |
pole | -0.022 |
lves | -0.021 |
none | -0.020 |
chard | -0.020 |
One | -0.020 |
Token | more |
Token ID | 517 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
pole | +0.071 |
lves | +0.069 |
none | +0.068 |
chard | +0.068 |
One | +0.066 |
Neg logit contributions | |
kiss | -0.057 |
ment | -0.055 |
less | -0.050 |
bless | -0.049 |
forgiveness | -0.049 |
Token | or |
Token ID | 393 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
pole | +0.017 |
One | +0.016 |
favorites | +0.016 |
pads | +0.016 |
none | +0.016 |
Neg logit contributions | |
less | -0.011 |
ment | -0.011 |
kiss | -0.011 |
ful | -0.011 |
forgiveness | -0.011 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.06e+00 |
Pos logit contributions | |
nam | +0.025 |
none | +0.024 |
pole | +0.024 |
chard | +0.023 |
pads | +0.023 |
Neg logit contributions | |
ment | -0.022 |
less | -0.021 |
kiss | -0.021 |
arl | -0.020 |
bless | -0.020 |
Token | ents |
Token ID | 658 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
pole | +0.220 |
lves | +0.210 |
chard | +0.209 |
none | +0.208 |
One | +0.193 |
Neg logit contributions | |
kiss | -0.611 |
ment | -0.598 |
less | -0.569 |
bless | -0.555 |
ful | -0.548 |
Token | . |
Token ID | 13 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
pole | +0.148 |
none | +0.144 |
pads | +0.130 |
chard | +0.124 |
One | +0.124 |
Neg logit contributions | |
kiss | -0.125 |
forgiveness | -0.125 |
irk | -0.120 |
prayer | -0.119 |
bless | -0.119 |
Token | Spot |
Token ID | 15899 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.028 |
prayer | +0.026 |
less | +0.026 |
band | +0.025 |
Neg logit contributions | |
pole | -0.025 |
lves | -0.024 |
chard | -0.023 |
nam | -0.022 |
none | -0.022 |
Token | leads |
Token ID | 5983 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
pole | +0.036 |
chard | +0.035 |
lves | +0.035 |
none | +0.034 |
nam | +0.033 |
Neg logit contributions | |
kiss | -0.028 |
ment | -0.026 |
bless | -0.024 |
prayer | -0.023 |
band | -0.023 |
Token | them |
Token ID | 606 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
pole | +0.028 |
none | +0.027 |
lves | +0.027 |
chard | +0.026 |
One | +0.026 |
Neg logit contributions | |
kiss | -0.029 |
ment | -0.028 |
less | -0.025 |
bless | -0.025 |
forgiveness | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
pole | +0.009 |
none | +0.009 |
chard | +0.009 |
One | +0.009 |
lves | +0.009 |
Neg logit contributions | |
kiss | -0.008 |
ment | -0.008 |
bless | -0.007 |
less | -0.007 |
forgiveness | -0.007 |
Token | shiny |
Token ID | 22441 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
pole | +0.011 |
none | +0.011 |
One | +0.011 |
chard | +0.011 |
lves | +0.011 |
Neg logit contributions | |
ment | -0.013 |
kiss | -0.013 |
less | -0.012 |
bless | -0.011 |
ful | -0.011 |
Token | things |
Token ID | 1243 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.013 |
bless | +0.012 |
less | +0.012 |
forgiveness | +0.012 |
Neg logit contributions | |
pole | -0.018 |
none | -0.017 |
chard | -0.017 |
lves | -0.017 |
One | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
kiss | +0.089 |
ment | +0.088 |
bless | +0.081 |
forgiveness | +0.078 |
less | +0.076 |
Neg logit contributions | |
none | -0.092 |
pole | -0.090 |
One | -0.085 |
chard | -0.085 |
lves | -0.083 |
Token | or |
Token ID | 393 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
pole | +0.064 |
lves | +0.062 |
chard | +0.060 |
none | +0.059 |
One | +0.058 |
Neg logit contributions | |
kiss | -0.058 |
ment | -0.055 |
less | -0.051 |
bless | -0.050 |
forgiveness | -0.050 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.05e+00 |
Pos logit contributions | |
none | +0.059 |
chard | +0.058 |
nam | +0.058 |
pole | +0.057 |
lves | +0.055 |
Neg logit contributions | |
kiss | -0.072 |
ment | -0.070 |
less | -0.065 |
bless | -0.065 |
forgiveness | -0.062 |
Token | ents |
Token ID | 658 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
pole | +0.255 |
none | +0.248 |
chard | +0.245 |
lves | +0.243 |
One | +0.232 |
Neg logit contributions | |
kiss | -0.551 |
ment | -0.542 |
less | -0.533 |
ful | -0.521 |
of | -0.500 |
Token | and |
Token ID | 290 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
pole | +0.178 |
none | +0.176 |
pads | +0.161 |
chard | +0.160 |
riages | +0.157 |
Neg logit contributions | |
kiss | -0.145 |
ment | -0.134 |
forgiveness | -0.129 |
bless | -0.129 |
prayer | -0.126 |
Token | they |
Token ID | 484 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
pole | +0.020 |
none | +0.020 |
lves | +0.019 |
chard | +0.019 |
One | +0.019 |
Neg logit contributions | |
kiss | -0.020 |
ment | -0.019 |
less | -0.017 |
bless | -0.017 |
forgiveness | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
pole | +0.067 |
lves | +0.065 |
chard | +0.063 |
none | +0.061 |
opes | +0.060 |
Neg logit contributions | |
kiss | -0.079 |
ment | -0.071 |
bless | -0.068 |
prayer | -0.067 |
forgiveness | -0.066 |
Token | very |
Token ID | 845 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
pole | +0.071 |
lves | +0.069 |
While | +0.067 |
chard | +0.065 |
opes | +0.065 |
Neg logit contributions | |
kiss | -0.054 |
fairy | -0.048 |
ment | -0.048 |
prayer | -0.048 |
from | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
pole | +0.210 |
lves | +0.205 |
chard | +0.201 |
none | +0.201 |
One | +0.196 |
Neg logit contributions | |
kiss | -0.116 |
ment | -0.109 |
less | -0.096 |
bless | -0.094 |
forgiveness | -0.092 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
kiss | +0.017 |
ment | +0.016 |
less | +0.015 |
forgiveness | +0.015 |
bless | +0.015 |
Neg logit contributions | |
pole | -0.017 |
lves | -0.016 |
chard | -0.016 |
none | -0.015 |
One | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
pole | +0.150 |
none | +0.142 |
One | +0.141 |
lves | +0.140 |
pads | +0.140 |
Neg logit contributions | |
kiss | -0.047 |
ment | -0.042 |
bless | -0.039 |
forgiveness | -0.037 |
prayer | -0.036 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
kiss | +0.069 |
ment | +0.066 |
less | +0.060 |
bless | +0.059 |
forgiveness | +0.059 |
Neg logit contributions | |
pole | -0.069 |
lves | -0.066 |
none | -0.065 |
chard | -0.065 |
One | -0.063 |
Token | or |
Token ID | 393 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
pole | +0.081 |
lves | +0.078 |
chard | +0.077 |
none | +0.076 |
uries | +0.073 |
Neg logit contributions | |
kiss | -0.091 |
ment | -0.090 |
less | -0.079 |
bless | -0.078 |
band | -0.078 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.03e+00 |
Pos logit contributions | |
pole | +0.033 |
lves | +0.032 |
opes | +0.030 |
One | +0.029 |
chard | +0.029 |
Neg logit contributions | |
kiss | -0.032 |
ment | -0.030 |
forgiveness | -0.028 |
fairy | -0.027 |
prayer | -0.027 |
Token | ents |
Token ID | 658 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
none | +0.279 |
chard | +0.276 |
One | +0.276 |
pole | +0.276 |
lves | +0.274 |
Neg logit contributions | |
ment | -0.508 |
less | -0.494 |
ful | -0.488 |
kiss | -0.488 |
of | -0.471 |
Token | . |
Token ID | 13 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
pole | +0.176 |
none | +0.166 |
chard | +0.161 |
pads | +0.157 |
lves | +0.156 |
Neg logit contributions | |
kiss | -0.131 |
ment | -0.118 |
forgiveness | -0.115 |
bless | -0.115 |
prayer | -0.113 |
Token | L |
Token ID | 406 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
pole | +0.003 |
chard | +0.003 |
lves | +0.003 |
nam | +0.003 |
opes | +0.003 |
Neg logit contributions | |
kiss | -0.002 |
ment | -0.002 |
less | -0.001 |
of | -0.001 |
shower | -0.001 |
Token | ila |
Token ID | 10102 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
pole | +0.023 |
lves | +0.023 |
none | +0.022 |
chard | +0.022 |
pads | +0.022 |
Neg logit contributions | |
kiss | -0.009 |
ment | -0.009 |
prayer | -0.008 |
forgiveness | -0.007 |
bless | -0.007 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.019 |
fairy | +0.018 |
band | +0.018 |
bless | +0.017 |
Neg logit contributions | |
lves | -0.032 |
chard | -0.031 |
pole | -0.031 |
nam | -0.030 |
none | -0.030 |
Token | can |
Token ID | 460 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
none | +0.002 |
pole | +0.002 |
One | +0.002 |
nam | +0.002 |
chard | +0.002 |
Neg logit contributions | |
ment | -0.002 |
kiss | -0.002 |
less | -0.002 |
guard | -0.002 |
forgiveness | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
kiss | +0.041 |
ment | +0.039 |
bless | +0.036 |
less | +0.036 |
forgiveness | +0.035 |
Neg logit contributions | |
pole | -0.042 |
lves | -0.041 |
chard | -0.040 |
none | -0.040 |
favourites | -0.038 |
Token | have |
Token ID | 423 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
kiss | +0.007 |
ment | +0.007 |
less | +0.006 |
forgiveness | +0.006 |
bless | +0.006 |
Neg logit contributions | |
pole | -0.010 |
lves | -0.010 |
none | -0.010 |
chard | -0.010 |
One | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
kiss | +0.040 |
band | +0.035 |
ment | +0.034 |
bless | +0.034 |
forgiveness | +0.034 |
Neg logit contributions | |
pole | -0.063 |
lves | -0.061 |
pads | -0.058 |
opes | -0.058 |
uries | -0.057 |
Token | or |
Token ID | 393 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
kiss | +0.014 |
ment | +0.013 |
less | +0.012 |
bless | +0.012 |
forgiveness | +0.012 |
Neg logit contributions | |
pole | -0.017 |
lves | -0.016 |
none | -0.016 |
chard | -0.016 |
One | -0.016 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
pole | +0.041 |
lves | +0.040 |
chard | +0.037 |
none | +0.037 |
One | +0.036 |
Neg logit contributions | |
kiss | -0.065 |
ment | -0.061 |
bless | -0.058 |
forgiveness | -0.057 |
less | -0.057 |
Token | ents |
Token ID | 658 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
lves | +0.271 |
none | +0.269 |
pole | +0.264 |
chard | +0.260 |
One | +0.259 |
Neg logit contributions | |
ment | -0.514 |
kiss | -0.513 |
less | -0.500 |
ful | -0.495 |
of | -0.477 |
Token | for |
Token ID | 329 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
pole | +0.134 |
none | +0.125 |
chard | +0.123 |
One | +0.114 |
pads | +0.110 |
Neg logit contributions | |
kiss | -0.126 |
ment | -0.123 |
forgiveness | -0.118 |
prayer | -0.116 |
bless | -0.112 |
Token | our |
Token ID | 674 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
kiss | +0.057 |
ment | +0.052 |
bless | +0.049 |
forgiveness | +0.049 |
band | +0.047 |
Neg logit contributions | |
pole | -0.079 |
lves | -0.077 |
pads | -0.074 |
chard | -0.073 |
none | -0.071 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
pole | +0.051 |
lves | +0.049 |
none | +0.049 |
chard | +0.049 |
favourites | +0.047 |
Neg logit contributions | |
kiss | -0.039 |
ment | -0.038 |
less | -0.034 |
bless | -0.033 |
forgiveness | -0.033 |
Token | man |
Token ID | 805 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
kiss | +0.070 |
ment | +0.069 |
less | +0.062 |
forgiveness | +0.061 |
bless | +0.061 |
Neg logit contributions | |
pole | -0.090 |
none | -0.084 |
chard | -0.083 |
lves | -0.081 |
One | -0.081 |
Token | Be |
Token ID | 3856 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
pole | +0.136 |
lves | +0.130 |
One | +0.126 |
none | +0.122 |
chard | +0.122 |
Neg logit contributions | |
kiss | -0.145 |
ment | -0.140 |
less | -0.133 |
forgiveness | -0.128 |
prayer | -0.127 |
Token | careful |
Token ID | 8161 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
kiss | +0.101 |
ment | +0.095 |
less | +0.090 |
prayer | +0.087 |
guard | +0.086 |
Neg logit contributions | |
pole | -0.096 |
none | -0.091 |
lves | -0.089 |
chard | -0.088 |
nam | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
kiss | +0.032 |
ment | +0.030 |
forgiveness | +0.028 |
band | +0.028 |
bless | +0.028 |
Neg logit contributions | |
pole | -0.033 |
none | -0.031 |
One | -0.030 |
opes | -0.029 |
uries | -0.029 |
Token | these |
Token ID | 777 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
pole | +0.010 |
none | +0.010 |
lves | +0.009 |
One | +0.009 |
chard | +0.009 |
Neg logit contributions | |
kiss | -0.009 |
ment | -0.009 |
less | -0.008 |
bless | -0.008 |
forgiveness | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
pole | +0.075 |
lves | +0.073 |
chard | +0.072 |
none | +0.071 |
One | +0.069 |
Neg logit contributions | |
kiss | -0.053 |
ment | -0.050 |
less | -0.045 |
bless | -0.045 |
forgiveness | -0.044 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
pole | +0.046 |
chard | +0.044 |
none | +0.044 |
lves | +0.044 |
nam | +0.042 |
Neg logit contributions | |
kiss | -0.056 |
ment | -0.054 |
less | -0.050 |
bless | -0.049 |
forgiveness | -0.049 |
Token | ents |
Token ID | 658 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
none | +0.265 |
lves | +0.261 |
pole | +0.260 |
chard | +0.257 |
One | +0.252 |
Neg logit contributions | |
ment | -0.533 |
kiss | -0.525 |
ful | -0.506 |
less | -0.505 |
bless | -0.490 |
Token | are |
Token ID | 389 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
pole | +0.142 |
none | +0.136 |
chard | +0.127 |
lves | +0.124 |
One | +0.124 |
Neg logit contributions | |
kiss | -0.110 |
ment | -0.104 |
forgiveness | -0.098 |
less | -0.097 |
prayer | -0.095 |
Token | very |
Token ID | 845 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
pole | +0.018 |
lves | +0.018 |
chard | +0.017 |
none | +0.017 |
One | +0.017 |
Neg logit contributions | |
kiss | -0.017 |
ment | -0.016 |
less | -0.015 |
bless | -0.015 |
prayer | -0.015 |
Token | special |
Token ID | 2041 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
pole | +0.184 |
lves | +0.177 |
chard | +0.177 |
none | +0.176 |
One | +0.169 |
Neg logit contributions | |
kiss | -0.167 |
ment | -0.160 |
less | -0.145 |
forgiveness | -0.144 |
bless | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
pole | +0.018 |
none | +0.018 |
favorites | +0.017 |
One | +0.017 |
chard | +0.017 |
Neg logit contributions | |
kiss | -0.014 |
ment | -0.013 |
less | -0.012 |
bless | -0.012 |
forgiveness | -0.012 |
Token | big |
Token ID | 1263 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ment | +0.033 |
kiss | +0.029 |
forgiveness | +0.027 |
bless | +0.027 |
iness | +0.027 |
Neg logit contributions | |
chard | -0.033 |
pole | -0.033 |
lves | -0.032 |
none | -0.031 |
One | -0.031 |
Token | tree |
Token ID | 5509 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
ment | +0.093 |
kiss | +0.088 |
less | +0.084 |
forgiveness | +0.083 |
bless | +0.081 |
Neg logit contributions | |
pole | -0.075 |
chard | -0.072 |
lves | -0.070 |
none | -0.070 |
One | -0.069 |
Token | with |
Token ID | 351 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
pole | +0.053 |
chard | +0.050 |
One | +0.050 |
none | +0.049 |
lves | +0.049 |
Neg logit contributions | |
kiss | -0.035 |
ment | -0.035 |
forgiveness | -0.032 |
bless | -0.031 |
less | -0.030 |
Token | many |
Token ID | 867 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
uries | +0.049 |
pole | +0.049 |
lves | +0.049 |
edy | +0.046 |
chard | +0.044 |
Neg logit contributions | |
kiss | -0.041 |
ment | -0.040 |
of | -0.037 |
band | -0.037 |
ful | -0.036 |
Token | or |
Token ID | 393 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
uries | +0.032 |
pole | +0.032 |
chard | +0.031 |
lves | +0.031 |
none | +0.030 |
Neg logit contributions | |
kiss | -0.028 |
ment | -0.027 |
of | -0.027 |
band | -0.025 |
ray | -0.025 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
pole | +0.043 |
lves | +0.040 |
none | +0.038 |
chard | +0.038 |
favourites | +0.037 |
Neg logit contributions | |
kiss | -0.062 |
ment | -0.060 |
less | -0.055 |
forgiveness | -0.054 |
bless | -0.054 |
Token | ents |
Token ID | 658 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
chard | +0.288 |
lves | +0.287 |
none | +0.287 |
pole | +0.277 |
opes | +0.262 |
Neg logit contributions | |
ment | -0.495 |
kiss | -0.494 |
less | -0.482 |
ful | -0.478 |
of | -0.476 |
Token | on |
Token ID | 319 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
pole | +0.167 |
none | +0.159 |
chard | +0.155 |
lves | +0.152 |
pads | +0.150 |
Neg logit contributions | |
kiss | -0.116 |
ment | -0.105 |
bless | -0.101 |
forgiveness | -0.101 |
prayer | -0.098 |
Token | it |
Token ID | 340 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
lves | +0.153 |
pole | +0.152 |
uries | +0.145 |
favourites | +0.143 |
cient | +0.143 |
Neg logit contributions | |
kiss | -0.077 |
ment | -0.074 |
band | -0.064 |
pain | -0.064 |
fairy | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
kiss | +0.008 |
ment | +0.007 |
less | +0.006 |
prayer | +0.006 |
ful | +0.006 |
Neg logit contributions | |
lves | -0.017 |
pole | -0.017 |
chard | -0.016 |
favourites | -0.016 |
none | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
pole | +0.001 |
opes | +0.001 |
lves | +0.001 |
uries | +0.001 |
cient | +0.001 |
Neg logit contributions | |
kiss | -0.001 |
of | -0.000 |
ment | -0.000 |
shower | -0.000 |
less | -0.000 |
Token | never |
Token ID | 1239 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
none | +0.024 |
chard | +0.022 |
pole | +0.021 |
nam | +0.020 |
lves | +0.019 |
Neg logit contributions | |
kiss | -0.047 |
ment | -0.046 |
less | -0.046 |
arl | -0.045 |
bless | -0.043 |
Token | played |
Token ID | 2826 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ment | +0.023 |
kiss | +0.022 |
less | +0.020 |
forgiveness | +0.020 |
bless | +0.020 |
Neg logit contributions | |
pole | -0.015 |
chard | -0.015 |
none | -0.015 |
One | -0.015 |
lves | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
pole | +0.018 |
none | +0.018 |
chard | +0.018 |
lves | +0.017 |
One | +0.017 |
Neg logit contributions | |
kiss | -0.013 |
ment | -0.013 |
prayer | -0.012 |
bless | -0.012 |
less | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
pole | +0.112 |
lves | +0.106 |
chard | +0.104 |
none | +0.103 |
One | +0.101 |
Neg logit contributions | |
kiss | -0.081 |
ment | -0.076 |
forgiveness | -0.068 |
bless | -0.068 |
less | -0.068 |
Token | or |
Token ID | 393 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
pole | +0.022 |
none | +0.022 |
chard | +0.022 |
lves | +0.022 |
favorites | +0.021 |
Neg logit contributions | |
ment | -0.025 |
kiss | -0.022 |
ful | -0.021 |
less | -0.020 |
bless | -0.020 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.02e+00 |
Pos logit contributions | |
chard | +0.053 |
none | +0.051 |
nam | +0.050 |
pole | +0.049 |
lves | +0.048 |
Neg logit contributions | |
ment | -0.047 |
kiss | -0.046 |
less | -0.041 |
prayer | -0.040 |
bless | -0.040 |
Token | ents |
Token ID | 658 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
none | +0.271 |
lves | +0.263 |
One | +0.260 |
chard | +0.257 |
pole | +0.256 |
Neg logit contributions | |
kiss | -0.523 |
ment | -0.520 |
less | -0.517 |
ful | -0.498 |
of | -0.485 |
Token | again |
Token ID | 757 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
pole | +0.136 |
none | +0.131 |
chard | +0.129 |
pads | +0.119 |
bank | +0.117 |
Neg logit contributions | |
kiss | -0.087 |
ment | -0.082 |
prayer | -0.078 |
bless | -0.076 |
forgiveness | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
kiss | +0.042 |
ment | +0.039 |
prayer | +0.037 |
bless | +0.037 |
less | +0.036 |
Neg logit contributions | |
none | -0.046 |
pole | -0.046 |
One | -0.045 |
chard | -0.044 |
pads | -0.043 |
Token | They |
Token ID | 1119 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
pole | +0.008 |
chard | +0.008 |
lves | +0.007 |
opes | +0.007 |
none | +0.007 |
Neg logit contributions | |
kiss | -0.005 |
ment | -0.005 |
prayer | -0.004 |
forgiveness | -0.004 |
bless | -0.004 |
Token | still |
Token ID | 991 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
pole | +0.019 |
lves | +0.018 |
opes | +0.017 |
chard | +0.017 |
pads | +0.017 |
Neg logit contributions | |
kiss | -0.022 |
ment | -0.019 |
bless | -0.019 |
band | -0.018 |
forgiveness | -0.018 |
Token | many |
Token ID | 867 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
lves | +0.029 |
pole | +0.028 |
chard | +0.027 |
cient | +0.027 |
uries | +0.026 |
Neg logit contributions | |
kiss | -0.019 |
ment | -0.017 |
band | -0.017 |
fairy | -0.016 |
of | -0.016 |
Token | colors |
Token ID | 7577 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
lves | +0.059 |
pole | +0.057 |
chard | +0.057 |
uries | +0.055 |
edy | +0.053 |
Neg logit contributions | |
kiss | -0.041 |
ment | -0.039 |
of | -0.036 |
band | -0.035 |
fairy | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
pole | +0.039 |
none | +0.037 |
pads | +0.036 |
chard | +0.036 |
One | +0.036 |
Neg logit contributions | |
kiss | -0.028 |
ment | -0.026 |
bless | -0.024 |
forgiveness | -0.024 |
prayer | -0.023 |
Token | Some |
Token ID | 2773 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
lves | +0.012 |
pole | +0.011 |
chard | +0.011 |
riages | +0.011 |
nam | +0.010 |
Neg logit contributions | |
kiss | -0.021 |
shower | -0.019 |
of | -0.019 |
moment | -0.019 |
forgiveness | -0.019 |
Token | or |
Token ID | 393 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
kiss | +0.015 |
ment | +0.015 |
bless | +0.013 |
less | +0.013 |
forgiveness | +0.013 |
Neg logit contributions | |
pole | -0.015 |
lves | -0.015 |
chard | -0.015 |
none | -0.014 |
uries | -0.014 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.01e+00 |
Pos logit contributions | |
pole | +0.039 |
lves | +0.037 |
chard | +0.034 |
none | +0.033 |
uries | +0.033 |
Neg logit contributions | |
kiss | -0.077 |
ment | -0.074 |
forgiveness | -0.069 |
bless | -0.069 |
band | -0.068 |
Token | ents |
Token ID | 658 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
chard | +0.281 |
lves | +0.278 |
none | +0.275 |
pole | +0.265 |
One | +0.256 |
Neg logit contributions | |
ment | -0.500 |
kiss | -0.498 |
ful | -0.479 |
less | -0.478 |
of | -0.470 |
Token | were |
Token ID | 547 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
pole | +0.121 |
none | +0.118 |
chard | +0.111 |
One | +0.102 |
pads | +0.102 |
Neg logit contributions | |
kiss | -0.133 |
ment | -0.126 |
forgiveness | -0.121 |
prayer | -0.121 |
bless | -0.120 |
Token | round |
Token ID | 2835 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
lves | +0.074 |
pole | +0.071 |
While | +0.068 |
opes | +0.068 |
pads | +0.068 |
Neg logit contributions | |
kiss | -0.061 |
ment | -0.056 |
less | -0.053 |
bless | -0.052 |
band | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
pole | +0.192 |
none | +0.187 |
lves | +0.182 |
One | +0.182 |
chard | +0.181 |
Neg logit contributions | |
kiss | -0.115 |
ment | -0.105 |
bless | -0.097 |
forgiveness | -0.096 |
less | -0.095 |
Token | some |
Token ID | 617 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
kiss | +0.002 |
ment | +0.002 |
less | +0.002 |
forgiveness | +0.002 |
bless | +0.002 |
Neg logit contributions | |
pole | -0.002 |
lves | -0.002 |
chard | -0.002 |
none | -0.002 |
favourites | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
pole | +0.088 |
lves | +0.084 |
chard | +0.081 |
none | +0.080 |
One | +0.078 |
Neg logit contributions | |
kiss | -0.101 |
ment | -0.096 |
less | -0.090 |
bless | -0.089 |
forgiveness | -0.088 |
Token | not |
Token ID | 407 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
pole | +0.049 |
lves | +0.049 |
opes | +0.044 |
chard | +0.044 |
One | +0.044 |
Neg logit contributions | |
kiss | -0.043 |
forgiveness | -0.039 |
ment | -0.039 |
band | -0.038 |
bless | -0.037 |
Token | touched |
Token ID | 12615 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
kiss | +0.085 |
ment | +0.082 |
less | +0.076 |
bless | +0.076 |
forgiveness | +0.075 |
Neg logit contributions | |
pole | -0.057 |
lves | -0.054 |
none | -0.054 |
chard | -0.053 |
One | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
pole | +0.057 |
lves | +0.055 |
chard | +0.053 |
uries | +0.052 |
favourites | +0.052 |
Neg logit contributions | |
kiss | -0.037 |
ment | -0.035 |
forgiveness | -0.031 |
bless | -0.031 |
less | -0.031 |
Token | or |
Token ID | 393 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
pole | +0.036 |
lves | +0.035 |
chard | +0.034 |
uries | +0.033 |
none | +0.033 |
Neg logit contributions | |
kiss | -0.035 |
ment | -0.031 |
bless | -0.030 |
fairy | -0.030 |
band | -0.029 |
Token | nam |
Token ID | 7402 |
Feature activation | +8.95e+00 |
Pos logit contributions | |
pole | +0.045 |
chard | +0.045 |
none | +0.044 |
lves | +0.043 |
nam | +0.042 |
Neg logit contributions | |
kiss | -0.060 |
ment | -0.059 |
less | -0.054 |
bless | -0.053 |
prayer | -0.052 |
Token | ents |
Token ID | 658 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
none | +0.247 |
pole | +0.247 |
lves | +0.245 |
opes | +0.236 |
One | +0.235 |
Neg logit contributions | |
kiss | -0.543 |
ment | -0.539 |
less | -0.523 |
ful | -0.512 |
bless | -0.501 |
Token | . |
Token ID | 13 |
Feature activation | +8.82e-03 |
Pos logit contributions | |
pole | +0.133 |
none | +0.129 |
chard | +0.123 |
bank | +0.115 |
One | +0.114 |
Neg logit contributions | |
kiss | -0.110 |
ment | -0.105 |
prayer | -0.099 |
bless | -0.099 |
forgiveness | -0.099 |
Token | They |
Token ID | 1119 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
pole | +0.000 |
lves | +0.000 |
chard | +0.000 |
cient | +0.000 |
opes | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
ment | -0.000 |
prayer | -0.000 |
less | -0.000 |
Time | -0.000 |
Token | hoped |
Token ID | 10719 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
pole | +0.024 |
lves | +0.022 |
chard | +0.021 |
opes | +0.021 |
uries | +0.021 |
Neg logit contributions | |
kiss | -0.027 |
ment | -0.023 |
band | -0.023 |
forgiveness | -0.022 |
fairy | -0.022 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
none | +0.019 |
One | +0.017 |
chard | +0.017 |
pole | +0.017 |
nam | +0.016 |
Neg logit contributions | |
kiss | -0.021 |
ment | -0.020 |
arl | -0.020 |
less | -0.019 |
ray | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
kiss | +0.085 |
ment | +0.080 |
less | +0.072 |
bless | +0.072 |
forgiveness | +0.072 |
Neg logit contributions | |
pole | -0.113 |
none | -0.110 |
chard | -0.108 |
lves | -0.107 |
One | -0.107 |
Token | play |
Token ID | 711 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
pole | +0.031 |
none | +0.030 |
lves | +0.030 |
chard | +0.030 |
One | +0.029 |
Neg logit contributions | |
kiss | -0.029 |
ment | -0.028 |
less | -0.026 |
bless | -0.025 |
forgiveness | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
kiss | +0.054 |
ment | +0.052 |
less | +0.046 |
bless | +0.046 |
prayer | +0.045 |
Neg logit contributions | |
pole | -0.081 |
lves | -0.078 |
none | -0.078 |
chard | -0.077 |
One | -0.075 |
Token | your |
Token ID | 534 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
pole | +0.092 |
lves | +0.089 |
chard | +0.087 |
none | +0.086 |
uries | +0.085 |
Neg logit contributions | |
kiss | -0.059 |
ment | -0.056 |
forgiveness | -0.049 |
band | -0.049 |
bless | -0.048 |
Token | or |
Token ID | 393 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ment | +0.017 |
kiss | +0.017 |
less | +0.016 |
bless | +0.016 |
ful | +0.015 |
Neg logit contributions | |
pole | -0.015 |
lves | -0.015 |
none | -0.015 |
chard | -0.015 |
favorites | -0.015 |
Token | nam |
Token ID | 7402 |
Feature activation | +8.92e+00 |
Pos logit contributions | |
chard | +0.057 |
pole | +0.057 |
none | +0.055 |
lves | +0.055 |
nam | +0.054 |
Neg logit contributions | |
ment | -0.055 |
kiss | -0.055 |
less | -0.050 |
bless | -0.048 |
prayer | -0.047 |
Token | ents |
Token ID | 658 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
none | +0.285 |
One | +0.283 |
lves | +0.281 |
pole | +0.275 |
chard | +0.272 |
Neg logit contributions | |
ment | -0.489 |
kiss | -0.487 |
less | -0.485 |
ful | -0.476 |
of | -0.464 |
Token | . |
Token ID | 13 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
pole | +0.138 |
none | +0.132 |
chard | +0.131 |
lves | +0.130 |
pads | +0.126 |
Neg logit contributions | |
kiss | -0.094 |
ment | -0.088 |
bless | -0.079 |
prayer | -0.078 |
forgiveness | -0.078 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
lves | +0.022 |
opes | +0.022 |
pole | +0.022 |
chard | +0.021 |
none | +0.020 |
Neg logit contributions | |
kiss | -0.020 |
ment | -0.018 |
prayer | -0.017 |
Time | -0.017 |
forgiveness | -0.016 |
Token | you |
Token ID | 345 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
pole | +0.004 |
lves | +0.004 |
chard | +0.003 |
none | +0.003 |
favourites | +0.003 |
Neg logit contributions | |
kiss | -0.003 |
ment | -0.003 |
bless | -0.002 |
forgiveness | -0.002 |
less | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
kiss | +0.136 |
ment | +0.122 |
bless | +0.113 |
less | +0.112 |
prayer | +0.108 |
Neg logit contributions | |
pole | -0.217 |
lves | -0.212 |
chard | -0.208 |
none | -0.205 |
opes | -0.201 |
Token | with |
Token ID | 351 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
pole | +0.042 |
chard | +0.040 |
none | +0.039 |
One | +0.039 |
lves | +0.039 |
Neg logit contributions | |
kiss | -0.030 |
ment | -0.029 |
forgiveness | -0.027 |
bless | -0.026 |
prayer | -0.026 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
pole | +0.046 |
lves | +0.045 |
chard | +0.043 |
none | +0.043 |
uries | +0.042 |
Neg logit contributions | |
kiss | -0.034 |
ment | -0.032 |
bless | -0.029 |
less | -0.029 |
forgiveness | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
pole | +0.119 |
One | +0.116 |
favorites | +0.113 |
favourites | +0.112 |
pads | +0.112 |
Neg logit contributions | |
kiss | -0.039 |
ment | -0.034 |
forgiveness | -0.034 |
less | -0.031 |
bless | -0.031 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
kiss | +0.092 |
ment | +0.088 |
bless | +0.079 |
less | +0.079 |
prayer | +0.078 |
Neg logit contributions | |
pole | -0.090 |
lves | -0.087 |
chard | -0.085 |
none | -0.085 |
uries | -0.081 |
Token | or |
Token ID | 393 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
pole | +0.079 |
chard | +0.076 |
lves | +0.076 |
none | +0.074 |
uries | +0.073 |
Neg logit contributions | |
kiss | -0.073 |
ment | -0.072 |
band | -0.063 |
bless | -0.062 |
prayer | -0.061 |
Token | nam |
Token ID | 7402 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
pole | +0.008 |
lves | +0.007 |
none | +0.006 |
chard | +0.006 |
One | +0.006 |
Neg logit contributions | |
kiss | -0.040 |
ment | -0.039 |
less | -0.037 |
bless | -0.037 |
forgiveness | -0.037 |
Token | ents |
Token ID | 658 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
pole | +0.258 |
none | +0.251 |
lves | +0.249 |
chard | +0.241 |
opes | +0.234 |
Neg logit contributions | |
kiss | -0.536 |
ment | -0.535 |
less | -0.515 |
ful | -0.502 |
bless | -0.492 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
pole | +0.163 |
none | +0.154 |
chard | +0.151 |
lves | +0.149 |
pads | +0.148 |
Neg logit contributions | |
kiss | -0.122 |
ment | -0.109 |
forgiveness | -0.107 |
prayer | -0.104 |
bless | -0.103 |
Token | One |
Token ID | 1881 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
kiss | +0.011 |
moment | +0.009 |
shower | +0.009 |
band | +0.008 |
prayer | +0.008 |
Neg logit contributions | |
lves | -0.010 |
riages | -0.010 |
chard | -0.010 |
opes | -0.010 |
pole | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
One | +0.012 |
pole | +0.011 |
chard | +0.011 |
While | +0.011 |
favourites | +0.011 |
Neg logit contributions | |
ment | -0.009 |
kiss | -0.009 |
forgiveness | -0.008 |
arl | -0.008 |
less | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
kiss | +0.159 |
ment | +0.152 |
bless | +0.134 |
forgiveness | +0.134 |
less | +0.133 |
Neg logit contributions | |
pole | -0.236 |
none | -0.230 |
lves | -0.229 |
chard | -0.226 |
One | -0.225 |
Token | ride |
Token ID | 6594 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
pole | +0.014 |
One | +0.013 |
chard | +0.013 |
lves | +0.013 |
none | +0.013 |
Neg logit contributions | |
ment | -0.011 |
ful | -0.009 |
kiss | -0.009 |
iness | -0.009 |
forgiveness | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
kiss | +0.039 |
ment | +0.038 |
bless | +0.035 |
prayer | +0.034 |
forgiveness | +0.033 |
Neg logit contributions | |
pole | -0.053 |
none | -0.050 |
chard | -0.049 |
One | -0.048 |
lves | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
ment | +0.015 |
kiss | +0.015 |
less | +0.014 |
prayer | +0.013 |
bless | +0.013 |
Neg logit contributions | |
pole | -0.021 |
none | -0.021 |
chard | -0.021 |
lves | -0.020 |
One | -0.020 |
Token | apple |
Token ID | 17180 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
pole | +0.030 |
chard | +0.030 |
lves | +0.029 |
none | +0.029 |
One | +0.028 |
Neg logit contributions | |
ment | -0.037 |
kiss | -0.035 |
less | -0.031 |
ful | -0.031 |
bless | -0.031 |
Token | or |
Token ID | 393 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
pole | +0.036 |
none | +0.034 |
chard | +0.034 |
lves | +0.034 |
One | +0.033 |
Neg logit contributions | |
kiss | -0.028 |
ment | -0.027 |
less | -0.024 |
bless | -0.024 |
forgiveness | -0.024 |
Token | chard |
Token ID | 30215 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
pole | +0.123 |
lves | +0.120 |
none | +0.116 |
chard | +0.115 |
One | +0.113 |
Neg logit contributions | |
kiss | -0.095 |
ment | -0.088 |
bless | -0.080 |
less | -0.080 |
forgiveness | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
pole | +0.507 |
none | +0.488 |
lves | +0.488 |
chard | +0.486 |
One | +0.473 |
Neg logit contributions | |
kiss | -0.317 |
ment | -0.302 |
less | -0.268 |
bless | -0.265 |
forgiveness | -0.260 |
Token | The |
Token ID | 383 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
pole | +0.008 |
lves | +0.008 |
opes | +0.008 |
pads | +0.008 |
chard | +0.008 |
Neg logit contributions | |
kiss | -0.010 |
ment | -0.009 |
band | -0.009 |
forgiveness | -0.009 |
less | -0.009 |
Token | neighbor |
Token ID | 4780 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
ment | +0.008 |
kiss | +0.008 |
less | +0.007 |
bless | +0.007 |
ful | +0.007 |
Neg logit contributions | |
pole | -0.010 |
chard | -0.010 |
none | -0.010 |
One | -0.009 |
lves | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
kiss | +0.004 |
ment | +0.004 |
less | +0.004 |
forgiveness | +0.004 |
bless | +0.004 |
Neg logit contributions | |
pole | -0.004 |
lves | -0.004 |
chard | -0.004 |
none | -0.004 |
opes | -0.004 |
Token | yes |
Token ID | 3763 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
none | +0.012 |
pole | +0.012 |
chard | +0.011 |
One | +0.011 |
lves | +0.011 |
Neg logit contributions | |
kiss | -0.014 |
ment | -0.013 |
bless | -0.012 |
less | -0.012 |
prayer | -0.012 |
Token | save |
Token ID | 3613 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
pole | +0.027 |
One | +0.026 |
bank | +0.026 |
none | +0.026 |
chard | +0.025 |
Neg logit contributions | |
ment | -0.026 |
less | -0.022 |
kiss | -0.021 |
prayer | -0.020 |
irk | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
kiss | +0.004 |
ment | +0.004 |
less | +0.004 |
bless | +0.004 |
prayer | +0.003 |
Neg logit contributions | |
pole | -0.005 |
lves | -0.005 |
none | -0.005 |
chard | -0.005 |
One | -0.005 |
Token | pup |
Token ID | 15552 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
pads | +0.049 |
favorites | +0.049 |
favourites | +0.048 |
none | +0.047 |
lves | +0.046 |
Neg logit contributions | |
ment | -0.048 |
kiss | -0.046 |
ful | -0.041 |
bless | -0.041 |
arl | -0.041 |
Token | from |
Token ID | 422 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
pole | +0.080 |
lves | +0.077 |
none | +0.077 |
chard | +0.076 |
One | +0.074 |
Neg logit contributions | |
kiss | -0.056 |
ment | -0.053 |
less | -0.047 |
bless | -0.047 |
prayer | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
pole | +0.055 |
lves | +0.053 |
none | +0.052 |
chard | +0.052 |
One | +0.051 |
Neg logit contributions | |
kiss | -0.040 |
ment | -0.038 |
less | -0.034 |
bless | -0.034 |
forgiveness | -0.033 |
Token | injuries |
Token ID | 6821 |
Feature activation | -7.70e+00 |
Pos logit contributions | |
none | +0.039 |
lves | +0.038 |
One | +0.038 |
chard | +0.037 |
bank | +0.037 |
Neg logit contributions | |
ment | -0.041 |
kiss | -0.035 |
less | -0.031 |
ful | -0.031 |
bless | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
kiss | +0.281 |
ment | +0.266 |
bless | +0.235 |
less | +0.232 |
forgiveness | +0.232 |
Neg logit contributions | |
pole | -0.438 |
none | -0.418 |
lves | -0.417 |
chard | -0.414 |
One | -0.406 |
Token | the |
Token ID | 262 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.022 |
less | +0.020 |
bless | +0.020 |
ray | +0.019 |
Neg logit contributions | |
none | -0.019 |
pole | -0.019 |
chard | -0.019 |
lves | -0.018 |
pads | -0.018 |
Token | pup |
Token ID | 15552 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
none | +0.009 |
lves | +0.009 |
bank | +0.009 |
pads | +0.009 |
favourites | +0.009 |
Neg logit contributions | |
ment | -0.010 |
kiss | -0.008 |
ful | -0.008 |
bless | -0.007 |
less | -0.007 |
Token | died |
Token ID | 3724 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
pole | +0.030 |
lves | +0.029 |
chard | +0.029 |
none | +0.028 |
One | +0.027 |
Neg logit contributions | |
kiss | -0.027 |
ment | -0.026 |
less | -0.024 |
bless | -0.023 |
forgiveness | -0.023 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
kiss | +0.099 |
bless | +0.088 |
ment | +0.088 |
forgiveness | +0.082 |
prayer | +0.081 |
Neg logit contributions | |
none | -0.110 |
pole | -0.109 |
chard | -0.104 |
lves | -0.102 |
pads | -0.101 |
Token | o |
Token ID | 78 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
pole | +0.069 |
lves | +0.066 |
chard | +0.064 |
none | +0.064 |
One | +0.061 |
Neg logit contributions | |
kiss | -0.099 |
ment | -0.095 |
less | -0.088 |
forgiveness | -0.088 |
bless | -0.088 |
Token | had |
Token ID | 550 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.023 |
bless | +0.021 |
less | +0.021 |
forgiveness | +0.020 |
Neg logit contributions | |
pole | -0.027 |
lves | -0.026 |
chard | -0.025 |
none | -0.025 |
nam | -0.024 |
Token | died |
Token ID | 3724 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
kiss | +0.044 |
ment | +0.042 |
less | +0.038 |
bless | +0.037 |
forgiveness | +0.037 |
Neg logit contributions | |
pole | -0.054 |
lves | -0.052 |
none | -0.051 |
chard | -0.051 |
One | -0.050 |
Token | from |
Token ID | 422 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
kiss | +0.112 |
bless | +0.099 |
ment | +0.099 |
prayer | +0.094 |
spell | +0.093 |
Neg logit contributions | |
none | -0.131 |
pole | -0.126 |
chard | -0.126 |
lves | -0.118 |
One | -0.118 |
Token | his |
Token ID | 465 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
none | +0.008 |
chard | +0.008 |
pole | +0.008 |
lves | +0.008 |
One | +0.008 |
Neg logit contributions | |
kiss | -0.009 |
ment | -0.009 |
less | -0.008 |
prayer | -0.008 |
bless | -0.008 |
Token | injuries |
Token ID | 6821 |
Feature activation | -7.68e+00 |
Pos logit contributions | |
ment | +0.001 |
kiss | +0.001 |
less | +0.001 |
ful | +0.001 |
bless | +0.001 |
Neg logit contributions | |
none | -0.001 |
chard | -0.001 |
favorites | -0.001 |
pole | -0.001 |
favourites | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
kiss | +0.285 |
ment | +0.270 |
forgiveness | +0.238 |
bless | +0.238 |
prayer | +0.237 |
Neg logit contributions | |
pole | -0.432 |
none | -0.413 |
lves | -0.406 |
chard | -0.405 |
One | -0.401 |
Token | His |
Token ID | 2399 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
ment | +0.013 |
kiss | +0.012 |
prayer | +0.011 |
forgiveness | +0.011 |
of | +0.010 |
Neg logit contributions | |
pole | -0.015 |
opes | -0.014 |
lves | -0.014 |
chard | -0.013 |
nam | -0.013 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.07e-01 |
Pos logit contributions | |
none | +0.014 |
favourites | +0.013 |
favorites | +0.013 |
chard | +0.013 |
pads | +0.013 |
Neg logit contributions | |
ment | -0.012 |
kiss | -0.012 |
less | -0.011 |
ful | -0.011 |
pour | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.030 |
less | +0.027 |
bless | +0.027 |
forgiveness | +0.027 |
Neg logit contributions | |
pole | -0.026 |
lves | -0.025 |
none | -0.024 |
chard | -0.024 |
One | -0.023 |
Token | very |
Token ID | 845 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
pole | +0.008 |
none | +0.007 |
lves | +0.007 |
chard | +0.007 |
One | +0.007 |
Neg logit contributions | |
kiss | -0.008 |
ment | -0.008 |
less | -0.007 |
bless | -0.007 |
prayer | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
none | +0.095 |
pole | +0.091 |
chard | +0.091 |
lves | +0.088 |
nam | +0.086 |
Neg logit contributions | |
kiss | -0.085 |
ment | -0.083 |
bless | -0.074 |
less | -0.074 |
forgiveness | -0.071 |
Token | go |
Token ID | 467 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
kiss | +0.158 |
ment | +0.149 |
less | +0.136 |
bless | +0.135 |
forgiveness | +0.133 |
Neg logit contributions | |
pole | -0.186 |
lves | -0.181 |
chard | -0.177 |
none | -0.176 |
One | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
kiss | +0.100 |
ment | +0.094 |
less | +0.084 |
bless | +0.083 |
forgiveness | +0.082 |
Neg logit contributions | |
pole | -0.150 |
lves | -0.145 |
none | -0.143 |
chard | -0.143 |
One | -0.138 |
Token | my |
Token ID | 616 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
pole | +0.003 |
none | +0.003 |
chard | +0.003 |
One | +0.003 |
lves | +0.003 |
Neg logit contributions | |
ment | -0.003 |
kiss | -0.003 |
less | -0.003 |
forgiveness | -0.002 |
bless | -0.002 |
Token | d |
Token ID | 288 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ment | +0.052 |
kiss | +0.051 |
less | +0.046 |
bless | +0.044 |
forgiveness | +0.044 |
Neg logit contributions | |
pole | -0.064 |
none | -0.062 |
chard | -0.062 |
favorites | -0.062 |
favourites | -0.061 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.64e+00 |
Pos logit contributions | |
kiss | +0.029 |
ment | +0.026 |
forgiveness | +0.025 |
prayer | +0.024 |
bless | +0.024 |
Neg logit contributions | |
pole | -0.065 |
lves | -0.060 |
none | -0.060 |
uries | -0.059 |
pads | -0.059 |
Token | ings |
Token ID | 654 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
kiss | +0.322 |
ment | +0.300 |
forgiveness | +0.287 |
less | +0.279 |
bless | +0.277 |
Neg logit contributions | |
pole | -0.386 |
none | -0.364 |
lves | -0.359 |
pads | -0.356 |
chard | -0.351 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
kiss | +0.066 |
ment | +0.066 |
forgiveness | +0.058 |
less | +0.058 |
prayer | +0.058 |
Neg logit contributions | |
pole | -0.079 |
none | -0.074 |
One | -0.073 |
chard | -0.072 |
lves | -0.072 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
kiss | +0.017 |
ment | +0.015 |
bless | +0.015 |
prayer | +0.014 |
forgiveness | +0.014 |
Neg logit contributions | |
pole | -0.016 |
lves | -0.016 |
chard | -0.015 |
none | -0.015 |
opes | -0.015 |
Token | your |
Token ID | 534 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
kiss | +0.039 |
less | +0.037 |
ment | +0.037 |
forgiveness | +0.036 |
prayer | +0.036 |
Neg logit contributions | |
none | -0.031 |
pole | -0.031 |
chard | -0.030 |
favorites | -0.030 |
One | -0.030 |
Token | lunch |
Token ID | 9965 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
ment | +0.012 |
less | +0.012 |
kiss | +0.012 |
ful | +0.012 |
pour | +0.011 |
Neg logit contributions | |
favorites | -0.013 |
favourites | -0.013 |
none | -0.013 |
bank | -0.013 |
chard | -0.013 |
Token | let |
Token ID | 1309 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
pole | +0.027 |
lves | +0.027 |
chard | +0.026 |
none | +0.026 |
favorites | +0.025 |
Neg logit contributions | |
kiss | -0.023 |
ment | -0.022 |
less | -0.020 |
bless | -0.020 |
forgiveness | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ment | +0.017 |
kiss | +0.017 |
less | +0.015 |
forgiveness | +0.015 |
prayer | +0.015 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.017 |
One | -0.017 |
none | -0.017 |
chard | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
pole | +0.085 |
One | +0.085 |
none | +0.081 |
Jerry | +0.075 |
While | +0.074 |
Neg logit contributions | |
kiss | -0.107 |
less | -0.102 |
ment | -0.102 |
guard | -0.102 |
bless | -0.101 |
Token | big |
Token ID | 1263 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ment | +0.008 |
iness | +0.007 |
guard | +0.007 |
ful | +0.007 |
forgiveness | +0.007 |
Neg logit contributions | |
pole | -0.007 |
One | -0.007 |
chard | -0.006 |
bank | -0.006 |
While | -0.006 |
Token | sn |
Token ID | 3013 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ment | +0.080 |
less | +0.071 |
guard | +0.067 |
bless | +0.066 |
forgiveness | +0.066 |
Neg logit contributions | |
pole | -0.074 |
One | -0.072 |
Jerry | -0.071 |
bank | -0.065 |
Ellie | -0.065 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
kiss | +0.054 |
prayer | +0.050 |
accidents | +0.050 |
bless | +0.049 |
forgiveness | +0.047 |
Neg logit contributions | |
pole | -0.070 |
One | -0.066 |
ratch | -0.062 |
lves | -0.062 |
While | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
forgiveness | +0.378 |
kiss | +0.345 |
bless | +0.332 |
accidents | +0.322 |
prise | +0.319 |
Neg logit contributions | |
pole | -0.327 |
bank | -0.298 |
One | -0.291 |
riages | -0.288 |
none | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
kiss | +0.080 |
ment | +0.077 |
less | +0.070 |
bless | +0.069 |
forgiveness | +0.068 |
Neg logit contributions | |
pole | -0.086 |
lves | -0.083 |
none | -0.081 |
chard | -0.081 |
One | -0.079 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ment | +0.035 |
kiss | +0.032 |
less | +0.031 |
arl | +0.030 |
bless | +0.030 |
Neg logit contributions | |
pole | -0.035 |
lves | -0.034 |
chard | -0.033 |
One | -0.033 |
bank | -0.032 |
Token | knew |
Token ID | 2993 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
pole | +0.059 |
none | +0.054 |
lves | +0.052 |
One | +0.051 |
chard | +0.051 |
Neg logit contributions | |
ment | -0.070 |
kiss | -0.069 |
bless | -0.064 |
less | -0.064 |
arl | -0.064 |
Token | he |
Token ID | 339 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
kiss | +0.019 |
ment | +0.018 |
less | +0.016 |
bless | +0.016 |
prayer | +0.016 |
Neg logit contributions | |
pole | -0.021 |
lves | -0.020 |
none | -0.020 |
chard | -0.020 |
One | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ment | +0.010 |
kiss | +0.010 |
less | +0.009 |
bless | +0.009 |
forgiveness | +0.009 |
Neg logit contributions | |
pole | -0.010 |
none | -0.009 |
One | -0.009 |
chard | -0.009 |
lves | -0.009 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
pole | +0.081 |
lves | +0.077 |
none | +0.077 |
chard | +0.076 |
One | +0.074 |
Neg logit contributions | |
kiss | -0.073 |
ment | -0.070 |
less | -0.064 |
bless | -0.063 |
forgiveness | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
pole | +0.018 |
none | +0.017 |
lves | +0.016 |
chard | +0.016 |
One | +0.016 |
Neg logit contributions | |
kiss | -0.016 |
ment | -0.015 |
bless | -0.014 |
less | -0.014 |
forgiveness | -0.013 |
Token | my |
Token ID | 616 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
pole | +0.013 |
none | +0.012 |
lves | +0.012 |
chard | +0.012 |
One | +0.012 |
Neg logit contributions | |
kiss | -0.013 |
ment | -0.013 |
less | -0.012 |
bless | -0.011 |
forgiveness | -0.011 |
Token | d |
Token ID | 288 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
ment | +0.036 |
kiss | +0.036 |
less | +0.032 |
bless | +0.031 |
forgiveness | +0.031 |
Neg logit contributions | |
pole | -0.044 |
none | -0.043 |
favorites | -0.042 |
favourites | -0.042 |
chard | -0.042 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.56e+00 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.027 |
prayer | +0.026 |
forgiveness | +0.025 |
bless | +0.025 |
Neg logit contributions | |
pole | -0.052 |
lves | -0.049 |
none | -0.048 |
favorites | -0.048 |
uries | -0.047 |
Token | ings |
Token ID | 654 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
kiss | +0.305 |
ment | +0.279 |
forgiveness | +0.274 |
bless | +0.262 |
less | +0.260 |
Neg logit contributions | |
pole | -0.388 |
none | -0.370 |
pads | -0.367 |
favorites | -0.359 |
opes | -0.354 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
ment | +0.070 |
kiss | +0.067 |
forgiveness | +0.061 |
prayer | +0.061 |
bless | +0.060 |
Neg logit contributions | |
pole | -0.069 |
One | -0.065 |
none | -0.064 |
chard | -0.061 |
lves | -0.060 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
pole | +0.145 |
lves | +0.144 |
chard | +0.137 |
none | +0.135 |
uries | +0.135 |
Neg logit contributions | |
kiss | -0.129 |
ment | -0.121 |
band | -0.107 |
forgiveness | -0.105 |
prayer | -0.105 |
Token | my |
Token ID | 1820 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
kiss | +0.137 |
ment | +0.136 |
less | +0.125 |
forgiveness | +0.122 |
bless | +0.121 |
Neg logit contributions | |
pole | -0.133 |
lves | -0.124 |
chard | -0.122 |
none | -0.122 |
One | -0.121 |
Token | says |
Token ID | 1139 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
kiss | +0.093 |
ment | +0.086 |
bless | +0.079 |
prayer | +0.077 |
forgiveness | +0.077 |
Neg logit contributions | |
pole | -0.098 |
lves | -0.098 |
chard | -0.095 |
none | -0.095 |
uries | -0.091 |
Token | f |
Token ID | 69 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
pole | +0.098 |
lves | +0.094 |
none | +0.092 |
chard | +0.092 |
One | +0.089 |
Neg logit contributions | |
kiss | -0.091 |
ment | -0.087 |
less | -0.080 |
bless | -0.079 |
forgiveness | -0.078 |
Token | ortunate |
Token ID | 13651 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
kiss | +0.025 |
ment | +0.023 |
forgiveness | +0.021 |
prayer | +0.021 |
bless | +0.020 |
Neg logit contributions | |
pole | -0.035 |
none | -0.033 |
lves | -0.033 |
One | -0.033 |
pads | -0.032 |
Token | y |
Token ID | 88 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
kiss | +0.056 |
ment | +0.054 |
forgiveness | +0.049 |
prayer | +0.048 |
bless | +0.046 |
Neg logit contributions | |
pole | -0.065 |
lves | -0.063 |
One | -0.060 |
none | -0.059 |
chard | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
pole | +0.148 |
One | +0.146 |
none | +0.146 |
lves | +0.145 |
bank | +0.140 |
Neg logit contributions | |
kiss | -0.145 |
ment | -0.143 |
forgiveness | -0.128 |
less | -0.127 |
bless | -0.124 |
Token | her |
Token ID | 607 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
ment | +0.009 |
kiss | +0.009 |
less | +0.008 |
arl | +0.008 |
bless | +0.008 |
Neg logit contributions | |
none | -0.009 |
lves | -0.008 |
chard | -0.008 |
pole | -0.008 |
nam | -0.008 |
Token | injuries |
Token ID | 6821 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
none | +0.009 |
favourites | +0.009 |
favorites | +0.009 |
lves | +0.009 |
pads | +0.009 |
Neg logit contributions | |
ment | -0.008 |
kiss | -0.008 |
Time | -0.007 |
guard | -0.007 |
less | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
kiss | +0.340 |
ment | +0.337 |
prayer | +0.310 |
forgiveness | +0.309 |
bless | +0.296 |
Neg logit contributions | |
pole | -0.349 |
none | -0.336 |
pads | -0.321 |
One | -0.312 |
lves | -0.312 |
Token | so |
Token ID | 523 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
pole | +0.029 |
none | +0.028 |
lves | +0.027 |
chard | +0.027 |
One | +0.026 |
Neg logit contributions | |
kiss | -0.031 |
ment | -0.031 |
less | -0.028 |
bless | -0.028 |
forgiveness | -0.027 |
Token | severe |
Token ID | 6049 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
chard | +0.140 |
none | +0.140 |
nam | +0.132 |
lves | +0.123 |
One | +0.123 |
Neg logit contributions | |
kiss | -0.187 |
ment | -0.176 |
bless | -0.170 |
forgiveness | -0.163 |
spell | -0.163 |
Token | , |
Token ID | 11 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
kiss | +0.044 |
less | +0.043 |
ment | +0.042 |
arl | +0.041 |
bless | +0.038 |
Neg logit contributions | |
pole | -0.049 |
One | -0.046 |
none | -0.046 |
bank | -0.046 |
lves | -0.045 |
Token | she |
Token ID | 673 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
kiss | +0.010 |
ment | +0.010 |
less | +0.010 |
arl | +0.010 |
bless | +0.009 |
Neg logit contributions | |
none | -0.010 |
nam | -0.009 |
One | -0.009 |
chard | -0.008 |
pole | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
none | +0.105 |
One | +0.101 |
pole | +0.099 |
chard | +0.098 |
favourites | +0.096 |
Neg logit contributions | |
kiss | -0.091 |
ment | -0.088 |
bless | -0.081 |
arl | -0.079 |
less | -0.077 |
Token | lightning |
Token ID | 14357 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ment | +0.137 |
kiss | +0.135 |
less | +0.123 |
bless | +0.120 |
forgiveness | +0.118 |
Neg logit contributions | |
pole | -0.152 |
chard | -0.145 |
none | -0.144 |
lves | -0.143 |
One | -0.138 |
Token | streak |
Token ID | 15113 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
kiss | +0.196 |
ment | +0.191 |
forgiveness | +0.184 |
less | +0.178 |
bless | +0.174 |
Neg logit contributions | |
pole | -0.232 |
none | -0.206 |
pads | -0.203 |
One | -0.202 |
lves | -0.197 |
Token | across |
Token ID | 1973 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
kiss | +0.046 |
ment | +0.042 |
forgiveness | +0.042 |
bless | +0.039 |
prayer | +0.038 |
Neg logit contributions | |
pole | -0.065 |
none | -0.060 |
One | -0.059 |
pads | -0.058 |
lves | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
kiss | +0.030 |
bless | +0.027 |
ment | +0.027 |
arl | +0.026 |
less | +0.026 |
Neg logit contributions | |
none | -0.025 |
One | -0.025 |
pole | -0.023 |
chard | -0.022 |
lves | -0.022 |
Token | night |
Token ID | 1755 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
ment | +0.110 |
kiss | +0.109 |
less | +0.100 |
forgiveness | +0.098 |
bless | +0.098 |
Neg logit contributions | |
pole | -0.098 |
lves | -0.095 |
chard | -0.092 |
none | -0.090 |
One | -0.089 |
Token | sky |
Token ID | 6766 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
kiss | +0.359 |
forgiveness | +0.348 |
arl | +0.324 |
ment | +0.321 |
bless | +0.320 |
Neg logit contributions | |
pole | -0.323 |
none | -0.309 |
One | -0.302 |
pads | -0.299 |
banks | -0.289 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
kiss | +0.079 |
forgiveness | +0.076 |
ment | +0.074 |
bless | +0.071 |
arl | +0.070 |
Neg logit contributions | |
pole | -0.094 |
none | -0.087 |
One | -0.084 |
chard | -0.082 |
pads | -0.082 |
Token | It |
Token ID | 632 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
lves | +0.009 |
pole | +0.009 |
chard | +0.009 |
opes | +0.009 |
none | +0.008 |
Neg logit contributions | |
kiss | -0.011 |
ment | -0.010 |
prayer | -0.009 |
bless | -0.009 |
forgiveness | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
kiss | +0.029 |
ment | +0.029 |
less | +0.027 |
forgiveness | +0.026 |
bless | +0.026 |
Neg logit contributions | |
pole | -0.030 |
none | -0.028 |
lves | -0.028 |
One | -0.028 |
chard | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
pole | +0.007 |
none | +0.007 |
chard | +0.007 |
lves | +0.007 |
One | +0.006 |
Neg logit contributions | |
kiss | -0.008 |
ment | -0.008 |
forgiveness | -0.007 |
less | -0.007 |
bless | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
kiss | +0.034 |
ment | +0.031 |
bless | +0.027 |
forgiveness | +0.027 |
less | +0.027 |
Neg logit contributions | |
pole | -0.060 |
lves | -0.058 |
chard | -0.057 |
none | -0.057 |
favourites | -0.056 |
Token | go |
Token ID | 467 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
ment | +0.100 |
kiss | +0.097 |
less | +0.088 |
bless | +0.083 |
forgiveness | +0.083 |
Neg logit contributions | |
pole | -0.150 |
One | -0.145 |
none | -0.141 |
lves | -0.141 |
chard | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
kiss | +0.088 |
ment | +0.084 |
less | +0.075 |
bless | +0.074 |
forgiveness | +0.074 |
Neg logit contributions | |
pole | -0.126 |
lves | -0.121 |
none | -0.119 |
chard | -0.119 |
One | -0.117 |
Token | my |
Token ID | 616 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
ment | +0.029 |
less | +0.025 |
kiss | +0.025 |
prayer | +0.024 |
bless | +0.023 |
Neg logit contributions | |
pole | -0.025 |
lves | -0.023 |
none | -0.023 |
One | -0.023 |
Jerry | -0.022 |
Token | d |
Token ID | 288 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ment | +0.035 |
kiss | +0.033 |
guard | +0.032 |
forgiveness | +0.032 |
fade | +0.031 |
Neg logit contributions | |
lves | -0.036 |
favorites | -0.035 |
pole | -0.035 |
favourites | -0.035 |
pads | -0.035 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.011 |
prayer | +0.011 |
forgiveness | +0.011 |
moment | +0.011 |
Neg logit contributions | |
pole | -0.040 |
lves | -0.039 |
One | -0.038 |
ratch | -0.038 |
opes | -0.037 |
Token | ings |
Token ID | 654 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
forgiveness | +0.363 |
kiss | +0.347 |
relief | +0.321 |
cheer | +0.320 |
miracle | +0.318 |
Neg logit contributions | |
pads | -0.281 |
pole | -0.272 |
none | -0.266 |
One | -0.264 |
opes | -0.261 |
Token | ," |
Token ID | 553 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
ment | +0.071 |
kiss | +0.070 |
prayer | +0.064 |
forgiveness | +0.064 |
bless | +0.063 |
Neg logit contributions | |
pole | -0.061 |
One | -0.056 |
lves | -0.054 |
none | -0.054 |
chard | -0.052 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
none | +0.124 |
One | +0.122 |
pole | +0.120 |
chard | +0.118 |
nam | +0.118 |
Neg logit contributions | |
ment | -0.136 |
less | -0.130 |
kiss | -0.128 |
bless | -0.124 |
ray | -0.118 |
Token | said |
Token ID | 531 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
ment | +0.117 |
kiss | +0.116 |
less | +0.109 |
bless | +0.106 |
forgiveness | +0.104 |
Neg logit contributions | |
pole | -0.100 |
none | -0.091 |
chard | -0.091 |
lves | -0.091 |
One | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
pole | +0.038 |
none | +0.037 |
chard | +0.037 |
One | +0.036 |
nam | +0.036 |
Neg logit contributions | |
kiss | -0.035 |
ment | -0.034 |
bless | -0.034 |
prayer | -0.032 |
Time | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
kiss | +0.076 |
ment | +0.068 |
bless | +0.066 |
prayer | +0.066 |
band | +0.065 |
Neg logit contributions | |
chard | -0.075 |
lves | -0.072 |
pole | -0.071 |
nam | -0.069 |
none | -0.069 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
pole | +0.075 |
lves | +0.074 |
chard | +0.071 |
none | +0.070 |
favourites | +0.068 |
Neg logit contributions | |
kiss | -0.062 |
ment | -0.058 |
less | -0.053 |
bless | -0.053 |
forgiveness | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
kiss | +0.107 |
ment | +0.105 |
pour | +0.092 |
bless | +0.092 |
ray | +0.091 |
Neg logit contributions | |
One | -0.117 |
none | -0.112 |
pole | -0.112 |
chard | -0.103 |
pads | -0.103 |
Token | my |
Token ID | 616 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ment | +0.007 |
kiss | +0.007 |
less | +0.007 |
bless | +0.006 |
forgiveness | +0.006 |
Neg logit contributions | |
pole | -0.007 |
none | -0.006 |
One | -0.006 |
lves | -0.006 |
chard | -0.006 |
Token | d |
Token ID | 288 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ment | +0.018 |
guard | +0.017 |
pour | +0.017 |
kiss | +0.016 |
ful | +0.016 |
Neg logit contributions | |
favorites | -0.015 |
favourites | -0.015 |
One | -0.014 |
none | -0.013 |
favorite | -0.013 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
kiss | +0.014 |
moment | +0.013 |
forgiveness | +0.012 |
ment | +0.012 |
prayer | +0.012 |
Neg logit contributions | |
pole | -0.037 |
opes | -0.035 |
ratch | -0.035 |
pads | -0.035 |
uries | -0.035 |
Token | ings |
Token ID | 654 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
forgiveness | +0.363 |
kiss | +0.351 |
relief | +0.334 |
accidents | +0.332 |
ful | +0.328 |
Neg logit contributions | |
pads | -0.271 |
bank | -0.263 |
favorites | -0.257 |
none | -0.257 |
pole | -0.256 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
ment | +0.064 |
kiss | +0.062 |
forgiveness | +0.055 |
prayer | +0.055 |
bless | +0.055 |
Neg logit contributions | |
pole | -0.065 |
One | -0.063 |
pads | -0.060 |
none | -0.059 |
riages | -0.056 |
Token | I |
Token ID | 314 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.029 |
less | +0.028 |
bless | +0.027 |
band | +0.027 |
Neg logit contributions | |
pole | -0.020 |
One | -0.019 |
none | -0.019 |
lves | -0.019 |
chard | -0.018 |
Token | forgive |
Token ID | 20927 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
ment | +0.056 |
kiss | +0.047 |
accidents | +0.046 |
less | +0.045 |
forgiveness | +0.044 |
Neg logit contributions | |
One | -0.061 |
none | -0.059 |
favourites | -0.058 |
favorites | -0.058 |
pole | -0.058 |
Token | you |
Token ID | 345 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
kiss | +0.088 |
ment | +0.086 |
less | +0.079 |
prayer | +0.075 |
bless | +0.074 |
Neg logit contributions | |
pole | -0.113 |
none | -0.110 |
One | -0.108 |
lves | -0.107 |
chard | -0.107 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ment | +0.040 |
kiss | +0.037 |
less | +0.034 |
forgiveness | +0.033 |
accidents | +0.033 |
Neg logit contributions | |
One | -0.041 |
none | -0.040 |
lves | -0.040 |
pole | -0.040 |
favourites | -0.040 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
kiss | +0.048 |
ment | +0.042 |
bless | +0.040 |
forgiveness | +0.039 |
band | +0.039 |
Neg logit contributions | |
pole | -0.080 |
lves | -0.078 |
pads | -0.078 |
opes | -0.076 |
chard | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
kiss | +0.051 |
ment | +0.049 |
less | +0.044 |
bless | +0.044 |
forgiveness | +0.043 |
Neg logit contributions | |
pole | -0.062 |
One | -0.061 |
none | -0.061 |
lves | -0.059 |
chard | -0.056 |
Token | my |
Token ID | 616 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
kiss | +0.020 |
ment | +0.020 |
less | +0.018 |
forgiveness | +0.018 |
bless | +0.018 |
Neg logit contributions | |
pole | -0.022 |
none | -0.022 |
lves | -0.021 |
One | -0.020 |
chard | -0.020 |
Token | d |
Token ID | 288 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
kiss | +0.034 |
ment | +0.033 |
bless | +0.029 |
less | +0.029 |
forgiveness | +0.029 |
Neg logit contributions | |
pole | -0.034 |
lves | -0.033 |
none | -0.033 |
One | -0.032 |
chard | -0.032 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.011 |
forgiveness | +0.011 |
prayer | +0.010 |
moment | +0.010 |
Neg logit contributions | |
pole | -0.042 |
lves | -0.039 |
opes | -0.039 |
One | -0.038 |
uries | -0.038 |
Token | ings |
Token ID | 654 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
forgiveness | +0.367 |
kiss | +0.352 |
relief | +0.339 |
accidents | +0.333 |
miracle | +0.330 |
Neg logit contributions | |
pole | -0.269 |
bank | -0.265 |
pads | -0.265 |
none | -0.261 |
opes | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ment | +0.066 |
kiss | +0.062 |
forgiveness | +0.058 |
bless | +0.056 |
prayer | +0.056 |
Neg logit contributions | |
pole | -0.064 |
One | -0.060 |
none | -0.058 |
pads | -0.057 |
Jerry | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.024 |
less | +0.022 |
bless | +0.022 |
forgiveness | +0.021 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.017 |
chard | -0.017 |
none | -0.017 |
favourites | -0.016 |
Token | tornado |
Token ID | 33718 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ment | +0.046 |
kiss | +0.043 |
less | +0.041 |
ful | +0.040 |
bless | +0.039 |
Neg logit contributions | |
pole | -0.042 |
none | -0.041 |
One | -0.040 |
lves | -0.039 |
chard | -0.038 |
Token | took |
Token ID | 1718 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
ment | +0.050 |
kiss | +0.046 |
less | +0.044 |
forgiveness | +0.042 |
ful | +0.041 |
Neg logit contributions | |
pole | -0.054 |
none | -0.051 |
lves | -0.050 |
One | -0.048 |
bank | -0.047 |
Token | What |
Token ID | 2061 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
lves | +0.130 |
One | +0.115 |
chard | +0.113 |
pole | +0.112 |
none | +0.111 |
Neg logit contributions | |
kiss | -0.147 |
ment | -0.146 |
prayer | -0.144 |
less | -0.139 |
ray | -0.135 |
Token | happened |
Token ID | 3022 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
kiss | +0.016 |
ment | +0.016 |
less | +0.014 |
bless | +0.013 |
prayer | +0.013 |
Neg logit contributions | |
pole | -0.017 |
none | -0.016 |
One | -0.016 |
chard | -0.016 |
lves | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.023 |
prayer | +0.021 |
fade | +0.021 |
ray | +0.021 |
Neg logit contributions | |
One | -0.017 |
chard | -0.017 |
none | -0.016 |
gonna | -0.016 |
Jerry | -0.015 |
Token | my |
Token ID | 616 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ment | +0.018 |
less | +0.016 |
kiss | +0.015 |
bless | +0.015 |
guard | +0.014 |
Neg logit contributions | |
none | -0.013 |
pole | -0.012 |
One | -0.012 |
lves | -0.011 |
Jerry | -0.011 |
Token | d |
Token ID | 288 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
kiss | +0.024 |
ment | +0.024 |
bless | +0.022 |
guard | +0.022 |
forgiveness | +0.022 |
Neg logit contributions | |
pole | -0.022 |
lves | -0.022 |
favorites | -0.022 |
favourites | -0.022 |
One | -0.022 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
kiss | +0.014 |
moment | +0.012 |
prayer | +0.012 |
forgiveness | +0.012 |
ment | +0.011 |
Neg logit contributions | |
pole | -0.038 |
lves | -0.037 |
opes | -0.036 |
ratch | -0.036 |
One | -0.036 |
Token | ings |
Token ID | 654 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
forgiveness | +0.371 |
kiss | +0.352 |
relief | +0.352 |
miracle | +0.341 |
comforting | +0.337 |
Neg logit contributions | |
pads | -0.252 |
none | -0.234 |
pole | -0.231 |
One | -0.231 |
bank | -0.230 |
Token | ? |
Token ID | 30 |
Feature activation | +7.26e-02 |
Pos logit contributions | |
ment | +0.067 |
kiss | +0.061 |
prayer | +0.058 |
forgiveness | +0.056 |
bless | +0.054 |
Neg logit contributions | |
pole | -0.054 |
One | -0.054 |
none | -0.051 |
chard | -0.050 |
pads | -0.049 |
Token | Why |
Token ID | 4162 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
pole | +0.003 |
lves | +0.003 |
none | +0.003 |
chard | +0.003 |
One | +0.002 |
Neg logit contributions | |
kiss | -0.004 |
ment | -0.004 |
less | -0.004 |
bless | -0.004 |
forgiveness | -0.004 |
Token | do |
Token ID | 466 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
pole | +0.016 |
none | +0.016 |
lves | +0.015 |
chard | +0.015 |
One | +0.015 |
Neg logit contributions | |
kiss | -0.015 |
ment | -0.015 |
less | -0.013 |
bless | -0.013 |
forgiveness | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
kiss | +0.036 |
ment | +0.035 |
less | +0.032 |
bless | +0.031 |
prayer | +0.030 |
Neg logit contributions | |
pole | -0.048 |
none | -0.048 |
lves | -0.047 |
chard | -0.046 |
One | -0.046 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ment | +0.048 |
kiss | +0.045 |
less | +0.040 |
forgiveness | +0.040 |
bless | +0.040 |
Neg logit contributions | |
One | -0.051 |
lves | -0.051 |
pole | -0.050 |
none | -0.050 |
favourites | -0.048 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
kiss | +0.055 |
ment | +0.049 |
bless | +0.045 |
forgiveness | +0.045 |
band | +0.045 |
Neg logit contributions | |
pole | -0.095 |
lves | -0.091 |
chard | -0.091 |
favourites | -0.089 |
favorites | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
kiss | +0.051 |
ment | +0.051 |
bless | +0.046 |
less | +0.045 |
pour | +0.044 |
Neg logit contributions | |
One | -0.058 |
pole | -0.056 |
none | -0.055 |
lves | -0.053 |
opes | -0.051 |
Token | my |
Token ID | 616 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
ment | +0.030 |
less | +0.027 |
kiss | +0.027 |
bless | +0.026 |
guard | +0.025 |
Neg logit contributions | |
none | -0.029 |
pole | -0.029 |
One | -0.027 |
nam | -0.026 |
chard | -0.026 |
Token | d |
Token ID | 288 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
kiss | +0.029 |
ment | +0.029 |
bless | +0.026 |
forgiveness | +0.026 |
guard | +0.026 |
Neg logit contributions | |
pole | -0.036 |
lves | -0.035 |
none | -0.034 |
favorites | -0.034 |
One | -0.033 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
kiss | +0.017 |
prayer | +0.014 |
ment | +0.014 |
moment | +0.014 |
forgiveness | +0.014 |
Neg logit contributions | |
pole | -0.046 |
lves | -0.043 |
One | -0.042 |
ratch | -0.042 |
opes | -0.042 |
Token | ings |
Token ID | 654 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
forgiveness | +0.371 |
kiss | +0.352 |
relief | +0.343 |
comforting | +0.342 |
miracle | +0.341 |
Neg logit contributions | |
pads | -0.242 |
bank | -0.236 |
none | -0.232 |
One | -0.230 |
pole | -0.230 |
Token | . |
Token ID | 13 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
ment | +0.073 |
kiss | +0.068 |
bless | +0.065 |
prayer | +0.064 |
forgiveness | +0.062 |
Neg logit contributions | |
pole | -0.060 |
One | -0.059 |
none | -0.053 |
pads | -0.052 |
Jerry | -0.051 |
Token | That |
Token ID | 1320 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.021 |
less | +0.020 |
bless | +0.019 |
forgiveness | +0.019 |
Neg logit contributions | |
pole | -0.013 |
lves | -0.012 |
none | -0.012 |
chard | -0.012 |
One | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pole | +0.028 |
lves | +0.028 |
chard | +0.027 |
none | +0.027 |
favourites | +0.026 |
Neg logit contributions | |
kiss | -0.025 |
ment | -0.023 |
bless | -0.021 |
forgiveness | -0.021 |
less | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
pole | +0.008 |
lves | +0.008 |
favourites | +0.007 |
favorites | +0.007 |
chard | +0.007 |
Neg logit contributions | |
kiss | -0.007 |
ment | -0.006 |
forgiveness | -0.006 |
less | -0.006 |
bless | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
kiss | +0.049 |
ment | +0.047 |
less | +0.043 |
bless | +0.043 |
forgiveness | +0.043 |
Neg logit contributions | |
pole | -0.041 |
lves | -0.040 |
chard | -0.039 |
none | -0.039 |
favourites | -0.037 |
Token | good |
Token ID | 922 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
pole | +0.065 |
lves | +0.063 |
none | +0.062 |
chard | +0.062 |
One | +0.060 |
Neg logit contributions | |
kiss | -0.065 |
ment | -0.063 |
less | -0.057 |
bless | -0.057 |
forgiveness | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
kiss | +0.017 |
bless | +0.016 |
fade | +0.016 |
ment | +0.016 |
pour | +0.016 |
Neg logit contributions | |
One | -0.013 |
favorites | -0.012 |
opes | -0.012 |
none | -0.012 |
pads | -0.012 |
Token | my |
Token ID | 616 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
ment | +0.030 |
kiss | +0.029 |
less | +0.027 |
bless | +0.026 |
guard | +0.025 |
Neg logit contributions | |
pole | -0.035 |
none | -0.033 |
lves | -0.032 |
One | -0.032 |
chard | -0.031 |
Token | d |
Token ID | 288 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.022 |
guard | +0.021 |
forgiveness | +0.020 |
bless | +0.020 |
Neg logit contributions | |
lves | -0.022 |
pole | -0.022 |
favorites | -0.022 |
favourites | -0.022 |
none | -0.022 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.26e+00 |
Pos logit contributions | |
kiss | +0.021 |
forgiveness | +0.019 |
prayer | +0.018 |
moment | +0.018 |
ment | +0.018 |
Neg logit contributions | |
pole | -0.036 |
lves | -0.035 |
opes | -0.034 |
ratch | -0.033 |
One | -0.033 |
Token | ings |
Token ID | 654 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
forgiveness | +0.359 |
kiss | +0.356 |
relief | +0.323 |
ful | +0.321 |
comforting | +0.316 |
Neg logit contributions | |
opes | -0.263 |
none | -0.262 |
pole | -0.253 |
bank | -0.252 |
pads | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
ment | +0.063 |
kiss | +0.061 |
bless | +0.056 |
forgiveness | +0.055 |
prayer | +0.055 |
Neg logit contributions | |
pole | -0.064 |
One | -0.061 |
none | -0.057 |
pads | -0.056 |
lves | -0.055 |
Token | I |
Token ID | 314 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.021 |
less | +0.020 |
bless | +0.020 |
forgiveness | +0.019 |
Neg logit contributions | |
pole | -0.015 |
lves | -0.015 |
none | -0.014 |
chard | -0.014 |
One | -0.014 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ment | +0.058 |
kiss | +0.054 |
less | +0.050 |
forgiveness | +0.050 |
prayer | +0.048 |
Neg logit contributions | |
lves | -0.063 |
pole | -0.063 |
One | -0.063 |
none | -0.062 |
favourites | -0.062 |
Token | glad |
Token ID | 9675 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
kiss | +0.076 |
ment | +0.070 |
bless | +0.066 |
less | +0.064 |
band | +0.064 |
Neg logit contributions | |
pole | -0.097 |
lves | -0.093 |
pads | -0.091 |
opes | -0.091 |
chard | -0.090 |
Token | The |
Token ID | 464 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
kiss | +0.035 |
ment | +0.035 |
prayer | +0.033 |
forgiveness | +0.032 |
bless | +0.032 |
Neg logit contributions | |
One | -0.038 |
lves | -0.037 |
pole | -0.037 |
While | -0.036 |
none | -0.035 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ment | +0.037 |
less | +0.033 |
kiss | +0.032 |
bless | +0.031 |
arl | +0.030 |
Neg logit contributions | |
chard | -0.043 |
pole | -0.042 |
nam | -0.040 |
none | -0.040 |
tallest | -0.040 |
Token | flew |
Token ID | 13112 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
pole | +0.035 |
lves | +0.033 |
none | +0.033 |
chard | +0.032 |
One | +0.031 |
Neg logit contributions | |
kiss | -0.040 |
ment | -0.038 |
less | -0.035 |
bless | -0.035 |
forgiveness | -0.034 |
Token | into |
Token ID | 656 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
kiss | +0.028 |
ment | +0.028 |
forgiveness | +0.026 |
bless | +0.026 |
prayer | +0.025 |
Neg logit contributions | |
pole | -0.030 |
none | -0.027 |
chard | -0.027 |
lves | -0.026 |
One | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
iness | +0.008 |
ment | +0.008 |
guard | +0.008 |
arl | +0.008 |
less | +0.007 |
Neg logit contributions | |
One | -0.004 |
none | -0.004 |
nam | -0.004 |
lves | -0.004 |
lots | -0.004 |
Token | night |
Token ID | 1755 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
ment | +0.080 |
less | +0.077 |
forgiveness | +0.077 |
ful | +0.075 |
bless | +0.073 |
Neg logit contributions | |
tallest | -0.050 |
One | -0.049 |
pole | -0.048 |
pads | -0.046 |
lves | -0.046 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
forgiveness | +0.397 |
apology | +0.369 |
arl | +0.353 |
kiss | +0.345 |
aid | +0.345 |
Neg logit contributions | |
pole | -0.271 |
pads | -0.255 |
One | -0.249 |
Suddenly | -0.248 |
banks | -0.235 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
forgiveness | +0.100 |
arl | +0.097 |
kiss | +0.093 |
bless | +0.090 |
ment | +0.090 |
Neg logit contributions | |
pole | -0.109 |
none | -0.096 |
One | -0.094 |
pads | -0.091 |
Suddenly | -0.088 |
Token | its |
Token ID | 663 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
ment | +0.011 |
kiss | +0.011 |
forgiveness | +0.010 |
less | +0.010 |
guard | +0.009 |
Neg logit contributions | |
pole | -0.011 |
none | -0.010 |
chard | -0.010 |
lves | -0.010 |
pads | -0.010 |
Token | colors |
Token ID | 7577 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
ment | +0.037 |
kiss | +0.037 |
less | +0.034 |
bless | +0.034 |
forgiveness | +0.033 |
Neg logit contributions | |
pole | -0.033 |
none | -0.033 |
chard | -0.032 |
favourites | -0.031 |
favorites | -0.031 |
Token | shimmer |
Token ID | 34493 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
forgiveness | +0.068 |
kiss | +0.068 |
ment | +0.066 |
bless | +0.065 |
prayer | +0.063 |
Neg logit contributions | |
pole | -0.066 |
none | -0.061 |
pads | -0.057 |
chard | -0.054 |
One | -0.053 |
Token | He |
Token ID | 679 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
kiss | +0.005 |
ment | +0.004 |
moment | +0.004 |
prayer | +0.004 |
band | +0.004 |
Neg logit contributions | |
pole | -0.009 |
lves | -0.009 |
chard | -0.008 |
none | -0.008 |
nam | -0.008 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
pole | +0.031 |
lves | +0.030 |
chard | +0.029 |
none | +0.029 |
opes | +0.028 |
Neg logit contributions | |
kiss | -0.038 |
ment | -0.035 |
band | -0.034 |
fairy | -0.033 |
prayer | -0.032 |
Token | up |
Token ID | 510 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
pole | +0.029 |
lves | +0.027 |
none | +0.027 |
chard | +0.027 |
uries | +0.027 |
Neg logit contributions | |
kiss | -0.020 |
ment | -0.019 |
less | -0.017 |
prayer | -0.017 |
bless | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
none | +0.049 |
One | +0.048 |
chard | +0.048 |
pole | +0.048 |
favourites | +0.045 |
Neg logit contributions | |
kiss | -0.044 |
bless | -0.040 |
ment | -0.040 |
forgiveness | -0.039 |
prayer | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
kiss | +0.014 |
less | +0.013 |
ment | +0.013 |
bless | +0.013 |
arl | +0.013 |
Neg logit contributions | |
nam | -0.013 |
One | -0.012 |
none | -0.012 |
chard | -0.012 |
bicycles | -0.012 |
Token | night |
Token ID | 1755 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
ment | +0.076 |
kiss | +0.073 |
ful | +0.069 |
forgiveness | +0.069 |
bless | +0.069 |
Neg logit contributions | |
One | -0.058 |
pole | -0.057 |
chard | -0.057 |
lves | -0.056 |
favorites | -0.054 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
forgiveness | +0.373 |
apology | +0.359 |
ment | +0.356 |
kiss | +0.350 |
arl | +0.349 |
Neg logit contributions | |
pole | -0.285 |
pads | -0.275 |
One | -0.270 |
ramids | -0.260 |
chard | -0.255 |
Token | and |
Token ID | 290 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
kiss | +0.107 |
forgiveness | +0.102 |
ment | +0.101 |
arl | +0.101 |
bless | +0.100 |
Neg logit contributions | |
pole | -0.112 |
none | -0.106 |
One | -0.104 |
pads | -0.099 |
chard | -0.097 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.012 |
less | +0.011 |
bless | +0.011 |
forgiveness | +0.011 |
Neg logit contributions | |
pole | -0.011 |
lves | -0.011 |
none | -0.010 |
chard | -0.010 |
One | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
pole | +0.036 |
lves | +0.035 |
chard | +0.034 |
none | +0.034 |
uries | +0.033 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.032 |
forgiveness | -0.029 |
less | -0.029 |
bless | -0.029 |
Token | tw |
Token ID | 665 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ment | +0.030 |
kiss | +0.027 |
less | +0.025 |
forgiveness | +0.025 |
iness | +0.025 |
Neg logit contributions | |
pole | -0.032 |
chard | -0.032 |
lves | -0.031 |
none | -0.030 |
One | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
kiss | +0.022 |
ment | +0.020 |
forgiveness | +0.018 |
less | +0.018 |
bless | +0.018 |
Neg logit contributions | |
pole | -0.043 |
lves | -0.042 |
chard | -0.041 |
favourites | -0.040 |
favorites | -0.040 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
kiss | +0.141 |
ment | +0.140 |
less | +0.124 |
bless | +0.123 |
prayer | +0.123 |
Neg logit contributions | |
pole | -0.127 |
none | -0.123 |
lves | -0.123 |
chard | -0.119 |
pads | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
ment | +0.116 |
kiss | +0.111 |
less | +0.100 |
bless | +0.096 |
guard | +0.096 |
Neg logit contributions | |
One | -0.101 |
pole | -0.099 |
none | -0.096 |
chard | -0.094 |
Jerry | -0.091 |
Token | my |
Token ID | 616 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ment | +0.001 |
kiss | +0.001 |
less | +0.001 |
bless | +0.001 |
guard | +0.001 |
Neg logit contributions | |
none | -0.001 |
One | -0.001 |
pole | -0.001 |
lves | -0.001 |
ours | -0.001 |
Token | d |
Token ID | 288 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
kiss | +0.016 |
ment | +0.016 |
bless | +0.015 |
forgiveness | +0.014 |
guard | +0.014 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.018 |
none | -0.017 |
opes | -0.017 |
One | -0.017 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.21e+00 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.011 |
prayer | +0.011 |
moment | +0.010 |
forgiveness | +0.010 |
Neg logit contributions | |
pole | -0.036 |
lves | -0.034 |
opes | -0.033 |
ratch | -0.033 |
One | -0.033 |
Token | ings |
Token ID | 654 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
forgiveness | +0.358 |
kiss | +0.344 |
relief | +0.325 |
miracle | +0.322 |
comforting | +0.321 |
Neg logit contributions | |
pads | -0.262 |
pole | -0.249 |
none | -0.248 |
bank | -0.247 |
One | -0.244 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
ment | +0.084 |
kiss | +0.076 |
prayer | +0.073 |
forgiveness | +0.071 |
less | +0.070 |
Neg logit contributions | |
pole | -0.046 |
One | -0.044 |
Jerry | -0.041 |
chard | -0.039 |
none | -0.038 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
One | +0.122 |
none | +0.116 |
chard | +0.113 |
pole | +0.110 |
nam | +0.109 |
Neg logit contributions | |
ment | -0.109 |
kiss | -0.105 |
less | -0.104 |
bless | -0.098 |
guard | -0.095 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
ment | +0.165 |
kiss | +0.160 |
less | +0.156 |
bless | +0.150 |
forgiveness | +0.149 |
Neg logit contributions | |
pole | -0.080 |
One | -0.070 |
chard | -0.069 |
none | -0.065 |
lves | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
One | +0.100 |
none | +0.098 |
chard | +0.095 |
pole | +0.095 |
nam | +0.093 |
Neg logit contributions | |
kiss | -0.112 |
prayer | -0.106 |
bless | -0.105 |
ment | -0.104 |
ray | -0.101 |
Token | you |
Token ID | 345 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.027 |
less | +0.024 |
bless | +0.024 |
forgiveness | +0.024 |
Neg logit contributions | |
pole | -0.055 |
lves | -0.053 |
chard | -0.052 |
none | -0.051 |
favourites | -0.051 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
kiss | +0.139 |
ment | +0.135 |
less | +0.122 |
bless | +0.121 |
forgiveness | +0.119 |
Neg logit contributions | |
pole | -0.140 |
lves | -0.135 |
none | -0.134 |
chard | -0.132 |
One | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ment | +0.125 |
kiss | +0.116 |
less | +0.107 |
sensation | +0.104 |
bless | +0.103 |
Neg logit contributions | |
One | -0.102 |
pole | -0.097 |
none | -0.094 |
Jerry | -0.091 |
chard | -0.091 |
Token | my |
Token ID | 616 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ment | +0.013 |
less | +0.010 |
ore | +0.010 |
sensation | +0.010 |
fade | +0.010 |
Neg logit contributions | |
none | -0.010 |
One | -0.010 |
pole | -0.009 |
Jerry | -0.009 |
ours | -0.009 |
Token | d |
Token ID | 288 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
ment | +0.009 |
kiss | +0.008 |
bless | +0.008 |
pour | +0.008 |
forgiveness | +0.008 |
Neg logit contributions | |
lves | -0.008 |
favorites | -0.007 |
favourites | -0.007 |
One | -0.007 |
pole | -0.007 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
kiss | +0.011 |
ment | +0.010 |
prayer | +0.009 |
forgiveness | +0.009 |
moment | +0.009 |
Neg logit contributions | |
pole | -0.030 |
lves | -0.029 |
opes | -0.028 |
ratch | -0.028 |
One | -0.027 |
Token | ings |
Token ID | 654 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
forgiveness | +0.337 |
kiss | +0.332 |
ful | +0.307 |
fairy | +0.305 |
relief | +0.303 |
Neg logit contributions | |
pads | -0.265 |
none | -0.263 |
pole | -0.262 |
opes | -0.258 |
One | -0.256 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
ment | +0.073 |
kiss | +0.064 |
prayer | +0.064 |
forgiveness | +0.061 |
bless | +0.060 |
Neg logit contributions | |
pole | -0.044 |
One | -0.042 |
Jerry | -0.038 |
chard | -0.035 |
Ellie | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
One | +0.120 |
none | +0.118 |
chard | +0.117 |
pole | +0.117 |
lves | +0.114 |
Neg logit contributions | |
ment | -0.103 |
kiss | -0.103 |
less | -0.097 |
bless | -0.093 |
prayer | -0.090 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
pole | +0.046 |
lves | +0.045 |
chard | +0.043 |
none | +0.043 |
favourites | +0.042 |
Neg logit contributions | |
kiss | -0.080 |
ment | -0.075 |
band | -0.072 |
forgiveness | -0.070 |
bless | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
pole | +0.120 |
none | +0.119 |
chard | +0.118 |
One | +0.117 |
nam | +0.114 |
Neg logit contributions | |
kiss | -0.101 |
ment | -0.096 |
bless | -0.092 |
prayer | -0.091 |
less | -0.087 |
Token | perfect |
Token ID | 2818 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
kiss | +0.007 |
ment | +0.006 |
bless | +0.006 |
forgiveness | +0.006 |
fairy | +0.006 |
Neg logit contributions | |
pole | -0.009 |
lves | -0.009 |
chard | -0.008 |
pads | -0.008 |
opes | -0.008 |
Token | fish |
Token ID | 5916 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
pole | +0.050 |
none | +0.049 |
favourites | +0.046 |
lves | +0.046 |
favorites | +0.046 |
Neg logit contributions | |
kiss | -0.048 |
ment | -0.047 |
bless | -0.042 |
forgiveness | -0.042 |
less | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
pole | +0.205 |
none | +0.192 |
chard | +0.190 |
lves | +0.189 |
pads | +0.183 |
Neg logit contributions | |
kiss | -0.160 |
ment | -0.154 |
forgiveness | -0.136 |
bless | -0.136 |
prayer | -0.135 |
Token | my |
Token ID | 616 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ment | +0.008 |
kiss | +0.007 |
less | +0.007 |
bless | +0.007 |
guard | +0.007 |
Neg logit contributions | |
pole | -0.007 |
none | -0.007 |
One | -0.007 |
lves | -0.007 |
nam | -0.007 |
Token | d |
Token ID | 288 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ment | +0.018 |
kiss | +0.018 |
less | +0.016 |
ful | +0.016 |
forgiveness | +0.016 |
Neg logit contributions | |
favorites | -0.019 |
favourites | -0.019 |
pole | -0.018 |
none | -0.018 |
lves | -0.018 |
Token | arl |
Token ID | 7063 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.012 |
forgiveness | +0.012 |
prayer | +0.012 |
bless | +0.011 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.017 |
chard | -0.016 |
none | -0.016 |
opes | -0.016 |
Token | ings |
Token ID | 654 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
forgiveness | +0.349 |
kiss | +0.344 |
relief | +0.322 |
miracle | +0.309 |
fairy | +0.309 |
Neg logit contributions | |
pads | -0.269 |
favorites | -0.268 |
opes | -0.267 |
none | -0.267 |
pole | -0.264 |
Token | ," |
Token ID | 553 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
ment | +0.054 |
kiss | +0.052 |
forgiveness | +0.048 |
prayer | +0.047 |
bless | +0.047 |
Neg logit contributions | |
pole | -0.059 |
One | -0.055 |
pads | -0.052 |
none | -0.052 |
Jerry | -0.051 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
One | +0.146 |
none | +0.143 |
nam | +0.140 |
chard | +0.136 |
pole | +0.135 |
Neg logit contributions | |
ment | -0.133 |
less | -0.122 |
kiss | -0.111 |
iness | -0.110 |
pour | -0.108 |
Token | says |
Token ID | 1139 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
kiss | +0.086 |
ment | +0.083 |
less | +0.076 |
bless | +0.075 |
forgiveness | +0.074 |
Neg logit contributions | |
pole | -0.091 |
lves | -0.087 |
none | -0.086 |
chard | -0.086 |
One | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
pole | +0.036 |
none | +0.036 |
One | +0.036 |
nam | +0.035 |
chard | +0.035 |
Neg logit contributions | |
kiss | -0.046 |
Time | -0.046 |
ment | -0.046 |
bless | -0.045 |
pour | -0.045 |
Token | magical |
Token ID | 10883 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
kiss | +0.026 |
ment | +0.025 |
ful | +0.023 |
less | +0.023 |
Time | +0.023 |
Neg logit contributions | |
pole | -0.030 |
none | -0.029 |
favorites | -0.029 |
favourites | -0.029 |
chard | -0.028 |
Token | snow |
Token ID | 6729 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
kiss | +0.074 |
ment | +0.071 |
less | +0.068 |
ful | +0.067 |
bless | +0.067 |
Neg logit contributions | |
pole | -0.070 |
none | -0.067 |
favourites | -0.065 |
One | -0.065 |
favorites | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
kiss | +0.109 |
forgiveness | +0.097 |
bless | +0.097 |
arl | +0.096 |
ment | +0.096 |
Neg logit contributions | |
pole | -0.123 |
none | -0.113 |
pads | -0.112 |
opes | -0.109 |
riages | -0.105 |
Token | filled |
Token ID | 5901 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
kiss | +0.127 |
ment | +0.126 |
less | +0.113 |
bless | +0.113 |
forgiveness | +0.110 |
Neg logit contributions | |
pole | -0.126 |
none | -0.125 |
chard | -0.119 |
lves | -0.117 |
One | -0.115 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
kiss | +0.027 |
ment | +0.026 |
prayer | +0.024 |
bless | +0.024 |
arl | +0.023 |
Neg logit contributions | |
pole | -0.033 |
none | -0.032 |
chard | -0.031 |
lves | -0.029 |
nam | -0.029 |
Token | night |
Token ID | 1755 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
ment | +0.060 |
kiss | +0.058 |
less | +0.053 |
forgiveness | +0.053 |
ful | +0.053 |
Neg logit contributions | |
pole | -0.061 |
lves | -0.058 |
tallest | -0.057 |
pads | -0.056 |
none | -0.056 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
forgiveness | +0.323 |
arl | +0.320 |
kiss | +0.320 |
apology | +0.311 |
ment | +0.305 |
Neg logit contributions | |
pole | -0.324 |
pads | -0.298 |
none | -0.294 |
One | -0.286 |
banks | -0.273 |
Token | with |
Token ID | 351 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
forgiveness | +0.089 |
kiss | +0.088 |
arl | +0.088 |
ment | +0.087 |
irk | +0.083 |
Neg logit contributions | |
pole | -0.106 |
none | -0.096 |
One | -0.092 |
pads | -0.091 |
tallest | -0.086 |
Token | beauty |
Token ID | 8737 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
none | +0.065 |
pole | +0.062 |
favourites | +0.060 |
One | +0.059 |
favorites | +0.059 |
Neg logit contributions | |
kiss | -0.058 |
ment | -0.057 |
arl | -0.053 |
bless | -0.053 |
guard | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
kiss | +0.074 |
forgiveness | +0.069 |
bless | +0.069 |
ment | +0.067 |
arl | +0.066 |
Neg logit contributions | |
pole | -0.089 |
none | -0.083 |
pads | -0.082 |
One | -0.077 |
chard | -0.076 |
Token | wonder |
Token ID | 4240 |
Feature activation | -9.53e-02 |
Pos logit contributions | |
none | +0.011 |
pole | +0.010 |
pads | +0.010 |
nam | +0.010 |
chard | +0.010 |
Neg logit contributions | |
kiss | -0.009 |
arl | -0.009 |
ment | -0.008 |
less | -0.008 |
guard | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
kiss | +0.043 |
ment | +0.041 |
bless | +0.041 |
forgiveness | +0.040 |
prayer | +0.037 |
Neg logit contributions | |
pole | -0.045 |
none | -0.041 |
pads | -0.040 |
One | -0.038 |
bank | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
kiss | +0.018 |
ment | +0.016 |
band | +0.015 |
prayer | +0.015 |
forgiveness | +0.015 |
Neg logit contributions | |
pole | -0.015 |
lves | -0.014 |
chard | -0.013 |
none | -0.013 |
favourites | -0.013 |
Token | rolled |
Token ID | 11686 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
kiss | +0.028 |
ment | +0.027 |
less | +0.025 |
bless | +0.025 |
forgiveness | +0.024 |
Neg logit contributions | |
pole | -0.030 |
none | -0.029 |
lves | -0.029 |
chard | -0.029 |
One | -0.028 |
Token | off |
Token ID | 572 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
pole | +0.002 |
none | +0.002 |
lves | +0.002 |
chard | +0.002 |
One | +0.002 |
Neg logit contributions | |
kiss | -0.002 |
ment | -0.001 |
bless | -0.001 |
forgiveness | -0.001 |
prayer | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
pole | +0.015 |
none | +0.015 |
One | +0.015 |
chard | +0.014 |
lves | +0.014 |
Neg logit contributions | |
kiss | -0.012 |
ment | -0.011 |
bless | -0.010 |
less | -0.010 |
forgiveness | -0.010 |
Token | night |
Token ID | 1755 |
Feature activation | -7.10e+00 |
Pos logit contributions | |
ment | +0.075 |
kiss | +0.066 |
less | +0.066 |
bless | +0.063 |
ful | +0.063 |
Neg logit contributions | |
pole | -0.055 |
bank | -0.053 |
One | -0.052 |
banks | -0.052 |
pads | -0.051 |
Token | stand |
Token ID | 1481 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
forgiveness | +0.314 |
ment | +0.291 |
apology | +0.272 |
irk | +0.272 |
kiss | +0.269 |
Neg logit contributions | |
pads | -0.347 |
pole | -0.342 |
One | -0.322 |
bank | -0.311 |
banks | -0.301 |
Token | and |
Token ID | 290 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
kiss | +0.188 |
ment | +0.182 |
forgiveness | +0.161 |
bless | +0.161 |
less | +0.155 |
Neg logit contributions | |
pole | -0.308 |
none | -0.292 |
lves | -0.288 |
chard | -0.287 |
One | -0.283 |
Token | under |
Token ID | 739 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
kiss | +0.037 |
ment | +0.037 |
less | +0.035 |
bless | +0.034 |
forgiveness | +0.033 |
Neg logit contributions | |
none | -0.030 |
chard | -0.030 |
pole | -0.029 |
lves | -0.029 |
nam | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
pole | +0.052 |
lves | +0.050 |
none | +0.050 |
chard | +0.050 |
One | +0.049 |
Neg logit contributions | |
kiss | -0.036 |
ment | -0.035 |
less | -0.031 |
bless | -0.031 |
forgiveness | -0.030 |
Token | bed |
Token ID | 3996 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
ment | +0.008 |
less | +0.007 |
forgiveness | +0.007 |
irk | +0.007 |
iness | +0.007 |
Neg logit contributions | |
One | -0.006 |
bank | -0.006 |
banks | -0.006 |
pole | -0.006 |
floppy | -0.005 |
Token | take |
Token ID | 1011 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
pole | +0.020 |
none | +0.019 |
chard | +0.019 |
One | +0.018 |
lves | +0.018 |
Neg logit contributions | |
ment | -0.011 |
kiss | -0.011 |
less | -0.010 |
prayer | -0.009 |
forgiveness | -0.009 |
Token | them |
Token ID | 606 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
kiss | +0.056 |
ment | +0.053 |
bless | +0.048 |
less | +0.048 |
band | +0.047 |
Neg logit contributions | |
pole | -0.067 |
lves | -0.064 |
chard | -0.063 |
none | -0.062 |
opes | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
pole | +0.015 |
none | +0.015 |
lves | +0.015 |
chard | +0.015 |
One | +0.014 |
Neg logit contributions | |
kiss | -0.011 |
ment | -0.011 |
bless | -0.009 |
prayer | -0.009 |
forgiveness | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
kiss | +0.003 |
ment | +0.003 |
less | +0.002 |
bless | +0.002 |
forgiveness | +0.002 |
Neg logit contributions | |
pole | -0.005 |
lves | -0.005 |
none | -0.005 |
chard | -0.005 |
One | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
pole | +0.055 |
pads | +0.053 |
lves | +0.053 |
opes | +0.051 |
nam | +0.051 |
Neg logit contributions | |
kiss | -0.054 |
fairy | -0.046 |
guard | -0.046 |
band | -0.046 |
bless | -0.046 |
Token | igator |
Token ID | 23823 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
pole | +0.064 |
lves | +0.062 |
none | +0.061 |
chard | +0.061 |
One | +0.059 |
Neg logit contributions | |
kiss | -0.059 |
ment | -0.056 |
less | -0.051 |
bless | -0.051 |
forgiveness | -0.050 |
Token | pond |
Token ID | 16723 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
pole | +0.363 |
lves | +0.353 |
none | +0.347 |
chard | +0.346 |
One | +0.337 |
Neg logit contributions | |
kiss | -0.208 |
ment | -0.195 |
less | -0.172 |
bless | -0.170 |
forgiveness | -0.167 |
Token | . |
Token ID | 13 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
pole | +0.164 |
none | +0.158 |
chard | +0.158 |
lves | +0.155 |
One | +0.152 |
Neg logit contributions | |
kiss | -0.106 |
ment | -0.099 |
bless | -0.090 |
less | -0.089 |
forgiveness | -0.088 |
Token |
|
Token ID | 198 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
lves | +0.004 |
pole | +0.004 |
opes | +0.004 |
pads | +0.004 |
uries | +0.004 |
Neg logit contributions | |
kiss | -0.003 |
ment | -0.002 |
prayer | -0.002 |
voice | -0.002 |
nurse | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.011 |
band | +0.011 |
less | +0.010 |
bless | +0.010 |
Neg logit contributions | |
pole | -0.019 |
lves | -0.019 |
none | -0.019 |
nam | -0.019 |
chard | -0.019 |
Token | Mom |
Token ID | 29252 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
kiss | +0.027 |
ment | +0.024 |
less | +0.022 |
bless | +0.022 |
band | +0.022 |
Neg logit contributions | |
pole | -0.038 |
lves | -0.037 |
none | -0.036 |
chard | -0.036 |
opes | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
none | +0.076 |
pole | +0.074 |
pads | +0.071 |
One | +0.070 |
chard | +0.070 |
Neg logit contributions | |
ment | -0.072 |
kiss | -0.070 |
bless | -0.064 |
forgiveness | -0.062 |
less | -0.062 |
Token | She |
Token ID | 1375 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
pole | +0.001 |
lves | +0.000 |
chard | +0.000 |
edy | +0.000 |
none | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
ment | -0.000 |
prayer | -0.000 |
bless | -0.000 |
forgiveness | -0.000 |
Token | did |
Token ID | 750 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
pole | +0.026 |
lves | +0.025 |
chard | +0.025 |
none | +0.024 |
nam | +0.023 |
Neg logit contributions | |
kiss | -0.029 |
ment | -0.027 |
bless | -0.025 |
prayer | -0.025 |
band | -0.025 |
Token | not |
Token ID | 407 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ment | +0.025 |
kiss | +0.025 |
less | +0.023 |
bless | +0.023 |
guard | +0.022 |
Neg logit contributions | |
none | -0.013 |
pole | -0.013 |
One | -0.012 |
chard | -0.012 |
lves | -0.012 |
Token | like |
Token ID | 588 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
ment | +0.073 |
less | +0.065 |
accidents | +0.063 |
forgiveness | +0.063 |
kiss | +0.061 |
Neg logit contributions | |
pole | -0.050 |
One | -0.049 |
uries | -0.047 |
none | -0.046 |
chard | -0.045 |
Token | sheep |
Token ID | 15900 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
none | +0.032 |
lves | +0.031 |
pole | +0.031 |
chard | +0.031 |
One | +0.031 |
Neg logit contributions | |
kiss | -0.029 |
ment | -0.028 |
less | -0.026 |
bless | -0.025 |
forgiveness | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
pole | +0.295 |
none | +0.290 |
pads | +0.282 |
lves | +0.281 |
chard | +0.279 |
Neg logit contributions | |
ment | -0.260 |
kiss | -0.256 |
bless | -0.226 |
less | -0.225 |
forgiveness | -0.225 |
Token | She |
Token ID | 1375 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
pole | +0.005 |
lves | +0.005 |
chard | +0.005 |
none | +0.004 |
uries | +0.004 |
Neg logit contributions | |
kiss | -0.005 |
ment | -0.004 |
prayer | -0.004 |
bless | -0.004 |
less | -0.004 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
pole | +0.027 |
lves | +0.026 |
chard | +0.025 |
none | +0.025 |
nam | +0.024 |
Neg logit contributions | |
kiss | -0.030 |
ment | -0.027 |
bless | -0.025 |
prayer | -0.025 |
band | -0.025 |
Token | pizza |
Token ID | 14256 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
none | +0.067 |
pole | +0.065 |
chard | +0.065 |
One | +0.065 |
lves | +0.064 |
Neg logit contributions | |
kiss | -0.059 |
ment | -0.058 |
less | -0.054 |
bless | -0.051 |
forgiveness | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
none | +0.139 |
pole | +0.135 |
pads | +0.128 |
One | +0.125 |
chard | +0.123 |
Neg logit contributions | |
ment | -0.129 |
kiss | -0.127 |
bless | -0.118 |
less | -0.118 |
arl | -0.117 |
Token | she |
Token ID | 673 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
kiss | +0.014 |
bless | +0.012 |
ment | +0.012 |
guard | +0.012 |
ray | +0.012 |
Neg logit contributions | |
none | -0.014 |
One | -0.013 |
pole | -0.013 |
lves | -0.013 |
chard | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
pole | +0.051 |
lves | +0.048 |
chard | +0.046 |
favorites | +0.046 |
One | +0.046 |
Neg logit contributions | |
kiss | -0.050 |
ment | -0.047 |
less | -0.044 |
bless | -0.044 |
forgiveness | -0.043 |
Token | listened |
Token ID | 16399 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
pole | +0.002 |
lves | +0.002 |
chard | +0.001 |
opes | +0.001 |
favourites | +0.001 |
Neg logit contributions | |
kiss | -0.002 |
ment | -0.001 |
forgiveness | -0.001 |
bless | -0.001 |
less | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
kiss | +0.018 |
ment | +0.017 |
bless | +0.016 |
forgiveness | +0.015 |
prayer | +0.015 |
Neg logit contributions | |
pole | -0.024 |
none | -0.024 |
One | -0.024 |
chard | -0.023 |
lves | -0.023 |
Token | Dog |
Token ID | 8532 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
kiss | +0.018 |
ment | +0.017 |
bless | +0.015 |
less | +0.015 |
forgiveness | +0.015 |
Neg logit contributions | |
pole | -0.021 |
lves | -0.020 |
chard | -0.020 |
none | -0.020 |
favourites | -0.019 |
Token | gy |
Token ID | 1360 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
pole | +0.052 |
lves | +0.050 |
chard | +0.048 |
none | +0.048 |
favourites | +0.044 |
Neg logit contributions | |
kiss | -0.172 |
ment | -0.166 |
less | -0.158 |
bless | -0.157 |
forgiveness | -0.155 |
Token | . |
Token ID | 13 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
pole | +0.331 |
none | +0.320 |
lves | +0.314 |
One | +0.313 |
chard | +0.312 |
Neg logit contributions | |
kiss | -0.234 |
ment | -0.230 |
less | -0.206 |
bless | -0.201 |
forgiveness | -0.197 |
Token | Now |
Token ID | 2735 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
ment | +0.023 |
kiss | +0.023 |
prayer | +0.022 |
band | +0.020 |
bless | +0.020 |
Neg logit contributions | |
chard | -0.022 |
pole | -0.022 |
nam | -0.021 |
favourites | -0.021 |
lves | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
kiss | +0.109 |
ment | +0.104 |
less | +0.094 |
bless | +0.093 |
forgiveness | +0.091 |
Neg logit contributions | |
pole | -0.143 |
lves | -0.139 |
chard | -0.137 |
none | -0.136 |
favourites | -0.132 |
Token | Kitty |
Token ID | 21168 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
kiss | +0.008 |
ment | +0.008 |
less | +0.008 |
forgiveness | +0.007 |
bless | +0.007 |
Neg logit contributions | |
pole | -0.007 |
none | -0.007 |
lves | -0.006 |
One | -0.006 |
chard | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
pole | +0.046 |
lves | +0.044 |
chard | +0.043 |
none | +0.043 |
nam | +0.041 |
Neg logit contributions | |
kiss | -0.049 |
ment | -0.046 |
bless | -0.043 |
less | -0.043 |
forgiveness | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
pole | +0.023 |
lves | +0.023 |
chard | +0.022 |
opes | +0.021 |
ramids | +0.021 |
Neg logit contributions | |
kiss | -0.014 |
ment | -0.013 |
less | -0.012 |
forgiveness | -0.012 |
band | -0.012 |
Token | promise |
Token ID | 6991 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
pole | +0.002 |
none | +0.002 |
One | +0.002 |
uries | +0.002 |
chard | +0.002 |
Neg logit contributions | |
ment | -0.002 |
less | -0.002 |
kiss | -0.001 |
accidents | -0.001 |
guard | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
kiss | +0.055 |
ment | +0.053 |
less | +0.048 |
bless | +0.048 |
prayer | +0.046 |
Neg logit contributions | |
none | -0.065 |
pole | -0.065 |
chard | -0.062 |
lves | -0.062 |
One | -0.062 |
Token | always |
Token ID | 1464 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
pole | +0.056 |
none | +0.055 |
One | +0.053 |
chard | +0.051 |
uries | +0.051 |
Neg logit contributions | |
ment | -0.048 |
less | -0.043 |
kiss | -0.042 |
irk | -0.039 |
accidents | -0.039 |
Token | be |
Token ID | 307 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
pole | +0.051 |
none | +0.050 |
One | +0.049 |
uries | +0.048 |
chard | +0.048 |
Neg logit contributions | |
ment | -0.042 |
less | -0.039 |
kiss | -0.036 |
accidents | -0.036 |
guard | -0.035 |
Token | best |
Token ID | 1266 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
kiss | +0.063 |
ment | +0.059 |
less | +0.053 |
bless | +0.052 |
forgiveness | +0.052 |
Neg logit contributions | |
pole | -0.101 |
lves | -0.099 |
chard | -0.095 |
opes | -0.095 |
none | -0.095 |
Token | friends |
Token ID | 2460 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
pole | +0.270 |
none | +0.263 |
lves | +0.258 |
favourites | +0.254 |
favorites | +0.252 |
Neg logit contributions | |
kiss | -0.285 |
ment | -0.272 |
less | -0.250 |
bless | -0.246 |
forgiveness | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
pole | +0.145 |
lves | +0.140 |
none | +0.140 |
chard | +0.139 |
One | +0.135 |
Neg logit contributions | |
kiss | -0.094 |
ment | -0.088 |
less | -0.078 |
bless | -0.078 |
forgiveness | -0.076 |
Token | They |
Token ID | 1119 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
kiss | +0.005 |
ment | +0.005 |
of | +0.004 |
less | +0.004 |
forgiveness | +0.004 |
Neg logit contributions | |
chard | -0.006 |
nam | -0.006 |
pole | -0.006 |
opes | -0.006 |
lves | -0.006 |
Token | made |
Token ID | 925 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
pole | +0.027 |
lves | +0.026 |
chard | +0.025 |
opes | +0.025 |
uries | +0.024 |
Neg logit contributions | |
kiss | -0.034 |
ment | -0.030 |
bless | -0.029 |
band | -0.028 |
prayer | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
kiss | +0.092 |
ment | +0.088 |
forgiveness | +0.079 |
band | +0.079 |
less | +0.079 |
Neg logit contributions | |
pole | -0.107 |
chard | -0.105 |
lves | -0.102 |
none | -0.099 |
nam | -0.097 |
Token | the |
Token ID | 262 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
pole | +0.101 |
lves | +0.097 |
none | +0.097 |
chard | +0.096 |
One | +0.093 |
Neg logit contributions | |
kiss | -0.081 |
ment | -0.078 |
less | -0.070 |
bless | -0.069 |
forgiveness | -0.068 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
pole | +0.011 |
lves | +0.011 |
none | +0.010 |
chard | +0.010 |
uries | +0.010 |
Neg logit contributions | |
kiss | -0.009 |
ment | -0.008 |
fairy | -0.008 |
band | -0.008 |
bless | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
pole | +0.086 |
lves | +0.086 |
none | +0.083 |
chard | +0.083 |
favourites | +0.081 |
Neg logit contributions | |
kiss | -0.066 |
ment | -0.062 |
less | -0.057 |
bless | -0.055 |
prayer | -0.054 |
Token | regular |
Token ID | 3218 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
pole | +0.093 |
lves | +0.090 |
chard | +0.087 |
none | +0.086 |
One | +0.084 |
Neg logit contributions | |
kiss | -0.074 |
ment | -0.069 |
bless | -0.063 |
less | -0.063 |
forgiveness | -0.062 |
Token | or |
Token ID | 393 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
pole | +0.049 |
none | +0.046 |
lves | +0.046 |
One | +0.046 |
chard | +0.045 |
Neg logit contributions | |
kiss | -0.049 |
ment | -0.048 |
less | -0.044 |
bless | -0.043 |
forgiveness | -0.043 |
Token | nam |
Token ID | 7402 |
Feature activation | +9.38e+00 |
Pos logit contributions | |
pole | +0.043 |
lves | +0.040 |
none | +0.038 |
chard | +0.038 |
One | +0.037 |
Neg logit contributions | |
kiss | -0.091 |
ment | -0.088 |
less | -0.083 |
bless | -0.082 |
forgiveness | -0.082 |
Token | ents |
Token ID | 658 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
lves | +0.280 |
none | +0.280 |
chard | +0.274 |
pole | +0.273 |
opes | +0.263 |
Neg logit contributions | |
ment | -0.551 |
kiss | -0.546 |
less | -0.530 |
ful | -0.517 |
of | -0.506 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
pole | +0.157 |
none | +0.147 |
chard | +0.142 |
lves | +0.141 |
pads | +0.138 |
Neg logit contributions | |
kiss | -0.164 |
ment | -0.155 |
forgiveness | -0.147 |
bless | -0.144 |
prayer | -0.143 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
pole | +0.065 |
lves | +0.060 |
none | +0.059 |
chard | +0.058 |
One | +0.055 |
Neg logit contributions | |
kiss | -0.149 |
ment | -0.144 |
less | -0.136 |
bless | -0.135 |
forgiveness | -0.134 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
kiss | +0.123 |
ment | +0.118 |
less | +0.107 |
bless | +0.106 |
forgiveness | +0.105 |
Neg logit contributions | |
pole | -0.134 |
lves | -0.130 |
none | -0.127 |
chard | -0.127 |
nam | -0.121 |
Token | upon |
Token ID | 2402 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
pole | +0.067 |
lves | +0.066 |
chard | +0.064 |
none | +0.064 |
uries | +0.063 |
Neg logit contributions | |
kiss | -0.044 |
ment | -0.042 |
less | -0.039 |
bless | -0.036 |
forgiveness | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
kiss | +0.021 |
ment | +0.020 |
forgiveness | +0.019 |
less | +0.018 |
prayer | +0.017 |
Neg logit contributions | |
pole | -0.028 |
lves | -0.027 |
chard | -0.026 |
none | -0.025 |
opes | -0.025 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
kiss | +0.144 |
ment | +0.138 |
less | +0.126 |
bless | +0.125 |
forgiveness | +0.124 |
Neg logit contributions | |
pole | -0.138 |
lves | -0.133 |
none | -0.131 |
chard | -0.131 |
One | -0.128 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
pole | +0.056 |
lves | +0.055 |
chard | +0.054 |
uries | +0.053 |
none | +0.053 |
Neg logit contributions | |
kiss | -0.037 |
ment | -0.035 |
less | -0.032 |
forgiveness | -0.030 |
bless | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
pole | +0.023 |
none | +0.022 |
chard | +0.022 |
lves | +0.022 |
One | +0.022 |
Neg logit contributions | |
kiss | -0.023 |
ment | -0.022 |
less | -0.020 |
bless | -0.020 |
prayer | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
pole | +0.111 |
lves | +0.108 |
chard | +0.107 |
none | +0.106 |
nam | +0.103 |
Neg logit contributions | |
kiss | -0.066 |
ment | -0.060 |
less | -0.055 |
bless | -0.053 |
prayer | -0.053 |
Token | there |
Token ID | 612 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
kiss | +0.070 |
ment | +0.066 |
less | +0.059 |
bless | +0.057 |
forgiveness | +0.057 |
Neg logit contributions | |
pole | -0.121 |
lves | -0.117 |
chard | -0.115 |
none | -0.115 |
One | -0.111 |
Token | was |
Token ID | 373 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
pole | +0.173 |
lves | +0.167 |
none | +0.165 |
chard | +0.164 |
One | +0.160 |
Neg logit contributions | |
kiss | -0.129 |
ment | -0.123 |
less | -0.110 |
bless | -0.109 |
forgiveness | -0.107 |
Token | a |
Token ID | 257 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
pole | +0.057 |
lves | +0.055 |
chard | +0.053 |
uries | +0.053 |
none | +0.052 |
Neg logit contributions | |
kiss | -0.035 |
ment | -0.032 |
band | -0.029 |
less | -0.029 |
forgiveness | -0.029 |
Token | little |
Token ID | 1310 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
lves | +0.018 |
chard | +0.018 |
pole | +0.018 |
One | +0.018 |
favourites | +0.017 |
Neg logit contributions | |
ment | -0.017 |
kiss | -0.015 |
less | -0.014 |
forgiveness | -0.014 |
iness | -0.014 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ment | +0.037 |
kiss | +0.031 |
less | +0.030 |
forgiveness | +0.030 |
fade | +0.029 |
Neg logit contributions | |
lves | -0.050 |
chard | -0.050 |
pole | -0.048 |
nam | -0.047 |
One | -0.047 |
Token | called |
Token ID | 1444 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
pole | +0.027 |
lves | +0.025 |
chard | +0.024 |
One | +0.024 |
none | +0.024 |
Neg logit contributions | |
kiss | -0.078 |
ment | -0.077 |
less | -0.072 |
prayer | -0.071 |
bless | -0.071 |
Token | 't |
Token ID | 470 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
pole | +0.014 |
lves | +0.013 |
chard | +0.013 |
none | +0.013 |
nam | +0.013 |
Neg logit contributions | |
kiss | -0.016 |
ment | -0.015 |
less | -0.015 |
bless | -0.014 |
forgiveness | -0.014 |
Token | expected |
Token ID | 2938 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
kiss | +0.043 |
ment | +0.043 |
less | +0.040 |
bless | +0.039 |
arl | +0.039 |
Neg logit contributions | |
pole | -0.031 |
none | -0.030 |
lves | -0.030 |
chard | -0.029 |
pads | -0.029 |
Token | Molly |
Token ID | 30236 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
none | +0.008 |
pole | +0.008 |
One | +0.008 |
chard | +0.008 |
lves | +0.008 |
Neg logit contributions | |
ment | -0.008 |
kiss | -0.008 |
less | -0.007 |
bless | -0.007 |
prayer | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
none | +0.078 |
pole | +0.077 |
chard | +0.074 |
pads | +0.074 |
One | +0.073 |
Neg logit contributions | |
kiss | -0.066 |
ment | -0.065 |
bless | -0.059 |
ray | -0.056 |
forgiveness | -0.056 |
Token | be |
Token ID | 307 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
ment | +0.026 |
less | +0.023 |
kiss | +0.020 |
prayer | +0.020 |
irk | +0.019 |
Neg logit contributions | |
One | -0.031 |
pole | -0.030 |
none | -0.029 |
uries | -0.028 |
bank | -0.028 |
Token | so |
Token ID | 523 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
kiss | +0.131 |
ment | +0.125 |
less | +0.115 |
bless | +0.113 |
forgiveness | +0.112 |
Neg logit contributions | |
pole | -0.136 |
lves | -0.131 |
chard | -0.128 |
none | -0.128 |
One | -0.125 |
Token | calm |
Token ID | 9480 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
pole | +0.173 |
chard | +0.172 |
lves | +0.172 |
none | +0.170 |
One | +0.163 |
Neg logit contributions | |
kiss | -0.220 |
ment | -0.208 |
bless | -0.197 |
forgiveness | -0.192 |
less | -0.191 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
kiss | +0.007 |
bless | +0.007 |
ment | +0.007 |
prayer | +0.006 |
forgiveness | +0.006 |
Neg logit contributions | |
pole | -0.008 |
none | -0.008 |
One | -0.008 |
chard | -0.007 |
lves | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
kiss | +0.017 |
ment | +0.017 |
prayer | +0.015 |
less | +0.015 |
forgiveness | +0.014 |
Neg logit contributions | |
pole | -0.021 |
lves | -0.021 |
riages | -0.020 |
nam | -0.020 |
opes | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
kiss | +0.031 |
ment | +0.030 |
less | +0.027 |
bless | +0.026 |
forgiveness | +0.026 |
Neg logit contributions | |
pole | -0.035 |
lves | -0.034 |
none | -0.034 |
chard | -0.034 |
nam | -0.032 |
Token | M |
Token ID | 44 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
kiss | +0.041 |
ment | +0.039 |
bless | +0.035 |
less | +0.035 |
prayer | +0.035 |
Neg logit contributions | |
pole | -0.056 |
lves | -0.054 |
none | -0.053 |
chard | -0.053 |
One | -0.053 |
Token | flying |
Token ID | 7348 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
pole | +0.076 |
none | +0.072 |
chard | +0.069 |
lves | +0.069 |
One | +0.067 |
Neg logit contributions | |
kiss | -0.068 |
ment | -0.066 |
arl | -0.063 |
less | -0.061 |
forgiveness | -0.060 |
Token | like |
Token ID | 588 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
pole | +0.037 |
none | +0.035 |
chard | +0.034 |
lves | +0.034 |
One | +0.033 |
Neg logit contributions | |
kiss | -0.034 |
ment | -0.032 |
bless | -0.031 |
forgiveness | -0.030 |
prayer | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kiss | +0.021 |
ment | +0.020 |
less | +0.018 |
bless | +0.018 |
prayer | +0.018 |
Neg logit contributions | |
pole | -0.022 |
none | -0.022 |
chard | -0.021 |
lves | -0.021 |
One | -0.020 |
Token | dark |
Token ID | 3223 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
pole | +0.005 |
lves | +0.005 |
chard | +0.005 |
none | +0.005 |
One | +0.005 |
Neg logit contributions | |
ment | -0.005 |
kiss | -0.005 |
forgiveness | -0.004 |
bless | -0.004 |
less | -0.004 |
Token | shadow |
Token ID | 9082 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
kiss | +0.082 |
ment | +0.082 |
forgiveness | +0.077 |
bless | +0.076 |
less | +0.074 |
Neg logit contributions | |
pole | -0.087 |
One | -0.084 |
lves | -0.080 |
chard | -0.078 |
none | -0.078 |
Token | in |
Token ID | 287 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
ment | +0.015 |
kiss | +0.015 |
forgiveness | +0.014 |
bless | +0.013 |
less | +0.013 |
Neg logit contributions | |
pole | -0.021 |
none | -0.019 |
One | -0.018 |
pads | -0.018 |
chard | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
pole | +0.108 |
none | +0.107 |
chard | +0.105 |
One | +0.105 |
lves | +0.103 |
Neg logit contributions | |
kiss | -0.084 |
ment | -0.081 |
less | -0.075 |
bless | -0.072 |
forgiveness | -0.071 |
Token | gloomy |
Token ID | 46400 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
pole | +0.033 |
lves | +0.032 |
chard | +0.031 |
One | +0.031 |
none | +0.031 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.033 |
less | -0.030 |
forgiveness | -0.030 |
bless | -0.029 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
kiss | +0.094 |
ment | +0.090 |
less | +0.085 |
bless | +0.084 |
forgiveness | +0.083 |
Neg logit contributions | |
pole | -0.074 |
lves | -0.070 |
chard | -0.069 |
none | -0.068 |
One | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
pole | +0.057 |
none | +0.054 |
chard | +0.053 |
lves | +0.053 |
One | +0.052 |
Neg logit contributions | |
kiss | -0.043 |
ment | -0.040 |
bless | -0.037 |
forgiveness | -0.037 |
less | -0.036 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ment | +0.028 |
kiss | +0.028 |
prayer | +0.024 |
bless | +0.023 |
of | +0.022 |
Neg logit contributions | |
pole | -0.030 |
lves | -0.029 |
opes | -0.029 |
edy | -0.029 |
chard | -0.029 |
Token | instead |
Token ID | 2427 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
kiss | +0.156 |
ment | +0.146 |
forgiveness | +0.130 |
bless | +0.130 |
arl | +0.128 |
Neg logit contributions | |
pole | -0.207 |
none | -0.192 |
chard | -0.190 |
lves | -0.187 |
bank | -0.176 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
kiss | +0.059 |
ment | +0.054 |
bless | +0.051 |
forgiveness | +0.049 |
band | +0.048 |
Neg logit contributions | |
pole | -0.095 |
none | -0.091 |
One | -0.088 |
chard | -0.085 |
pads | -0.084 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
kiss | +0.014 |
ment | +0.014 |
prayer | +0.012 |
forgiveness | +0.012 |
bless | +0.011 |
Neg logit contributions | |
pole | -0.020 |
chard | -0.020 |
nam | -0.020 |
lves | -0.020 |
opes | -0.019 |
Token | Once |
Token ID | 7454 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
kiss | +0.136 |
ment | +0.130 |
less | +0.119 |
bless | +0.117 |
forgiveness | +0.115 |
Neg logit contributions | |
pole | -0.144 |
lves | -0.139 |
none | -0.136 |
chard | -0.136 |
favourites | -0.130 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
pole | +0.055 |
lves | +0.055 |
uries | +0.053 |
chard | +0.053 |
opes | +0.053 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.031 |
less | -0.029 |
prayer | -0.027 |
forgiveness | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
pole | +0.021 |
lves | +0.020 |
none | +0.020 |
chard | +0.020 |
One | +0.019 |
Neg logit contributions | |
kiss | -0.019 |
ment | -0.018 |
less | -0.016 |
bless | -0.016 |
forgiveness | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
pole | +0.089 |
lves | +0.087 |
chard | +0.087 |
none | +0.086 |
nam | +0.084 |
Neg logit contributions | |
kiss | -0.050 |
ment | -0.044 |
less | -0.041 |
bless | -0.039 |
prayer | -0.039 |
Token | there |
Token ID | 612 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
kiss | +0.076 |
ment | +0.072 |
less | +0.065 |
forgiveness | +0.061 |
bless | +0.061 |
Neg logit contributions | |
pole | -0.146 |
lves | -0.143 |
chard | -0.140 |
none | -0.139 |
pads | -0.136 |
Token | was |
Token ID | 373 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
pole | +0.154 |
lves | +0.148 |
none | +0.148 |
chard | +0.146 |
One | +0.145 |
Neg logit contributions | |
kiss | -0.126 |
ment | -0.120 |
less | -0.108 |
bless | -0.108 |
forgiveness | -0.106 |
Token | a |
Token ID | 257 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
pole | +0.047 |
lves | +0.046 |
uries | +0.045 |
chard | +0.044 |
ramids | +0.044 |
Neg logit contributions | |
kiss | -0.024 |
ment | -0.021 |
band | -0.019 |
less | -0.019 |
ful | -0.019 |
Token | little |
Token ID | 1310 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
ment | +0.000 |
kiss | +0.000 |
less | +0.000 |
forgiveness | +0.000 |
iness | +0.000 |
Neg logit contributions | |
lves | -0.000 |
pole | -0.000 |
chard | -0.000 |
One | -0.000 |
nam | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
kiss | +0.014 |
ment | +0.014 |
prayer | +0.013 |
bless | +0.012 |
forgiveness | +0.012 |
Neg logit contributions | |
pole | -0.016 |
lves | -0.016 |
chard | -0.015 |
opes | -0.015 |
none | -0.015 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
kiss | +0.136 |
ment | +0.130 |
less | +0.119 |
bless | +0.118 |
forgiveness | +0.117 |
Neg logit contributions | |
pole | -0.134 |
lves | -0.129 |
none | -0.127 |
chard | -0.127 |
One | -0.123 |
Token | upon |
Token ID | 2402 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
pole | +0.059 |
lves | +0.058 |
chard | +0.056 |
none | +0.056 |
uries | +0.055 |
Neg logit contributions | |
kiss | -0.039 |
ment | -0.037 |
less | -0.034 |
bless | -0.032 |
forgiveness | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
pole | +0.022 |
none | +0.021 |
lves | +0.021 |
chard | +0.021 |
One | +0.020 |
Neg logit contributions | |
kiss | -0.021 |
ment | -0.020 |
less | -0.019 |
bless | -0.018 |
prayer | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
pole | +0.091 |
lves | +0.088 |
chard | +0.087 |
none | +0.087 |
nam | +0.084 |
Neg logit contributions | |
kiss | -0.057 |
ment | -0.052 |
less | -0.048 |
bless | -0.047 |
prayer | -0.046 |
Token | there |
Token ID | 612 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
kiss | +0.077 |
ment | +0.072 |
less | +0.065 |
bless | +0.062 |
forgiveness | +0.061 |
Neg logit contributions | |
pole | -0.145 |
lves | -0.142 |
chard | -0.139 |
none | -0.138 |
favourites | -0.134 |
Token | was |
Token ID | 373 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
pole | +0.141 |
none | +0.137 |
lves | +0.135 |
One | +0.135 |
chard | +0.132 |
Neg logit contributions | |
kiss | -0.128 |
ment | -0.123 |
bless | -0.111 |
less | -0.111 |
forgiveness | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
pole | +0.047 |
lves | +0.045 |
chard | +0.044 |
none | +0.044 |
uries | +0.044 |
Neg logit contributions | |
kiss | -0.029 |
ment | -0.027 |
band | -0.024 |
less | -0.024 |
forgiveness | -0.023 |
Token | loyal |
Token ID | 9112 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ment | +0.005 |
kiss | +0.004 |
less | +0.004 |
forgiveness | +0.004 |
bless | +0.004 |
Neg logit contributions | |
lves | -0.006 |
pole | -0.006 |
chard | -0.006 |
One | -0.005 |
favourites | -0.005 |
Token | friend |
Token ID | 1545 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
pole | +0.001 |
One | +0.001 |
lves | +0.001 |
chard | +0.001 |
favorites | +0.001 |
Neg logit contributions | |
ment | -0.001 |
kiss | -0.001 |
forgiveness | -0.001 |
less | -0.001 |
fade | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
pole | +0.022 |
lves | +0.022 |
chard | +0.021 |
none | +0.021 |
favourites | +0.020 |
Neg logit contributions | |
kiss | -0.044 |
ment | -0.042 |
bless | -0.040 |
less | -0.039 |
forgiveness | -0.039 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
kiss | +0.014 |
ment | +0.013 |
prayer | +0.012 |
voice | +0.012 |
of | +0.012 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.018 |
pads | -0.017 |
uries | -0.017 |
chard | -0.017 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
pole | +0.000 |
chard | +0.000 |
uries | +0.000 |
none | +0.000 |
lves | +0.000 |
Neg logit contributions | |
kiss | -0.000 |
band | -0.000 |
fairy | -0.000 |
bless | -0.000 |
sigh | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ment | +0.093 |
kiss | +0.090 |
bless | +0.086 |
pour | +0.083 |
less | +0.082 |
Neg logit contributions | |
none | -0.070 |
One | -0.067 |
pole | -0.063 |
Jerry | -0.061 |
Ellie | -0.059 |
Token | an |
Token ID | 281 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
kiss | +0.050 |
ment | +0.047 |
less | +0.043 |
bless | +0.043 |
forgiveness | +0.042 |
Neg logit contributions | |
pole | -0.056 |
lves | -0.053 |
none | -0.053 |
chard | -0.053 |
One | -0.051 |
Token | idea |
Token ID | 2126 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
chard | +0.022 |
lves | +0.022 |
pole | +0.022 |
none | +0.021 |
ramids | +0.021 |
Neg logit contributions | |
kiss | -0.013 |
ment | -0.012 |
forgiveness | -0.011 |
prayer | -0.011 |
pain | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
kiss | +0.007 |
ment | +0.007 |
bless | +0.006 |
prayer | +0.006 |
less | +0.006 |
Neg logit contributions | |
pole | -0.008 |
One | -0.008 |
none | -0.007 |
lves | -0.007 |
pads | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
kiss | +0.026 |
ment | +0.025 |
prayer | +0.022 |
less | +0.022 |
band | +0.022 |
Neg logit contributions | |
pole | -0.024 |
lves | -0.024 |
none | -0.023 |
chard | -0.023 |
uries | -0.023 |
Token | went |
Token ID | 1816 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
chard | +0.026 |
none | +0.026 |
nam | +0.026 |
pole | +0.026 |
lves | +0.026 |
Neg logit contributions | |
kiss | -0.023 |
band | -0.021 |
fairy | -0.019 |
prayer | -0.018 |
bless | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ment | +0.072 |
kiss | +0.071 |
bless | +0.064 |
forgiveness | +0.063 |
prayer | +0.063 |
Neg logit contributions | |
pole | -0.082 |
chard | -0.080 |
lves | -0.079 |
none | -0.078 |
One | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ment | +0.078 |
kiss | +0.072 |
less | +0.070 |
prayer | +0.065 |
ray | +0.064 |
Neg logit contributions | |
pole | -0.095 |
chard | -0.093 |
One | -0.093 |
lves | -0.092 |
none | -0.091 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
pole | +0.006 |
chard | +0.006 |
lves | +0.006 |
none | +0.006 |
One | +0.006 |
Neg logit contributions | |
ment | -0.007 |
kiss | -0.007 |
bless | -0.006 |
less | -0.006 |
forgiveness | -0.006 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
kiss | +0.002 |
ment | +0.002 |
less | +0.002 |
forgiveness | +0.002 |
band | +0.002 |
Neg logit contributions | |
pole | -0.002 |
lves | -0.001 |
favorites | -0.001 |
favourites | -0.001 |
uries | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
kiss | +0.072 |
ment | +0.068 |
less | +0.063 |
bless | +0.063 |
forgiveness | +0.062 |
Neg logit contributions | |
pole | -0.060 |
lves | -0.057 |
chard | -0.056 |
none | -0.055 |
favourites | -0.054 |
Token | know |
Token ID | 760 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
pole | +0.009 |
lves | +0.008 |
One | +0.008 |
none | +0.008 |
chard | +0.008 |
Neg logit contributions | |
kiss | -0.008 |
ment | -0.008 |
less | -0.008 |
forgiveness | -0.007 |
bless | -0.007 |
Token | what |
Token ID | 644 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
kiss | +0.043 |
ment | +0.040 |
less | +0.037 |
bless | +0.037 |
prayer | +0.036 |
Neg logit contributions | |
pole | -0.049 |
none | -0.049 |
chard | -0.048 |
lves | -0.048 |
nam | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
pole | +0.046 |
none | +0.046 |
chard | +0.045 |
lves | +0.045 |
One | +0.045 |
Neg logit contributions | |
kiss | -0.032 |
ment | -0.030 |
less | -0.027 |
bless | -0.027 |
prayer | -0.025 |
Token | do |
Token ID | 466 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
pole | +0.069 |
One | +0.067 |
none | +0.066 |
lves | +0.065 |
chard | +0.065 |
Neg logit contributions | |
ment | -0.035 |
kiss | -0.031 |
less | -0.029 |
forgiveness | -0.026 |
bless | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.012 |
bless | +0.012 |
prayer | +0.011 |
less | +0.011 |
Neg logit contributions | |
none | -0.015 |
pole | -0.015 |
One | -0.015 |
chard | -0.014 |
lves | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
pole | +0.032 |
lves | +0.029 |
opes | +0.029 |
riages | +0.029 |
uries | +0.029 |
Neg logit contributions | |
kiss | -0.020 |
ment | -0.018 |
next | -0.017 |
voice | -0.017 |
moment | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
kiss | +0.010 |
ment | +0.009 |
less | +0.008 |
forgiveness | +0.008 |
band | +0.008 |
Neg logit contributions | |
pole | -0.014 |
lves | -0.014 |
chard | -0.014 |
none | -0.014 |
nam | -0.013 |
Token | Just |
Token ID | 5703 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.028 |
less | +0.026 |
band | +0.025 |
bless | +0.025 |
Neg logit contributions | |
pole | -0.032 |
none | -0.031 |
lves | -0.031 |
chard | -0.031 |
favorites | -0.029 |
Token | then |
Token ID | 788 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
kiss | +0.072 |
ment | +0.069 |
less | +0.067 |
forgiveness | +0.066 |
bless | +0.065 |
Neg logit contributions | |
pole | -0.046 |
chard | -0.045 |
none | -0.045 |
One | -0.043 |
lves | -0.042 |
Token | wrapped |
Token ID | 12908 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
ment | +0.201 |
less | +0.198 |
arl | +0.197 |
kiss | +0.196 |
forgiveness | +0.191 |
Neg logit contributions | |
pole | -0.129 |
none | -0.119 |
chard | -0.114 |
One | -0.114 |
lves | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
none | +0.019 |
pole | +0.019 |
chard | +0.019 |
lves | +0.018 |
nam | +0.018 |
Neg logit contributions | |
kiss | -0.016 |
ment | -0.015 |
bless | -0.014 |
prayer | -0.014 |
less | -0.014 |
Token | blanket |
Token ID | 18447 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ment | +0.065 |
kiss | +0.058 |
bless | +0.054 |
less | +0.053 |
ful | +0.052 |
Neg logit contributions | |
none | -0.075 |
pole | -0.074 |
chard | -0.072 |
lves | -0.071 |
nam | -0.071 |
Token | around |
Token ID | 1088 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
kiss | +0.048 |
ment | +0.047 |
bless | +0.046 |
forgiveness | +0.044 |
prayer | +0.042 |
Neg logit contributions | |
pole | -0.047 |
none | -0.046 |
chard | -0.044 |
One | -0.042 |
nam | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
none | +0.009 |
One | +0.008 |
chard | +0.008 |
nam | +0.008 |
pole | +0.008 |
Neg logit contributions | |
kiss | -0.010 |
ment | -0.009 |
arl | -0.009 |
guard | -0.009 |
bless | -0.009 |
Token | baby |
Token ID | 5156 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ment | +0.026 |
kiss | +0.026 |
less | +0.023 |
bless | +0.023 |
forgiveness | +0.022 |
Neg logit contributions | |
pole | -0.030 |
lves | -0.029 |
chard | -0.029 |
none | -0.029 |
nam | -0.028 |
Token | so |
Token ID | 523 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
pole | +0.011 |
chard | +0.010 |
lves | +0.010 |
none | +0.010 |
pads | +0.010 |
Neg logit contributions | |
ment | -0.009 |
kiss | -0.009 |
forgiveness | -0.008 |
bless | -0.008 |
less | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
none | +0.135 |
lves | +0.120 |
pole | +0.119 |
One | +0.119 |
chard | +0.118 |
Neg logit contributions | |
kiss | -0.141 |
bless | -0.126 |
ment | -0.124 |
arl | -0.123 |
forgiveness | -0.122 |
Token | could |
Token ID | 714 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ment | +0.094 |
kiss | +0.094 |
less | +0.088 |
forgiveness | +0.088 |
bless | +0.086 |
Neg logit contributions | |
pole | -0.067 |
none | -0.066 |
lves | -0.061 |
pads | -0.060 |
chard | -0.060 |
Token | have |
Token ID | 423 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
none | +0.065 |
One | +0.064 |
pole | +0.064 |
chard | +0.060 |
bank | +0.057 |
Neg logit contributions | |
ment | -0.061 |
less | -0.053 |
irk | -0.052 |
accidents | -0.050 |
forgiveness | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
kiss | +0.034 |
ment | +0.032 |
less | +0.029 |
bless | +0.029 |
forgiveness | +0.029 |
Neg logit contributions | |
pole | -0.035 |
lves | -0.033 |
chard | -0.033 |
none | -0.033 |
One | -0.032 |
Token | thanked |
Token ID | 26280 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
pole | +0.012 |
lves | +0.012 |
chard | +0.011 |
none | +0.011 |
uries | +0.011 |
Neg logit contributions | |
kiss | -0.012 |
ment | -0.010 |
bless | -0.010 |
band | -0.010 |
prayer | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
less | +0.023 |
ment | +0.022 |
kiss | +0.022 |
ray | +0.021 |
guard | +0.020 |
Neg logit contributions | |
none | -0.023 |
One | -0.023 |
pole | -0.023 |
chard | -0.022 |
nam | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
pole | +0.032 |
chard | +0.032 |
favorites | +0.032 |
favourites | +0.031 |
nam | +0.031 |
Neg logit contributions | |
ment | -0.026 |
kiss | -0.025 |
less | -0.024 |
Time | -0.024 |
pour | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ment | +0.110 |
kiss | +0.106 |
pain | +0.101 |
ray | +0.100 |
forgiveness | +0.097 |
Neg logit contributions | |
pole | -0.145 |
One | -0.136 |
none | -0.133 |
pads | -0.131 |
chard | -0.129 |
Token | keeping |
Token ID | 5291 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ment | +0.084 |
kiss | +0.081 |
less | +0.078 |
prayer | +0.074 |
ray | +0.073 |
Neg logit contributions | |
none | -0.073 |
nam | -0.070 |
chard | -0.070 |
pole | -0.067 |
Jerry | -0.063 |
Token | her |
Token ID | 607 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
kiss | +0.012 |
ment | +0.011 |
less | +0.011 |
prayer | +0.010 |
guard | +0.010 |
Neg logit contributions | |
none | -0.014 |
pole | -0.014 |
chard | -0.013 |
lves | -0.013 |
One | -0.013 |
Token | promise |
Token ID | 6991 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
none | +0.008 |
nam | +0.007 |
chard | +0.007 |
favourites | +0.007 |
favorites | +0.007 |
Neg logit contributions | |
ment | -0.007 |
arl | -0.006 |
kiss | -0.006 |
less | -0.006 |
Time | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
kiss | +0.136 |
ment | +0.134 |
bless | +0.120 |
forgiveness | +0.116 |
ray | +0.114 |
Neg logit contributions | |
none | -0.176 |
pole | -0.174 |
chard | -0.165 |
One | -0.164 |
pads | -0.161 |
Token | They |
Token ID | 1119 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
kiss | +0.000 |
ment | +0.000 |
prayer | +0.000 |
ful | +0.000 |
forgiveness | +0.000 |
Neg logit contributions | |
lves | -0.000 |
pole | -0.000 |
chard | -0.000 |
none | -0.000 |
nam | -0.000 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
pole | +0.028 |
lves | +0.027 |
opes | +0.026 |
uries | +0.026 |
chard | +0.026 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.029 |
band | -0.028 |
bless | -0.028 |
ful | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
kiss | +0.014 |
ment | +0.013 |
less | +0.012 |
bless | +0.012 |
prayer | +0.012 |
Neg logit contributions | |
pole | -0.018 |
none | -0.018 |
chard | -0.018 |
lves | -0.018 |
One | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
none | +0.002 |
pole | +0.002 |
chard | +0.002 |
lves | +0.002 |
favourites | +0.002 |
Neg logit contributions | |
kiss | -0.002 |
ment | -0.002 |
bless | -0.002 |
prayer | -0.002 |
arl | -0.002 |
Token | way |
Token ID | 835 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ment | +0.031 |
iness | +0.025 |
ful | +0.025 |
kiss | +0.025 |
arl | +0.025 |
Neg logit contributions | |
pole | -0.025 |
chard | -0.025 |
none | -0.025 |
lves | -0.024 |
favourites | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
pole | +0.009 |
none | +0.009 |
One | +0.008 |
pads | +0.008 |
chard | +0.008 |
Neg logit contributions | |
ment | -0.008 |
kiss | -0.008 |
bless | -0.008 |
prayer | -0.007 |
forgiveness | -0.007 |
Token | act |
Token ID | 719 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
ment | +0.020 |
less | +0.018 |
arl | +0.017 |
irk | +0.017 |
prayer | +0.016 |
Neg logit contributions | |
none | -0.021 |
One | -0.021 |
pole | -0.020 |
bank | -0.019 |
chard | -0.019 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
pole | +0.034 |
none | +0.033 |
pads | +0.031 |
uries | +0.030 |
One | +0.030 |
Neg logit contributions | |
kiss | -0.032 |
ment | -0.031 |
bless | -0.030 |
prayer | -0.029 |
forgiveness | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
none | +0.035 |
pole | +0.035 |
pads | +0.034 |
One | +0.033 |
favourites | +0.032 |
Neg logit contributions | |
kiss | -0.038 |
arl | -0.037 |
bless | -0.036 |
ment | -0.035 |
less | -0.034 |
Token | silly |
Token ID | 14397 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
ment | +0.009 |
kiss | +0.009 |
less | +0.008 |
bless | +0.008 |
arl | +0.008 |
Neg logit contributions | |
none | -0.011 |
pole | -0.011 |
chard | -0.010 |
nam | -0.010 |
pads | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
none | +0.033 |
pole | +0.033 |
pads | +0.033 |
favourites | +0.032 |
One | +0.032 |
Neg logit contributions | |
kiss | -0.031 |
ment | -0.031 |
bless | -0.030 |
arl | -0.029 |
pour | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
kiss | +0.018 |
ment | +0.017 |
prayer | +0.015 |
bless | +0.015 |
forgiveness | +0.015 |
Neg logit contributions | |
pole | -0.021 |
lves | -0.020 |
chard | -0.020 |
none | -0.019 |
nam | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
kiss | +0.020 |
ment | +0.020 |
less | +0.018 |
bless | +0.017 |
prayer | +0.017 |
Neg logit contributions | |
pole | -0.022 |
One | -0.022 |
lves | -0.021 |
none | -0.021 |
chard | -0.020 |
Token | Ruby |
Token ID | 32101 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
ment | +0.040 |
kiss | +0.038 |
less | +0.036 |
prayer | +0.035 |
forgiveness | +0.035 |
Neg logit contributions | |
pole | -0.033 |
One | -0.031 |
none | -0.030 |
lves | -0.030 |
pads | -0.029 |
Token | Sn |
Token ID | 5489 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
kiss | +0.090 |
ment | +0.083 |
less | +0.079 |
bless | +0.079 |
forgiveness | +0.076 |
Neg logit contributions | |
pole | -0.088 |
lves | -0.083 |
none | -0.080 |
chard | -0.080 |
pads | -0.078 |
Token | ugg |
Token ID | 6837 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
pole | +0.091 |
lves | +0.089 |
none | +0.088 |
chard | +0.088 |
One | +0.086 |
Neg logit contributions | |
kiss | -0.039 |
ment | -0.036 |
less | -0.031 |
bless | -0.030 |
forgiveness | -0.030 |
Token | les |
Token ID | 829 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
kiss | +0.244 |
click | +0.231 |
forgiveness | +0.229 |
cheer | +0.223 |
handy | +0.223 |
Neg logit contributions | |
favorites | -0.172 |
opes | -0.166 |
favourites | -0.160 |
pads | -0.159 |
lves | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | -7.63e-01 |
Pos logit contributions | |
pole | +0.050 |
lves | +0.049 |
none | +0.048 |
chard | +0.048 |
One | +0.047 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.031 |
less | -0.028 |
bless | -0.027 |
forgiveness | -0.027 |
Token | One |
Token ID | 1881 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
kiss | +0.053 |
prayer | +0.045 |
bless | +0.045 |
shower | +0.045 |
ment | +0.044 |
Neg logit contributions | |
lves | -0.023 |
pole | -0.022 |
chard | -0.021 |
opes | -0.020 |
riages | -0.019 |
Token | day |
Token ID | 1110 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
ment | +0.001 |
kiss | +0.001 |
forgiveness | +0.001 |
arl | +0.001 |
bless | +0.001 |
Neg logit contributions | |
One | -0.001 |
pole | -0.001 |
While | -0.001 |
pads | -0.001 |
favourites | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
kiss | +0.152 |
ment | +0.144 |
less | +0.128 |
bless | +0.125 |
forgiveness | +0.123 |
Neg logit contributions | |
pole | -0.256 |
lves | -0.248 |
none | -0.245 |
chard | -0.244 |
One | -0.238 |
Token | they |
Token ID | 484 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
kiss | +0.052 |
ment | +0.052 |
less | +0.046 |
bless | +0.046 |
forgiveness | +0.046 |
Neg logit contributions | |
pole | -0.055 |
none | -0.055 |
chard | -0.055 |
lves | -0.054 |
One | -0.053 |
Token | went |
Token ID | 1816 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
pole | +0.023 |
lves | +0.022 |
opes | +0.022 |
uries | +0.021 |
none | +0.021 |
Neg logit contributions | |
kiss | -0.016 |
ment | -0.013 |
bless | -0.013 |
band | -0.013 |
less | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
kiss | +0.045 |
ment | +0.044 |
forgiveness | +0.038 |
less | +0.038 |
bless | +0.038 |
Neg logit contributions | |
pole | -0.070 |
lves | -0.068 |
none | -0.067 |
chard | -0.067 |
One | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
kiss | +0.057 |
ment | +0.045 |
bless | +0.045 |
band | +0.044 |
forgiveness | +0.042 |
Neg logit contributions | |
pole | -0.118 |
lves | -0.109 |
none | -0.109 |
opes | -0.107 |
pads | -0.107 |
Token | " |
Token ID | 366 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
kiss | +0.025 |
ment | +0.023 |
less | +0.022 |
bless | +0.021 |
forgiveness | +0.021 |
Neg logit contributions | |
pole | -0.025 |
lves | -0.024 |
chard | -0.023 |
none | -0.023 |
favourites | -0.022 |
Token | I |
Token ID | 40 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
pole | +0.124 |
lves | +0.120 |
none | +0.118 |
chard | +0.117 |
One | +0.115 |
Neg logit contributions | |
kiss | -0.106 |
ment | -0.104 |
less | -0.093 |
bless | -0.092 |
forgiveness | -0.091 |
Token | got |
Token ID | 1392 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ment | +0.061 |
kiss | +0.059 |
forgiveness | +0.053 |
prayer | +0.052 |
less | +0.052 |
Neg logit contributions | |
pole | -0.057 |
lves | -0.056 |
none | -0.054 |
One | -0.054 |
favourites | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
kiss | +0.056 |
ment | +0.053 |
less | +0.048 |
bless | +0.048 |
forgiveness | +0.047 |
Neg logit contributions | |
pole | -0.074 |
lves | -0.071 |
chard | -0.070 |
none | -0.070 |
One | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
kiss | +0.199 |
ment | +0.192 |
less | +0.173 |
bless | +0.172 |
forgiveness | +0.170 |
Neg logit contributions | |
pole | -0.219 |
lves | -0.211 |
none | -0.208 |
chard | -0.207 |
One | -0.200 |
Token | you |
Token ID | 345 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
ment | +0.046 |
kiss | +0.043 |
less | +0.041 |
bless | +0.039 |
forgiveness | +0.039 |
Neg logit contributions | |
pole | -0.035 |
none | -0.033 |
lves | -0.032 |
chard | -0.031 |
One | -0.030 |
Token | bad |
Token ID | 2089 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
kiss | +0.159 |
ment | +0.145 |
less | +0.137 |
bless | +0.135 |
forgiveness | +0.131 |
Neg logit contributions | |
pole | -0.188 |
chard | -0.183 |
lves | -0.183 |
none | -0.178 |
One | -0.173 |
Token | chicken |
Token ID | 9015 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
ment | +0.082 |
kiss | +0.082 |
less | +0.076 |
forgiveness | +0.075 |
guard | +0.073 |
Neg logit contributions | |
pole | -0.063 |
none | -0.060 |
pads | -0.059 |
opes | -0.059 |
One | -0.059 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
pole | +0.142 |
none | +0.132 |
lves | +0.131 |
pads | +0.124 |
chard | +0.124 |
Neg logit contributions | |
kiss | -0.197 |
ment | -0.197 |
forgiveness | -0.178 |
less | -0.177 |
prayer | -0.175 |
Token |
|
Token ID | 198 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
pole | +0.106 |
lves | +0.104 |
chard | +0.100 |
uries | +0.097 |
none | +0.097 |
Neg logit contributions | |
kiss | -0.082 |
ment | -0.077 |
forgiveness | -0.067 |
band | -0.067 |
less | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
pole | +0.002 |
lves | +0.002 |
chard | +0.002 |
none | +0.002 |
favourites | +0.002 |
Neg logit contributions | |
kiss | -0.002 |
ment | -0.002 |
less | -0.001 |
bless | -0.001 |
forgiveness | -0.001 |
Token | She |
Token ID | 3347 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
kiss | +0.013 |
ment | +0.013 |
less | +0.012 |
bless | +0.012 |
forgiveness | +0.012 |
Neg logit contributions | |
pole | -0.013 |
lves | -0.012 |
none | -0.012 |
chard | -0.012 |
favourites | -0.012 |
Token | scoop |
Token ID | 23529 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
kiss | +0.017 |
band | +0.015 |
ment | +0.015 |
fairy | +0.014 |
cleaner | +0.014 |
Neg logit contributions | |
lves | -0.019 |
pole | -0.019 |
chard | -0.018 |
uries | -0.018 |
nam | -0.018 |
Token | ed |
Token ID | 276 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
kiss | +0.023 |
prayer | +0.022 |
bless | +0.022 |
forgiveness | +0.022 |
ment | +0.021 |
Neg logit contributions | |
pole | -0.018 |
lves | -0.017 |
none | -0.017 |
pads | -0.016 |
One | -0.016 |
Token | up |
Token ID | 510 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
pole | +0.058 |
lves | +0.056 |
none | +0.055 |
chard | +0.055 |
One | +0.053 |
Neg logit contributions | |
kiss | -0.053 |
ment | -0.051 |
less | -0.046 |
bless | -0.046 |
forgiveness | -0.045 |
Token | some |
Token ID | 617 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
none | +0.107 |
pole | +0.106 |
lves | +0.106 |
chard | +0.105 |
One | +0.101 |
Neg logit contributions | |
kiss | -0.092 |
ment | -0.088 |
bless | -0.083 |
prayer | -0.081 |
less | -0.081 |
Token | of |
Token ID | 286 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
kiss | +0.072 |
bless | +0.072 |
prayer | +0.071 |
ment | +0.070 |
forgiveness | +0.066 |
Neg logit contributions | |
pole | -0.052 |
none | -0.051 |
lves | -0.051 |
bank | -0.051 |
favorites | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
kiss | +0.106 |
ment | +0.097 |
less | +0.085 |
forgiveness | +0.084 |
bless | +0.083 |
Neg logit contributions | |
pole | -0.200 |
lves | -0.191 |
chard | -0.188 |
none | -0.187 |
uries | -0.186 |
Token | dirt |
Token ID | 13647 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
kiss | +0.030 |
ment | +0.029 |
bless | +0.026 |
prayer | +0.026 |
forgiveness | +0.025 |
Neg logit contributions | |
pole | -0.031 |
lves | -0.030 |
none | -0.030 |
chard | -0.029 |
favourites | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
kiss | +0.144 |
bless | +0.139 |
forgiveness | +0.131 |
ment | +0.130 |
prayer | +0.124 |
Neg logit contributions | |
pole | -0.187 |
none | -0.181 |
chard | -0.169 |
pads | -0.168 |
bank | -0.168 |
Token | let |
Token ID | 1309 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
kiss | +0.033 |
ment | +0.032 |
less | +0.030 |
bless | +0.030 |
forgiveness | +0.029 |
Neg logit contributions | |
pole | -0.028 |
none | -0.027 |
lves | -0.026 |
chard | -0.026 |
pads | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
pole | +0.030 |
lves | +0.029 |
none | +0.028 |
chard | +0.028 |
One | +0.027 |
Neg logit contributions | |
kiss | -0.024 |
ment | -0.023 |
less | -0.021 |
bless | -0.021 |
forgiveness | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -9.33e-01 |
Pos logit contributions | |
kiss | +0.034 |
ment | +0.032 |
bless | +0.029 |
forgiveness | +0.028 |
prayer | +0.028 |
Neg logit contributions | |
pole | -0.052 |
none | -0.050 |
chard | -0.048 |
lves | -0.048 |
One | -0.048 |
Token | And |
Token ID | 843 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ment | +0.037 |
kiss | +0.037 |
forgiveness | +0.034 |
of | +0.034 |
less | +0.034 |
Neg logit contributions | |
pole | -0.048 |
lves | -0.048 |
chard | -0.047 |
nam | -0.046 |
uries | -0.043 |
Token | that |
Token ID | 326 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
kiss | +0.015 |
ment | +0.014 |
bless | +0.013 |
less | +0.013 |
arl | +0.012 |
Neg logit contributions | |
none | -0.011 |
pole | -0.011 |
chard | -0.011 |
lves | -0.010 |
One | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
kiss | +0.097 |
ment | +0.090 |
prayer | +0.084 |
forgiveness | +0.083 |
less | +0.083 |
Neg logit contributions | |
lves | -0.127 |
pole | -0.126 |
chard | -0.123 |
uries | -0.119 |
nam | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
pole | +0.014 |
lves | +0.013 |
chard | +0.013 |
none | +0.013 |
One | +0.013 |
Neg logit contributions | |
kiss | -0.013 |
ment | -0.012 |
less | -0.011 |
bless | -0.011 |
forgiveness | -0.011 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ment | +0.004 |
kiss | +0.004 |
bless | +0.003 |
less | +0.003 |
ful | +0.003 |
Neg logit contributions | |
none | -0.004 |
pole | -0.004 |
chard | -0.004 |
One | -0.004 |
lves | -0.004 |
Token | ending |
Token ID | 7464 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
kiss | +0.139 |
ment | +0.136 |
bless | +0.135 |
ful | +0.123 |
arl | +0.120 |
Neg logit contributions | |
none | -0.155 |
One | -0.152 |
bank | -0.149 |
banks | -0.144 |
pole | -0.138 |
Token | for |
Token ID | 329 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
kiss | +0.239 |
ment | +0.222 |
bless | +0.209 |
prayer | +0.200 |
forgiveness | +0.198 |
Neg logit contributions | |
pole | -0.289 |
none | -0.276 |
One | -0.263 |
pads | -0.262 |
lves | -0.256 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
kiss | +0.146 |
ment | +0.141 |
less | +0.131 |
bless | +0.130 |
prayer | +0.129 |
Neg logit contributions | |
pole | -0.079 |
none | -0.077 |
chard | -0.074 |
lves | -0.074 |
One | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
pole | +0.044 |
lves | +0.043 |
none | +0.042 |
chard | +0.042 |
One | +0.041 |
Neg logit contributions | |
kiss | -0.028 |
ment | -0.027 |
less | -0.024 |
bless | -0.024 |
forgiveness | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
kiss | +0.037 |
ment | +0.035 |
forgiveness | +0.032 |
of | +0.030 |
less | +0.030 |
Neg logit contributions | |
pole | -0.064 |
chard | -0.064 |
lves | -0.062 |
nam | -0.061 |
none | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
pole | +0.112 |
none | +0.112 |
One | +0.109 |
opes | +0.105 |
pads | +0.105 |
Neg logit contributions | |
kiss | -0.103 |
ment | -0.096 |
bless | -0.093 |
band | -0.088 |
forgiveness | -0.088 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
pole | +0.039 |
none | +0.039 |
lves | +0.037 |
chard | +0.036 |
pads | +0.036 |
Neg logit contributions | |
kiss | -0.036 |
ment | -0.036 |
bless | -0.033 |
less | -0.032 |
forgiveness | -0.032 |
Token | had |
Token ID | 550 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
none | +0.006 |
pole | +0.006 |
chard | +0.005 |
lves | +0.005 |
nam | +0.005 |
Neg logit contributions | |
kiss | -0.006 |
ment | -0.006 |
less | -0.005 |
bless | -0.005 |
forgiveness | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
pole | +0.035 |
lves | +0.034 |
chard | +0.033 |
opes | +0.031 |
favourites | +0.031 |
Neg logit contributions | |
kiss | -0.033 |
ment | -0.030 |
less | -0.029 |
forgiveness | -0.028 |
band | -0.028 |
Token | wonderful |
Token ID | 7932 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
pole | +0.009 |
none | +0.009 |
lves | +0.009 |
One | +0.009 |
chard | +0.009 |
Neg logit contributions | |
ment | -0.010 |
kiss | -0.009 |
less | -0.009 |
ful | -0.008 |
bless | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
ment | +0.031 |
ful | +0.030 |
kiss | +0.029 |
less | +0.028 |
bless | +0.028 |
Neg logit contributions | |
One | -0.035 |
favourites | -0.034 |
pole | -0.034 |
favorites | -0.033 |
none | -0.032 |
Token | exploring |
Token ID | 13504 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
kiss | +0.185 |
ment | +0.174 |
forgiveness | +0.162 |
prayer | +0.160 |
bless | +0.159 |
Neg logit contributions | |
pole | -0.195 |
none | -0.193 |
favourites | -0.184 |
pads | -0.184 |
One | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
pole | +0.019 |
none | +0.018 |
chard | +0.018 |
lves | +0.018 |
One | +0.018 |
Neg logit contributions | |
kiss | -0.015 |
ment | -0.014 |
less | -0.013 |
bless | -0.013 |
prayer | -0.012 |
Token | new |
Token ID | 649 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ment | +0.011 |
kiss | +0.010 |
less | +0.009 |
forgiveness | +0.009 |
ful | +0.009 |
Neg logit contributions | |
pole | -0.008 |
lves | -0.008 |
chard | -0.008 |
One | -0.008 |
favourites | -0.008 |
Token | city |
Token ID | 1748 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
kiss | +0.005 |
ment | +0.005 |
bless | +0.004 |
less | +0.004 |
forgiveness | +0.004 |
Neg logit contributions | |
pole | -0.005 |
lves | -0.005 |
none | -0.005 |
One | -0.005 |
chard | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
pole | +0.012 |
lves | +0.012 |
none | +0.012 |
chard | +0.012 |
One | +0.011 |
Neg logit contributions | |
kiss | -0.008 |
ment | -0.007 |
less | -0.007 |
bless | -0.006 |
forgiveness | -0.006 |