TOP ACTIVATIONS
MAX = 0.086

fair to take something that isn 't yours ."
she said . " Something isn 't right ." Her friends
Mom my , my flower isn 't growing anymore ," Tim
before you touch something that isn 't yours ! You can
pl uck cel ery that isn 't grown . He showed
at the dog statue , isn 't it cool ?" The
, Bob ! That pen isn 't for playing - don
that Fl uffy , it isn 't nice . â
, " T asting things isn 't always a good idea
We have different likes and disl ikes . We can be
around before taking something that isn 't yours ."
" This pe b ble isn 't as pretty as the
" The sign says ' CA UTION '."
never to take anything that isn 't hers . The end
like her big brother Tom , who had many trophies on
will never take anything that isn â t hers
is the fairy garden . Isn 't it wonderful ?"
made Ruby a princess . Isn 't she much better now
drew a pink flower . Isn 't it beautiful ?" she
a very nice k ite isn â t it

MIN ACTIVATIONS
MIN = -0.105

merry way . <|endoftext|> C ind y and her mom my
to her . <|endoftext|> C ind y was a cheerful three
The end . <|endoftext|> C ind y and Tim were good
playing together . <|endoftext|> C ind y wanted to move .
even better . <|endoftext|> C ind y was a little girl
the top . From the very top of the pine tree
day on , Lucy took very good care of her toy
relieved . She learned a very important lesson that day .
. After a very fun day , Sandy and
a bite ! <|endoftext|> C ind y and Peter were playing
y again . She worked very hard and soon the couch
Sue and Carl learned a very important lesson : it 's
idea . He took a really big stick and started to
pan . She learned a very important lesson that day :
the parade . He worked very hard on it , making
glad we got <|endoftext|> C ind y was a cheerful girl
sad . He learned a very important lesson that day -
The baby learned a very important lesson that day -
building blocks . She worked very hard and soon her palace
was a human who took very good care of their things

INTERVAL 0.038 - 0.086
CONTAINS 3.148%

He asked her if he could use the knife too .
with all her might and , after some effort , the
sw am in the ocean , collected shells , and even
And Betty learned that it doesn 't matter what you look
to speed away before it could reach her .

INTERVAL -0.010 - 0.038
CONTAINS 64.673%

" Don 't worry , we will get you another balloon
to record what it saw . It recorded the wind ,
agreed . They played together and had fun . From that
. The pot was the star of the show and the
to use other colors . You need to improve your drawings

INTERVAL -0.057 - -0.010
CONTAINS 31.598%

and had so much fun ! But then , a big
chat , play and have lots of fun . The pirate
and got the ball back . Tim my was happy he
and thanked the angel . She had a great time visiting
three - year - old . He had an unusual sc

INTERVAL -0.105 - -0.057
CONTAINS 0.581%

their voices and made a lot of noise .
They laughed and had so much fun together . Suddenly ,
the swings and had a lot of fun .
the road . One time , the ball went
't food ! One day , M illy was
Token fair
Token ID3148
Feature activation+1.28e-02

Pos logit contributions
ced+0.000
 str+0.000
pen+0.000
 pro+0.000
 marker+0.000
Neg logit contributions
 wolves-0.000
igators-0.000
unn-0.000
 bamboo-0.000
loo-0.000
Token to
Token ID284
Feature activation+2.68e-02

Pos logit contributions
ced+0.022
pen+0.021
 marker+0.020
 pro+0.020
 str+0.018
Neg logit contributions
 wolves-0.023
igators-0.022
 bamboo-0.021
 Dod-0.019
py-0.019
Token take
Token ID1011
Feature activation-6.99e-03

Pos logit contributions
pen+0.042
ced+0.042
 marker+0.038
mine+0.037
 str+0.037
Neg logit contributions
 wolves-0.053
igators-0.052
eer-0.047
 bamboo-0.046
unn-0.046
Token something
Token ID1223
Feature activation-1.17e-02

Pos logit contributions
igators+0.013
 wolves+0.012
eer+0.011
 bamboo+0.011
py+0.011
Neg logit contributions
ced-0.013
pen-0.012
 marker-0.010
 str-0.010
 pro-0.010
Token that
Token ID326
Feature activation+2.99e-02

Pos logit contributions
 wolves+0.020
igators+0.020
eer+0.018
py+0.018
 bamboo+0.017
Neg logit contributions
ced-0.022
pen-0.021
 pro-0.020
 marker-0.019
 widened-0.018
Token isn
Token ID2125
Feature activation+8.59e-02

Pos logit contributions
ced+0.046
pen+0.043
 marker+0.042
 str+0.039
 pro+0.039
Neg logit contributions
 wolves-0.059
 bamboo-0.054
igators-0.054
eer-0.052
py-0.051
Token't
Token ID470
Feature activation+3.03e-02

Pos logit contributions
ced+0.115
pen+0.106
 marker+0.097
 widening+0.091
 pro+0.090
Neg logit contributions
igators-0.199
 wolves-0.195
eer-0.176
 bamboo-0.174
py-0.174
Token yours
Token ID12431
Feature activation+1.23e-02

Pos logit contributions
ced+0.059
pen+0.056
 marker+0.053
 pro+0.052
 str+0.051
Neg logit contributions
 wolves-0.045
igators-0.044
 bamboo-0.040
unn-0.040
 habitats-0.038
Token."
Token ID526
Feature activation+2.66e-02

Pos logit contributions
pen+0.023
ced+0.023
 pro+0.021
can+0.021
 marker+0.021
Neg logit contributions
igators-0.021
 wolves-0.021
 bamboo-0.018
eer-0.017
py-0.017
Token
Token ID198
Feature activation+6.50e-04

Pos logit contributions
ced+0.048
pen+0.046
 marker+0.042
+0.041
 pro+0.041
Neg logit contributions
 wolves-0.048
igators-0.047
eer-0.043
 bamboo-0.042
py-0.039
Token
Token ID198
Feature activation+2.24e-03

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
+0.001
 pro+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 bamboo-0.001
py-0.001
Token she
Token ID673
Feature activation-1.08e-02

Pos logit contributions
ced+0.063
pen+0.061
 marker+0.056
+0.054
 pro+0.054
Neg logit contributions
 wolves-0.086
igators-0.085
eer-0.079
 bamboo-0.077
py-0.073
Token said
Token ID531
Feature activation-1.59e-03

Pos logit contributions
 wolves+0.016
igators+0.016
eer+0.014
 bamboo+0.014
py+0.013
Neg logit contributions
ced-0.022
pen-0.022
-0.021
 marker-0.020
 pro-0.019
Token.
Token ID13
Feature activation-2.01e-03

Pos logit contributions
 wolves+0.002
igators+0.002
 about+0.001
eer+0.001
 for+0.001
Neg logit contributions
ced-0.004
pen-0.004
-0.004
 marker-0.003
 pro-0.003
Token "
Token ID366
Feature activation+6.06e-02

Pos logit contributions
 wolves+0.003
igators+0.003
eer+0.003
 bamboo+0.003
py+0.003
Neg logit contributions
ced-0.004
pen-0.004
-0.004
 marker-0.004
 pro-0.003
TokenSomething
Token ID22210
Feature activation-2.56e-03

Pos logit contributions
pen+0.103
ced+0.103
 marker+0.091
+0.087
 widened+0.087
Neg logit contributions
igators-0.105
 wolves-0.099
eer-0.092
 bamboo-0.089
 hay-0.088
Token isn
Token ID2125
Feature activation+8.44e-02

Pos logit contributions
 wolves+0.005
igators+0.005
eer+0.005
py+0.004
 bamboo+0.004
Neg logit contributions
ced-0.004
 pro-0.004
pen-0.004
 marker-0.004
-0.004
Token't
Token ID470
Feature activation+2.37e-02

Pos logit contributions
ced+0.135
pen+0.129
 marker+0.120
 widening+0.114
 markers+0.113
Neg logit contributions
igators-0.173
 wolves-0.164
 about-0.147
py-0.145
 bamboo-0.142
Token right
Token ID826
Feature activation+6.46e-03

Pos logit contributions
ced+0.047
pen+0.046
+0.042
 marker+0.042
 pro+0.041
Neg logit contributions
 wolves-0.038
igators-0.038
eer-0.034
 bamboo-0.033
py-0.030
Token."
Token ID526
Feature activation+2.24e-02

Pos logit contributions
ced+0.014
pen+0.013
 marker+0.012
+0.012
 pro+0.012
Neg logit contributions
 wolves-0.010
igators-0.010
eer-0.008
 bamboo-0.008
py-0.008
Token Her
Token ID2332
Feature activation-3.45e-02

Pos logit contributions
ced+0.040
pen+0.040
+0.038
 marker+0.037
 pro+0.036
Neg logit contributions
 wolves-0.040
igators-0.040
eer-0.036
 bamboo-0.035
py-0.033
Token friends
Token ID2460
Feature activation+6.09e-03

Pos logit contributions
igators+0.055
 wolves+0.054
eer+0.048
 bamboo+0.047
py+0.043
Neg logit contributions
ced-0.071
pen-0.068
 marker-0.064
-0.063
 pro-0.062
TokenMom
Token ID29252
Feature activation+3.34e-03

Pos logit contributions
ced+0.060
pen+0.059
+0.053
 pro+0.052
 marker+0.051
Neg logit contributions
 wolves-0.058
igators-0.056
 bamboo-0.051
eer-0.050
 hay-0.047
Tokenmy
Token ID1820
Feature activation+9.61e-03

Pos logit contributions
ced+0.007
pen+0.007
+0.007
 marker+0.006
 pro+0.006
Neg logit contributions
 wolves-0.005
igators-0.004
eer-0.004
 bamboo-0.004
py-0.004
Token,
Token ID11
Feature activation+3.74e-02

Pos logit contributions
ced+0.020
pen+0.020
+0.018
 marker+0.018
 widening+0.018
Neg logit contributions
 wolves-0.014
igators-0.013
eer-0.012
 bamboo-0.011
 dogs-0.011
Token my
Token ID616
Feature activation-5.53e-03

Pos logit contributions
ced+0.061
 marker+0.059
pen+0.059
 pro+0.054
 str+0.052
Neg logit contributions
igators-0.070
 wolves-0.070
eer-0.064
 bamboo-0.062
py-0.060
Token flower
Token ID15061
Feature activation-1.01e-02

Pos logit contributions
 wolves+0.009
igators+0.009
eer+0.008
 bamboo+0.008
py+0.008
Neg logit contributions
ced-0.011
pen-0.010
 marker-0.009
-0.009
 pro-0.009
Token isn
Token ID2125
Feature activation+8.38e-02

Pos logit contributions
 wolves+0.017
igators+0.017
eer+0.016
 bamboo+0.015
py+0.014
Neg logit contributions
ced-0.018
pen-0.018
 marker-0.017
-0.017
 pro-0.016
Token't
Token ID470
Feature activation+2.50e-02

Pos logit contributions
ced+0.156
pen+0.146
 marker+0.136
 markers+0.132
 widening+0.129
Neg logit contributions
igators-0.149
 wolves-0.140
py-0.128
 about-0.125
 bamboo-0.124
Token growing
Token ID3957
Feature activation+1.91e-02

Pos logit contributions
ced+0.052
pen+0.050
 marker+0.046
+0.046
 pro+0.045
Neg logit contributions
 wolves-0.039
igators-0.038
eer-0.034
 bamboo-0.033
py-0.030
Token anymore
Token ID7471
Feature activation-2.64e-03

Pos logit contributions
ced+0.037
pen+0.036
 marker+0.033
 pro+0.032
+0.032
Neg logit contributions
 wolves-0.031
igators-0.030
eer-0.028
 bamboo-0.026
py-0.025
Token,"
Token ID553
Feature activation+4.68e-02

Pos logit contributions
 wolves+0.005
igators+0.005
eer+0.005
py+0.004
 bamboo+0.004
Neg logit contributions
ced-0.004
pen-0.004
 marker-0.004
 pro-0.004
-0.003
Token Tim
Token ID5045
Feature activation+4.07e-02

Pos logit contributions
ced+0.102
pen+0.098
 marker+0.093
+0.091
 pro+0.089
Neg logit contributions
 wolves-0.068
igators-0.066
eer-0.059
 bamboo-0.055
py-0.052
Token before
Token ID878
Feature activation+1.21e-02

Pos logit contributions
igators+0.056
 wolves+0.050
eer+0.049
 bamboo+0.049
unn+0.047
Neg logit contributions
ced-0.052
pen-0.047
 marker-0.042
 str-0.042
 pro-0.041
Token you
Token ID345
Feature activation-6.97e-03

Pos logit contributions
ced+0.022
pen+0.020
+0.019
 marker+0.019
 str+0.018
Neg logit contributions
igators-0.022
eer-0.021
 wolves-0.021
 bamboo-0.020
py-0.019
Token touch
Token ID3638
Feature activation+4.65e-04

Pos logit contributions
 wolves+0.014
igators+0.014
 bamboo+0.013
eer+0.013
py+0.012
Neg logit contributions
ced-0.011
pen-0.011
-0.010
 marker-0.010
 pro-0.009
Token something
Token ID1223
Feature activation-1.15e-03

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
 pro+0.001
 markers+0.001
Neg logit contributions
igators-0.001
 wolves-0.001
eer-0.001
unn-0.001
 bamboo-0.001
Token that
Token ID326
Feature activation+3.02e-02

Pos logit contributions
 wolves+0.002
igators+0.002
eer+0.002
py+0.002
 bamboo+0.002
Neg logit contributions
ced-0.002
pen-0.002
 pro-0.002
 marker-0.002
 widened-0.002
Token isn
Token ID2125
Feature activation+8.38e-02

Pos logit contributions
ced+0.047
pen+0.044
 marker+0.043
 str+0.040
 pro+0.039
Neg logit contributions
 wolves-0.058
igators-0.055
 bamboo-0.055
eer-0.052
py-0.051
Token't
Token ID470
Feature activation+2.88e-02

Pos logit contributions
ced+0.102
pen+0.097
 marker+0.086
 pro+0.080
 widening+0.079
Neg logit contributions
igators-0.202
 wolves-0.200
eer-0.181
 bamboo-0.178
py-0.178
Token yours
Token ID12431
Feature activation+1.15e-02

Pos logit contributions
ced+0.056
pen+0.052
 marker+0.049
 pro+0.048
 str+0.048
Neg logit contributions
 wolves-0.042
igators-0.041
 bamboo-0.040
unn-0.040
 habitats-0.039
Token!
Token ID0
Feature activation-7.30e-03

Pos logit contributions
ced+0.020
pen+0.020
 pro+0.018
can+0.018
 marker+0.018
Neg logit contributions
igators-0.021
 wolves-0.021
 bamboo-0.018
eer-0.018
 habitats-0.017
Token You
Token ID921
Feature activation+5.47e-03

Pos logit contributions
 wolves+0.013
igators+0.013
 bamboo+0.012
eer+0.012
py+0.011
Neg logit contributions
-0.013
pen-0.013
ced-0.012
 pro-0.011
 marker-0.011
Token can
Token ID460
Feature activation+5.69e-02

Pos logit contributions
ced+0.010
pen+0.009
 marker+0.008
+0.008
 pro+0.008
Neg logit contributions
 wolves-0.010
igators-0.010
eer-0.009
 bamboo-0.009
py-0.008
Token pl
Token ID458
Feature activation+3.33e-02

Pos logit contributions
ced+0.032
pen+0.031
 marker+0.029
+0.028
 pro+0.027
Neg logit contributions
 wolves-0.038
igators-0.037
eer-0.034
 bamboo-0.033
py-0.031
Tokenuck
Token ID1347
Feature activation-1.93e-02

Pos logit contributions
ced+0.057
pen+0.054
 marker+0.050
+0.049
 pro+0.049
Neg logit contributions
 wolves-0.062
igators-0.062
eer-0.056
 bamboo-0.055
py-0.052
Token cel
Token ID18725
Feature activation+9.78e-03

Pos logit contributions
igators+0.035
 wolves+0.034
eer+0.032
 bamboo+0.032
unn+0.031
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.030
 pro-0.028
mine-0.027
Tokenery
Token ID1924
Feature activation+4.66e-04

Pos logit contributions
ced+0.019
pen+0.018
 marker+0.017
+0.017
 pro+0.016
Neg logit contributions
 wolves-0.016
igators-0.016
eer-0.014
 bamboo-0.014
py-0.013
Token that
Token ID326
Feature activation+1.98e-02

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
+0.001
 pro+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 bamboo-0.001
py-0.001
Token isn
Token ID2125
Feature activation+8.38e-02

Pos logit contributions
ced+0.033
pen+0.031
 marker+0.029
 pro+0.028
+0.028
Neg logit contributions
 wolves-0.038
igators-0.037
eer-0.034
 bamboo-0.034
unn-0.032
Token't
Token ID470
Feature activation+2.31e-02

Pos logit contributions
ced+0.123
pen+0.116
 marker+0.106
 widening+0.103
 widened+0.101
Neg logit contributions
igators-0.181
 wolves-0.173
py-0.158
 about-0.152
 bamboo-0.151
Token grown
Token ID7334
Feature activation+1.73e-02

Pos logit contributions
ced+0.042
pen+0.040
 marker+0.037
 pro+0.037
+0.035
Neg logit contributions
 wolves-0.041
igators-0.040
eer-0.037
 bamboo-0.036
unn-0.034
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
ced+0.037
pen+0.035
+0.035
 marker+0.034
 widening+0.033
Neg logit contributions
 wolves-0.025
igators-0.024
eer-0.022
 bamboo-0.021
py-0.019
Token He
Token ID679
Feature activation-1.90e-02

Pos logit contributions
 wolves+0.015
igators+0.014
eer+0.013
 bamboo+0.013
py+0.012
Neg logit contributions
pen-0.022
ced-0.021
-0.021
 marker-0.020
 pro-0.020
Token showed
Token ID3751
Feature activation-2.69e-02

Pos logit contributions
 wolves+0.041
igators+0.041
eer+0.038
 bamboo+0.037
py+0.035
Neg logit contributions
ced-0.028
pen-0.027
 pro-0.024
 marker-0.023
 str-0.023
Token at
Token ID379
Feature activation-3.09e-03

Pos logit contributions
ced+0.040
pen+0.039
+0.037
 marker+0.036
 widening+0.036
Neg logit contributions
 wolves-0.025
igators-0.024
 bamboo-0.021
eer-0.020
 about-0.019
Token the
Token ID262
Feature activation+1.99e-02

Pos logit contributions
igators+0.005
 wolves+0.005
eer+0.005
unn+0.004
 bamboo+0.004
Neg logit contributions
ced-0.006
pen-0.005
-0.005
 pro-0.005
 marker-0.005
Token dog
Token ID3290
Feature activation+7.93e-03

Pos logit contributions
ced+0.044
pen+0.043
+0.041
 widened+0.039
 widening+0.038
Neg logit contributions
 wolves-0.028
igators-0.026
 bamboo-0.025
eer-0.025
 gorilla-0.025
Token statue
Token ID15207
Feature activation-3.33e-03

Pos logit contributions
ced+0.013
pen+0.013
 pro+0.011
 marker+0.011
+0.011
Neg logit contributions
 wolves-0.016
igators-0.016
eer-0.014
 bamboo-0.013
unn-0.013
Token,
Token ID11
Feature activation+3.85e-02

Pos logit contributions
 wolves+0.007
igators+0.006
eer+0.006
 bamboo+0.006
unn+0.006
Neg logit contributions
ced-0.005
pen-0.005
 pro-0.005
 marker-0.005
-0.004
Token isn
Token ID2125
Feature activation+8.29e-02

Pos logit contributions
ced+0.072
pen+0.070
 marker+0.066
 pro+0.064
+0.063
Neg logit contributions
igators-0.064
 wolves-0.064
eer-0.058
 bamboo-0.055
py-0.053
Token't
Token ID470
Feature activation+9.29e-03

Pos logit contributions
ced+0.139
pen+0.133
 marker+0.121
 widening+0.118
pron+0.114
Neg logit contributions
igators-0.161
 wolves-0.153
 Rex-0.141
 about-0.138
 Kitty-0.137
Token it
Token ID340
Feature activation+2.90e-02

Pos logit contributions
ced+0.017
pen+0.016
+0.016
 marker+0.015
 widening+0.014
Neg logit contributions
 wolves-0.017
igators-0.017
eer-0.016
 bamboo-0.015
 about-0.014
Token cool
Token ID3608
Feature activation+2.98e-02

Pos logit contributions
ced+0.065
pen+0.063
 marker+0.059
+0.058
 pro+0.058
Neg logit contributions
 wolves-0.040
igators-0.039
eer-0.034
 bamboo-0.033
py-0.030
Token?"
Token ID1701
Feature activation+3.03e-02

Pos logit contributions
ced+0.062
pen+0.061
 marker+0.057
 pro+0.056
mine+0.055
Neg logit contributions
 wolves-0.045
igators-0.044
eer-0.038
 bamboo-0.038
py-0.034
Token The
Token ID383
Feature activation-5.08e-04

Pos logit contributions
ced+0.070
pen+0.068
 marker+0.063
+0.063
 pro+0.062
Neg logit contributions
 wolves-0.039
igators-0.039
eer-0.034
 bamboo-0.033
py-0.029
Token,
Token ID11
Feature activation+3.88e-02

Pos logit contributions
igators+0.022
eer+0.020
 wolves+0.019
 habitats+0.019
py+0.018
Neg logit contributions
ced-0.014
pen-0.013
 marker-0.012
 pro-0.012
 str-0.011
Token Bob
Token ID5811
Feature activation+1.58e-02

Pos logit contributions
ced+0.074
 yes+0.070
 marker+0.069
pen+0.068
 pro+0.066
Neg logit contributions
igators-0.054
 wolves-0.049
 habitats-0.049
eer-0.048
unn-0.047
Token!
Token ID0
Feature activation+4.27e-03

Pos logit contributions
ced+0.023
pen+0.023
 marker+0.019
+0.019
 pro+0.018
Neg logit contributions
igators-0.034
 wolves-0.033
 bamboo-0.031
eer-0.030
 habitats-0.029
Token That
Token ID1320
Feature activation+6.72e-04

Pos logit contributions
pen+0.007
+0.007
ced+0.006
can+0.006
 marker+0.006
Neg logit contributions
igators-0.008
 wolves-0.008
 bamboo-0.007
eer-0.007
 hay-0.007
Token pen
Token ID3112
Feature activation+1.21e-02

Pos logit contributions
ced+0.001
+0.001
pen+0.001
 widening+0.001
 widened+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 dogs-0.001
 bamboo-0.001
Token isn
Token ID2125
Feature activation+8.27e-02

Pos logit contributions
ced+0.024
pen+0.024
 marker+0.022
+0.021
 pro+0.021
Neg logit contributions
 wolves-0.019
igators-0.019
eer-0.017
 bamboo-0.016
 gor-0.015
Token't
Token ID470
Feature activation+2.48e-02

Pos logit contributions
ced+0.113
pen+0.107
 marker+0.096
 pro+0.091
 widening+0.090
Neg logit contributions
igators-0.190
 wolves-0.188
 bamboo-0.168
eer-0.166
py-0.165
Token for
Token ID329
Feature activation+1.31e-03

Pos logit contributions
ced+0.056
pen+0.054
 marker+0.050
 pro+0.049
+0.048
Neg logit contributions
igators-0.033
 wolves-0.033
eer-0.029
 bamboo-0.028
unn-0.025
Token playing
Token ID2712
Feature activation+2.84e-02

Pos logit contributions
ced+0.003
pen+0.002
 marker+0.002
+0.002
 str+0.002
Neg logit contributions
igators-0.002
eer-0.002
 wolves-0.002
 bamboo-0.002
ior-0.002
Token -
Token ID532
Feature activation+1.59e-02

Pos logit contributions
ced+0.059
pen+0.057
 marker+0.052
+0.052
 pro+0.051
Neg logit contributions
 wolves-0.044
igators-0.044
eer-0.039
 bamboo-0.038
py-0.035
Token don
Token ID836
Feature activation+7.31e-02

Pos logit contributions
ced+0.022
pen+0.020
 pro+0.019
 marker+0.019
 str+0.018
Neg logit contributions
igators-0.034
eer-0.032
 wolves-0.032
py-0.031
unn-0.031
Token that
Token ID326
Feature activation+2.09e-02

Pos logit contributions
igators+0.005
 wolves+0.005
eer+0.005
py+0.005
unn+0.004
Neg logit contributions
ced-0.006
pen-0.005
-0.005
 pro-0.005
 marker-0.005
Token Fl
Token ID1610
Feature activation-7.20e-03

Pos logit contributions
ced+0.037
pen+0.035
 pro+0.034
 marker+0.033
+0.032
Neg logit contributions
igators-0.037
 wolves-0.037
eer-0.034
 bamboo-0.033
py-0.032
Tokenuffy
Token ID15352
Feature activation+2.68e-02

Pos logit contributions
igators+0.015
 wolves+0.014
eer+0.013
 bamboo+0.012
 choices+0.012
Neg logit contributions
-0.012
ced-0.011
pen-0.011
 marker-0.009
 pro-0.009
Token,
Token ID11
Feature activation+4.84e-02

Pos logit contributions
ced+0.043
pen+0.042
+0.038
 marker+0.036
 pro+0.036
Neg logit contributions
 wolves-0.053
igators-0.052
 bamboo-0.048
eer-0.047
py-0.045
Token it
Token ID340
Feature activation+3.37e-03

Pos logit contributions
ced+0.078
pen+0.075
 pro+0.071
 marker+0.070
+0.068
Neg logit contributions
igators-0.093
 wolves-0.089
eer-0.085
unn-0.080
py-0.080
Token isn
Token ID2125
Feature activation+8.24e-02

Pos logit contributions
ced+0.005
pen+0.004
 marker+0.004
 pro+0.004
+0.004
Neg logit contributions
 wolves-0.007
igators-0.007
eer-0.007
 bamboo-0.007
unn-0.006
Token't
Token ID470
Feature activation+2.47e-02

Pos logit contributions
ced+0.095
pen+0.089
 marker+0.076
 pro+0.072
+0.071
Neg logit contributions
igators-0.204
 wolves-0.203
 bamboo-0.185
eer-0.184
py-0.179
Token nice
Token ID3621
Feature activation+2.80e-02

Pos logit contributions
ced+0.044
pen+0.040
 marker+0.039
 pro+0.037
 str+0.037
Neg logit contributions
igators-0.042
 wolves-0.042
eer-0.039
 habitats-0.039
unn-0.038
Token.
Token ID13
Feature activation-4.10e-03

Pos logit contributions
pen+0.045
ced+0.045
 pro+0.042
 marker+0.041
+0.038
Neg logit contributions
igators-0.053
 wolves-0.053
eer-0.049
 bamboo-0.048
py-0.046
Tokenâ
Token ID22940
Feature activation+3.31e-03

Pos logit contributions
igators+0.007
 wolves+0.007
eer+0.007
py+0.006
 bamboo+0.006
Neg logit contributions
-0.007
pen-0.007
ced-0.006
 pro-0.006
can-0.006
Token
Token ID26391
Feature activation+1.11e-02

Pos logit contributions
ced+0.005
pen+0.005
+0.005
mine+0.004
 marker+0.004
Neg logit contributions
 wolves-0.007
igators-0.007
 bamboo-0.006
eer-0.006
 gor-0.006
Token,
Token ID11
Feature activation+3.11e-02

Pos logit contributions
igators+0.020
 wolves+0.020
eer+0.018
 bamboo+0.017
py+0.016
Neg logit contributions
ced-0.030
pen-0.029
 marker-0.027
 pro-0.026
-0.026
Token "
Token ID366
Feature activation+5.29e-02

Pos logit contributions
ced+0.063
pen+0.061
 marker+0.056
+0.056
 pro+0.054
Neg logit contributions
 wolves-0.050
igators-0.049
eer-0.044
 bamboo-0.043
py-0.039
TokenT
Token ID51
Feature activation-1.45e-03

Pos logit contributions
ced+0.077
pen+0.074
+0.066
 marker+0.065
 pro+0.063
Neg logit contributions
igators-0.113
 wolves-0.112
eer-0.102
 bamboo-0.101
py-0.096
Tokenasting
Token ID9222
Feature activation+2.10e-02

Pos logit contributions
 wolves+0.002
igators+0.002
eer+0.002
 bamboo+0.002
py+0.002
Neg logit contributions
ced-0.003
pen-0.003
 marker-0.002
-0.002
 pro-0.002
Token things
Token ID1243
Feature activation+1.95e-02

Pos logit contributions
ced+0.036
pen+0.035
 marker+0.032
+0.031
 pro+0.031
Neg logit contributions
 wolves-0.040
igators-0.039
eer-0.036
 bamboo-0.034
py-0.033
Token isn
Token ID2125
Feature activation+8.24e-02

Pos logit contributions
ced+0.031
pen+0.030
 marker+0.028
+0.026
 pro+0.026
Neg logit contributions
 wolves-0.039
igators-0.037
eer-0.036
 bamboo-0.035
py-0.033
Token't
Token ID470
Feature activation+2.17e-02

Pos logit contributions
ced+0.110
pen+0.102
 marker+0.090
 widening+0.086
 pro+0.086
Neg logit contributions
igators-0.192
 wolves-0.186
 bamboo-0.167
py-0.166
eer-0.166
Token always
Token ID1464
Feature activation+1.27e-02

Pos logit contributions
ced+0.040
pen+0.037
 marker+0.037
 pro+0.035
 str+0.033
Neg logit contributions
 wolves-0.036
igators-0.035
eer-0.032
 habitats-0.032
 bamboo-0.032
Token a
Token ID257
Feature activation+3.87e-02

Pos logit contributions
ced+0.023
pen+0.020
 marker+0.019
 pro+0.019
 str+0.018
Neg logit contributions
 wolves-0.022
unn-0.021
igators-0.021
eer-0.021
 bamboo-0.020
Token good
Token ID922
Feature activation+5.09e-03

Pos logit contributions
ced+0.081
pen+0.080
+0.074
 marker+0.071
 widening+0.071
Neg logit contributions
 wolves-0.058
igators-0.056
eer-0.051
 bamboo-0.050
 gorilla-0.045
Token idea
Token ID2126
Feature activation+1.58e-02

Pos logit contributions
ced+0.010
pen+0.009
 marker+0.009
+0.008
 pro+0.008
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.007
Token We
Token ID775
Feature activation+2.98e-02

Pos logit contributions
 wolves+0.015
igators+0.014
 bamboo+0.014
eer+0.013
py+0.013
Neg logit contributions
-0.013
pen-0.013
 dot-0.013
 marker-0.012
mine-0.012
Token have
Token ID423
Feature activation-4.46e-03

Pos logit contributions
ced+0.054
pen+0.052
+0.047
 marker+0.047
 pro+0.046
Neg logit contributions
 wolves-0.053
igators-0.053
eer-0.048
 bamboo-0.047
py-0.043
Token different
Token ID1180
Feature activation+8.79e-03

Pos logit contributions
igators+0.008
 wolves+0.008
eer+0.007
 bamboo+0.007
py+0.007
Neg logit contributions
ced-0.008
pen-0.008
 marker-0.008
 str-0.007
 markers-0.007
Token likes
Token ID7832
Feature activation+5.55e-03

Pos logit contributions
ced+0.014
pen+0.014
 marker+0.014
 markers+0.013
 str+0.012
Neg logit contributions
 wolves-0.017
igators-0.016
eer-0.015
 bamboo-0.015
 Dod-0.014
Token and
Token ID290
Feature activation+1.34e-02

Pos logit contributions
ced+0.010
pen+0.010
 marker+0.010
 markers+0.010
 str+0.009
Neg logit contributions
igators-0.009
 wolves-0.008
eer-0.008
py-0.007
 bamboo-0.007
Token disl
Token ID19621
Feature activation+8.20e-02

Pos logit contributions
ced+0.022
 marker+0.022
 str+0.021
 markers+0.021
pen+0.020
Neg logit contributions
 wolves-0.024
igators-0.023
eer-0.022
 bamboo-0.022
 Dod-0.021
Tokenikes
Token ID7938
Feature activation+2.51e-02

Pos logit contributions
ced+0.158
pen+0.146
+0.141
 marker+0.139
 pro+0.135
Neg logit contributions
igators-0.130
 wolves-0.127
 about-0.123
eer-0.120
 choices-0.115
Token.
Token ID13
Feature activation-9.28e-03

Pos logit contributions
ced+0.045
pen+0.044
 marker+0.041
 pro+0.040
+0.039
Neg logit contributions
 wolves-0.044
igators-0.044
 bamboo-0.040
eer-0.039
 Fif-0.037
Token We
Token ID775
Feature activation+2.69e-02

Pos logit contributions
 wolves+0.016
igators+0.016
 bamboo+0.015
eer+0.014
py+0.013
Neg logit contributions
pen-0.015
-0.015
 dot-0.015
 marker-0.014
ced-0.014
Token can
Token ID460
Feature activation+5.37e-02

Pos logit contributions
ced+0.052
pen+0.050
+0.047
 marker+0.045
 widening+0.045
Neg logit contributions
igators-0.045
 wolves-0.044
eer-0.040
 bamboo-0.038
 dogs-0.035
Token be
Token ID307
Feature activation-6.55e-03

Pos logit contributions
ced+0.105
pen+0.099
+0.091
 pro+0.089
 marker+0.089
Neg logit contributions
igators-0.089
 wolves-0.087
eer-0.078
 bamboo-0.078
py-0.073
Token around
Token ID1088
Feature activation+2.52e-03

Pos logit contributions
igators+0.041
 wolves+0.036
unn+0.036
 bamboo+0.036
eer+0.034
Neg logit contributions
ced-0.049
pen-0.046
 str-0.042
 marker-0.042
 pro-0.041
Token before
Token ID878
Feature activation+1.32e-02

Pos logit contributions
ced+0.005
pen+0.005
 marker+0.005
 pro+0.005
 str+0.005
Neg logit contributions
igators-0.003
 bamboo-0.003
unn-0.003
 wolves-0.003
ifi-0.003
Token taking
Token ID2263
Feature activation-2.80e-02

Pos logit contributions
ced+0.021
pen+0.020
 marker+0.018
+0.018
 pro+0.018
Neg logit contributions
igators-0.026
eer-0.025
 wolves-0.024
 bamboo-0.023
unn-0.022
Token something
Token ID1223
Feature activation-1.28e-02

Pos logit contributions
igators+0.064
 wolves+0.061
eer+0.057
 bamboo+0.056
unn+0.055
Neg logit contributions
ced-0.040
pen-0.038
 marker-0.032
 str-0.030
 pro-0.030
Token that
Token ID326
Feature activation+2.97e-02

Pos logit contributions
igators+0.023
 wolves+0.023
eer+0.021
py+0.021
ior+0.019
Neg logit contributions
pen-0.022
ced-0.022
 pro-0.020
 marker-0.020
 str-0.019
Token isn
Token ID2125
Feature activation+8.20e-02

Pos logit contributions
ced+0.046
pen+0.044
 marker+0.043
 str+0.040
 pro+0.040
Neg logit contributions
 wolves-0.058
igators-0.053
 bamboo-0.052
eer-0.050
py-0.049
Token't
Token ID470
Feature activation+2.75e-02

Pos logit contributions
ced+0.104
pen+0.097
 marker+0.086
 pro+0.080
 widening+0.079
Neg logit contributions
igators-0.196
 wolves-0.195
eer-0.176
 bamboo-0.176
py-0.173
Token yours
Token ID12431
Feature activation+1.15e-02

Pos logit contributions
ced+0.057
pen+0.054
 marker+0.051
 pro+0.050
 str+0.049
Neg logit contributions
 wolves-0.039
igators-0.038
 bamboo-0.034
unn-0.033
 habitats-0.033
Token."
Token ID526
Feature activation+2.06e-02

Pos logit contributions
pen+0.021
ced+0.020
can+0.019
 marker+0.019
 pro+0.019
Neg logit contributions
igators-0.020
 wolves-0.020
 bamboo-0.016
eer-0.016
 habitats-0.016
Token
Token ID198
Feature activation-5.07e-03

Pos logit contributions
pen+0.031
ced+0.030
+0.029
 marker+0.027
 pro+0.027
Neg logit contributions
igators-0.043
 wolves-0.041
eer-0.038
 bamboo-0.036
py-0.036
Token
Token ID198
Feature activation-3.39e-03

Pos logit contributions
igators+0.010
 wolves+0.010
eer+0.009
 bamboo+0.009
 choices+0.008
Neg logit contributions
ced-0.008
pen-0.008
-0.007
 marker-0.007
 pro-0.007
Token "
Token ID366
Feature activation+5.64e-02

Pos logit contributions
 wolves+0.020
igators+0.020
eer+0.018
 bamboo+0.018
py+0.017
Neg logit contributions
ced-0.020
pen-0.019
-0.018
 marker-0.017
 pro-0.017
TokenThis
Token ID1212
Feature activation-5.88e-03

Pos logit contributions
pen+0.097
ced+0.093
 marker+0.086
+0.084
 widening+0.080
Neg logit contributions
igators-0.100
 wolves-0.097
eer-0.087
 bamboo-0.086
 hay-0.082
Token pe
Token ID613
Feature activation-1.87e-02

Pos logit contributions
 wolves+0.011
igators+0.010
eer+0.009
 bamboo+0.009
py+0.009
Neg logit contributions
ced-0.011
pen-0.010
 marker-0.009
-0.009
 pro-0.009
Tokenb
Token ID65
Feature activation+2.06e-02

Pos logit contributions
 wolves+0.043
igators+0.042
eer+0.039
 bamboo+0.038
 dogs+0.036
Neg logit contributions
ced-0.025
pen-0.024
 marker-0.021
-0.020
 pro-0.020
Tokenble
Token ID903
Feature activation-4.60e-03

Pos logit contributions
ced+0.025
pen+0.024
 marker+0.021
+0.021
 pro+0.020
Neg logit contributions
 wolves-0.049
igators-0.049
eer-0.045
 bamboo-0.044
py-0.042
Token isn
Token ID2125
Feature activation+8.18e-02

Pos logit contributions
 wolves+0.008
igators+0.008
 bamboo+0.007
eer+0.007
py+0.007
Neg logit contributions
ced-0.008
pen-0.008
 marker-0.007
 pro-0.007
-0.007
Token't
Token ID470
Feature activation+1.91e-02

Pos logit contributions
ced+0.121
pen+0.116
 marker+0.103
 widening+0.102
 pro+0.099
Neg logit contributions
igators-0.179
 wolves-0.169
py-0.154
 bamboo-0.151
eer-0.150
Token as
Token ID355
Feature activation-7.16e-03

Pos logit contributions
ced+0.036
pen+0.035
 marker+0.032
 pro+0.031
+0.031
Neg logit contributions
 wolves-0.033
igators-0.032
eer-0.029
 bamboo-0.028
py-0.026
Token pretty
Token ID2495
Feature activation+1.15e-02

Pos logit contributions
 wolves+0.014
igators+0.013
eer+0.012
 bamboo+0.012
py+0.012
Neg logit contributions
ced-0.012
 marker-0.011
pen-0.011
 pro-0.010
 markers-0.010
Token as
Token ID355
Feature activation-2.08e-02

Pos logit contributions
ced+0.021
pen+0.020
 marker+0.019
 pro+0.018
+0.018
Neg logit contributions
 wolves-0.021
igators-0.020
eer-0.018
 bamboo-0.018
py-0.017
Token the
Token ID262
Feature activation-5.76e-03

Pos logit contributions
 wolves+0.039
igators+0.038
eer+0.035
py+0.034
 bamboo+0.034
Neg logit contributions
ced-0.035
pen-0.032
 marker-0.031
 pro-0.030
 markers-0.029
Token "
Token ID366
Feature activation+5.32e-02

Pos logit contributions
ced+0.053
pen+0.053
 marker+0.048
+0.047
 pro+0.046
Neg logit contributions
 wolves-0.034
igators-0.033
eer-0.029
 bamboo-0.029
 about-0.026
TokenThe
Token ID464
Feature activation-3.09e-03

Pos logit contributions
ced+0.102
pen+0.099
 marker+0.090
+0.089
 widened+0.082
Neg logit contributions
igators-0.086
 wolves-0.085
eer-0.076
 bamboo-0.075
py-0.069
Token sign
Token ID1051
Feature activation-2.28e-02

Pos logit contributions
igators+0.005
 wolves+0.005
eer+0.004
 bamboo+0.004
py+0.004
Neg logit contributions
ced-0.006
pen-0.006
 marker-0.006
-0.006
 pro-0.006
Token says
Token ID1139
Feature activation+2.46e-03

Pos logit contributions
 wolves+0.039
igators+0.036
 bamboo+0.035
eer+0.035
py+0.032
Neg logit contributions
ced-0.042
pen-0.040
 marker-0.038
 pro-0.037
 str-0.036
Token '
Token ID705
Feature activation+4.95e-02

Pos logit contributions
ced+0.004
pen+0.004
 marker+0.004
+0.004
 pro+0.004
Neg logit contributions
igators-0.005
 wolves-0.004
eer-0.004
unn-0.004
 bamboo-0.004
TokenCA
Token ID8141
Feature activation+8.17e-02

Pos logit contributions
ced+0.075
pen+0.072
 marker+0.067
+0.064
 pro+0.062
Neg logit contributions
igators-0.099
 wolves-0.099
eer-0.091
 bamboo-0.089
 dogs-0.083
TokenUTION
Token ID35354
Feature activation+3.38e-03

Pos logit contributions
ced+0.136
pen+0.120
 marker+0.113
 widened+0.112
 widening+0.111
Neg logit contributions
 wolves-0.145
igators-0.144
 bamboo-0.139
 Rex-0.134
 gorilla-0.129
Token'."
Token ID30827
Feature activation+1.81e-02

Pos logit contributions
ced+0.005
pen+0.005
 marker+0.004
+0.004
mine+0.004
Neg logit contributions
 wolves-0.007
igators-0.007
 bamboo-0.007
eer-0.007
py-0.006
Token
Token ID220
Feature activation+1.83e-02

Pos logit contributions
ced+0.034
pen+0.033
 marker+0.030
+0.030
 pro+0.029
Neg logit contributions
 wolves-0.031
igators-0.031
eer-0.028
 bamboo-0.027
py-0.025
Token
Token ID198
Feature activation+6.12e-03

Pos logit contributions
ced+0.034
pen+0.033
+0.030
 marker+0.030
 pro+0.029
Neg logit contributions
 wolves-0.032
igators-0.031
eer-0.028
 bamboo-0.028
py-0.026
Token
Token ID198
Feature activation+6.82e-03

Pos logit contributions
ced+0.012
pen+0.011
 marker+0.011
+0.010
 pro+0.010
Neg logit contributions
 wolves-0.010
igators-0.010
eer-0.009
 bamboo-0.009
py-0.008
Token never
Token ID1239
Feature activation-3.70e-02

Pos logit contributions
 wolves+0.023
igators+0.023
eer+0.022
 bamboo+0.021
py+0.020
Neg logit contributions
ced-0.019
pen-0.018
 pro-0.017
 str-0.017
 marker-0.017
Token to
Token ID284
Feature activation+1.46e-02

Pos logit contributions
 wolves+0.079
igators+0.079
eer+0.073
 bamboo+0.072
py+0.069
Neg logit contributions
pen-0.054
ced-0.054
 str-0.049
 pro-0.049
 marker-0.047
Token take
Token ID1011
Feature activation-2.90e-02

Pos logit contributions
pen+0.023
ced+0.023
 marker+0.021
+0.020
 str+0.020
Neg logit contributions
 wolves-0.030
igators-0.030
eer-0.027
 bamboo-0.026
py-0.025
Token anything
Token ID1997
Feature activation-3.54e-03

Pos logit contributions
igators+0.054
 wolves+0.051
eer+0.050
py+0.048
unn+0.047
Neg logit contributions
ced-0.052
pen-0.049
 pro-0.043
 marker-0.042
 str-0.041
Token that
Token ID326
Feature activation+2.49e-02

Pos logit contributions
 wolves+0.006
igators+0.006
eer+0.006
 bamboo+0.005
py+0.005
Neg logit contributions
ced-0.007
pen-0.007
 pro-0.006
 marker-0.006
-0.006
Token isn
Token ID2125
Feature activation+8.17e-02

Pos logit contributions
ced+0.044
pen+0.042
 marker+0.040
+0.039
 pro+0.039
Neg logit contributions
 wolves-0.045
igators-0.044
 bamboo-0.040
eer-0.040
py-0.038
Token't
Token ID470
Feature activation+2.57e-02

Pos logit contributions
ced+0.112
pen+0.104
 marker+0.099
 widening+0.091
 widened+0.089
Neg logit contributions
igators-0.183
 wolves-0.179
py-0.161
eer-0.159
 about-0.159
Token hers
Token ID25144
Feature activation+1.15e-02

Pos logit contributions
ced+0.048
pen+0.045
 pro+0.042
 marker+0.042
 str+0.041
Neg logit contributions
 wolves-0.041
igators-0.039
 bamboo-0.037
unn-0.037
eer-0.037
Token.
Token ID13
Feature activation-1.65e-02

Pos logit contributions
ced+0.022
pen+0.021
 marker+0.020
+0.019
 pro+0.019
Neg logit contributions
 wolves-0.019
igators-0.019
eer-0.017
 bamboo-0.017
py-0.015
Token The
Token ID383
Feature activation-2.64e-03

Pos logit contributions
igators+0.032
 wolves+0.032
eer+0.028
 bamboo+0.028
py+0.026
Neg logit contributions
pen-0.027
ced-0.027
-0.026
 pro-0.024
 marker-0.024
Token end
Token ID886
Feature activation-3.51e-02

Pos logit contributions
 wolves+0.004
igators+0.004
eer+0.004
 bamboo+0.004
 dogs+0.003
Neg logit contributions
ced-0.005
pen-0.005
 marker-0.005
-0.005
 pro-0.005
Token like
Token ID588
Feature activation+5.97e-03

Pos logit contributions
 wolves+0.016
igators+0.015
eer+0.014
 bamboo+0.013
py+0.013
Neg logit contributions
pen-0.019
ced-0.018
 pro-0.017
 marker-0.017
-0.017
Token her
Token ID607
Feature activation-7.02e-03

Pos logit contributions
ced+0.012
pen+0.012
+0.011
 marker+0.011
 pro+0.011
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.007
Token big
Token ID1263
Feature activation+3.03e-02

Pos logit contributions
 wolves+0.009
igators+0.009
eer+0.008
 bamboo+0.008
py+0.007
Neg logit contributions
ced-0.016
pen-0.016
 marker-0.015
-0.015
 pro-0.014
Token brother
Token ID3956
Feature activation+3.03e-02

Pos logit contributions
ced+0.055
pen+0.054
 marker+0.049
+0.049
 pro+0.048
Neg logit contributions
 wolves-0.053
igators-0.053
eer-0.048
 bamboo-0.047
py-0.044
Token Tom
Token ID4186
Feature activation+5.43e-02

Pos logit contributions
pen+0.054
ced+0.054
 pro+0.049
 marker+0.048
 str+0.046
Neg logit contributions
 wolves-0.055
igators-0.054
eer-0.049
 bamboo-0.048
py-0.045
Token,
Token ID11
Feature activation+8.16e-02

Pos logit contributions
ced+0.100
pen+0.099
 marker+0.088
 pro+0.087
mine+0.086
Neg logit contributions
 wolves-0.096
igators-0.095
eer-0.084
 bamboo-0.083
unn-0.078
Token who
Token ID508
Feature activation+1.06e-02

Pos logit contributions
ced+0.171
pen+0.169
 marker+0.155
+0.153
 pro+0.153
Neg logit contributions
 wolves-0.120
igators-0.119
eer-0.107
 bamboo-0.101
py-0.095
Token had
Token ID550
Feature activation+1.71e-02

Pos logit contributions
ced+0.018
pen+0.018
 marker+0.016
+0.016
 widening+0.016
Neg logit contributions
igators-0.019
 wolves-0.019
eer-0.018
 bamboo-0.017
py-0.016
Token many
Token ID867
Feature activation-9.48e-03

Pos logit contributions
ced+0.031
pen+0.030
 pro+0.027
 marker+0.027
 str+0.026
Neg logit contributions
 wolves-0.031
igators-0.031
eer-0.028
 bamboo-0.027
unn-0.026
Token trophies
Token ID21732
Feature activation+1.06e-02

Pos logit contributions
igators+0.014
 wolves+0.014
eer+0.012
 bamboo+0.012
 dogs+0.011
Neg logit contributions
ced-0.020
pen-0.020
-0.018
 marker-0.018
 pro-0.018
Token on
Token ID319
Feature activation+8.77e-03

Pos logit contributions
ced+0.023
pen+0.022
 marker+0.020
+0.020
 pro+0.020
Neg logit contributions
 wolves-0.016
igators-0.015
eer-0.014
 bamboo-0.013
py-0.012
Token will
Token ID481
Feature activation+2.92e-02

Pos logit contributions
ced+0.018
pen+0.017
 marker+0.016
 str+0.016
 pro+0.015
Neg logit contributions
igators-0.018
 wolves-0.018
 bamboo-0.017
eer-0.017
py-0.015
Token never
Token ID1239
Feature activation-2.88e-02

Pos logit contributions
ced+0.059
pen+0.058
 marker+0.053
+0.053
 pro+0.052
Neg logit contributions
 wolves-0.046
igators-0.045
eer-0.040
 bamboo-0.039
py-0.036
Token take
Token ID1011
Feature activation-1.81e-02

Pos logit contributions
 wolves+0.058
igators+0.058
eer+0.053
 bamboo+0.052
py+0.049
Neg logit contributions
pen-0.046
ced-0.046
 marker-0.041
 pro-0.040
-0.039
Token anything
Token ID1997
Feature activation-2.71e-03

Pos logit contributions
igators+0.033
 wolves+0.031
eer+0.030
 bamboo+0.028
py+0.028
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.029
 pro-0.028
 str-0.027
Token that
Token ID326
Feature activation+3.21e-02

Pos logit contributions
 wolves+0.004
igators+0.004
eer+0.004
 bamboo+0.004
py+0.004
Neg logit contributions
ced-0.005
pen-0.005
 marker-0.005
 pro-0.005
-0.005
Token isn
Token ID2125
Feature activation+8.12e-02

Pos logit contributions
ced+0.061
pen+0.059
 marker+0.055
+0.054
 pro+0.053
Neg logit contributions
 wolves-0.055
igators-0.054
eer-0.048
 bamboo-0.048
py-0.044
Tokenâ
Token ID22940
Feature activation+4.21e-02

Pos logit contributions
ced+0.122
pen+0.111
 marker+0.110
 widening+0.102
 markers+0.101
Neg logit contributions
igators-0.170
 wolves-0.165
py-0.150
 about-0.148
eer-0.143
Token
Token ID26391
Feature activation+3.37e-02

Pos logit contributions
ced+0.075
pen+0.073
+0.066
 marker+0.066
 pro+0.064
Neg logit contributions
 wolves-0.077
igators-0.076
eer-0.069
 bamboo-0.068
py-0.063
Token
Token ID8151
Feature activation+5.92e-02

Pos logit contributions
ced+0.061
pen+0.060
 marker+0.058
 widening+0.057
 widened+0.055
Neg logit contributions
 wolves-0.056
igators-0.051
 dogs-0.047
 about-0.047
eer-0.046
Tokent
Token ID83
Feature activation+2.28e-02

Pos logit contributions
ced+0.076
pen+0.070
 marker+0.065
 widening+0.062
 widened+0.061
Neg logit contributions
igators-0.135
 wolves-0.134
eer-0.122
 bamboo-0.118
 about-0.116
Token hers
Token ID25144
Feature activation+6.54e-03

Pos logit contributions
ced+0.042
pen+0.040
 pro+0.037
 marker+0.036
 str+0.035
Neg logit contributions
 wolves-0.038
igators-0.038
eer-0.035
 bamboo-0.035
unn-0.033
Token is
Token ID318
Feature activation+1.32e-02

Pos logit contributions
ced+0.013
pen+0.013
+0.012
 marker+0.012
 pro+0.012
Neg logit contributions
 wolves-0.007
igators-0.007
eer-0.006
 bamboo-0.006
py-0.006
Token the
Token ID262
Feature activation+2.86e-02

Pos logit contributions
ced+0.020
 pro+0.017
 marker+0.017
 markers+0.017
pen+0.016
Neg logit contributions
unn-0.026
eer-0.026
 wolves-0.026
igators-0.025
ior-0.023
Token fairy
Token ID25607
Feature activation+4.82e-03

Pos logit contributions
ced+0.058
pen+0.056
+0.052
 marker+0.050
 pro+0.050
Neg logit contributions
 wolves-0.046
igators-0.045
eer-0.040
 bamboo-0.040
py-0.036
Token garden
Token ID11376
Feature activation+1.45e-02

Pos logit contributions
ced+0.008
pen+0.008
 marker+0.008
 pro+0.007
 str+0.007
Neg logit contributions
 wolves-0.009
igators-0.008
 bamboo-0.008
eer-0.007
unn-0.007
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
ced+0.023
pen+0.022
 marker+0.021
 markers+0.020
 pro+0.019
Neg logit contributions
 wolves-0.027
igators-0.025
eer-0.024
py-0.023
unn-0.023
Token Isn
Token ID25110
Feature activation+8.11e-02

Pos logit contributions
 wolves+0.025
igators+0.025
eer+0.022
 bamboo+0.022
unn+0.021
Neg logit contributions
pen-0.018
can-0.017
-0.017
 dot-0.017
 marker-0.017
Token't
Token ID470
Feature activation+1.98e-02

Pos logit contributions
ced+0.130
pen+0.123
 marker+0.117
 pro+0.110
 widening+0.109
Neg logit contributions
igators-0.163
 wolves-0.151
 about-0.145
py-0.140
 bamboo-0.138
Token it
Token ID340
Feature activation+3.02e-02

Pos logit contributions
ced+0.027
pen+0.026
 marker+0.023
 pro+0.023
+0.021
Neg logit contributions
 wolves-0.043
igators-0.043
eer-0.039
 bamboo-0.039
py-0.037
Token wonderful
Token ID7932
Feature activation+2.76e-02

Pos logit contributions
ced+0.050
pen+0.047
 marker+0.046
 pro+0.043
 str+0.042
Neg logit contributions
 wolves-0.056
igators-0.056
eer-0.052
 bamboo-0.050
unn-0.048
Token?"
Token ID1701
Feature activation+3.60e-02

Pos logit contributions
ced+0.053
pen+0.051
 marker+0.049
 pro+0.048
 markers+0.045
Neg logit contributions
 wolves-0.045
igators-0.045
eer-0.040
 bamboo-0.038
unn-0.036
Token
Token ID198
Feature activation+3.59e-03

Pos logit contributions
ced+0.088
pen+0.085
 marker+0.080
+0.079
 pro+0.078
Neg logit contributions
 wolves-0.043
igators-0.040
 bamboo-0.035
eer-0.034
 dogs-0.033
Token made
Token ID925
Feature activation+1.00e-02

Pos logit contributions
ced+0.047
pen+0.045
 widening+0.044
mine+0.043
+0.042
Neg logit contributions
 wolves-0.029
igators-0.028
eer-0.027
 bamboo-0.026
 about-0.026
Token Ruby
Token ID10888
Feature activation+2.16e-02

Pos logit contributions
ced+0.019
pen+0.018
 marker+0.017
 pro+0.016
+0.016
Neg logit contributions
igators-0.017
 wolves-0.017
eer-0.016
 bamboo-0.015
py-0.014
Token a
Token ID257
Feature activation+3.89e-02

Pos logit contributions
ced+0.038
pen+0.037
 marker+0.033
+0.033
 pro+0.032
Neg logit contributions
 wolves-0.040
igators-0.039
eer-0.035
 bamboo-0.035
py-0.032
Token princess
Token ID21752
Feature activation+1.64e-02

Pos logit contributions
ced+0.070
pen+0.068
+0.062
 marker+0.059
mine+0.058
Neg logit contributions
 wolves-0.070
igators-0.068
 bamboo-0.064
eer-0.062
py-0.058
Token.
Token ID13
Feature activation-6.13e-03

Pos logit contributions
ced+0.031
pen+0.031
 marker+0.028
 pro+0.027
+0.027
Neg logit contributions
igators-0.028
 wolves-0.028
eer-0.024
 bamboo-0.024
py-0.022
Token Isn
Token ID25110
Feature activation+8.11e-02

Pos logit contributions
igators+0.012
 wolves+0.012
eer+0.011
 ost+0.010
 bamboo+0.010
Neg logit contributions
pen-0.009
 marker-0.009
-0.008
can-0.008
 pro-0.008
Token't
Token ID470
Feature activation+2.02e-02

Pos logit contributions
ced+0.126
pen+0.121
 marker+0.110
 widening+0.104
 pro+0.102
Neg logit contributions
igators-0.167
 wolves-0.161
 about-0.149
py-0.146
 bamboo-0.145
Token she
Token ID673
Feature activation+3.38e-02

Pos logit contributions
ced+0.030
pen+0.029
 marker+0.026
 pro+0.025
+0.025
Neg logit contributions
 wolves-0.042
igators-0.042
eer-0.038
 bamboo-0.038
py-0.035
Token much
Token ID881
Feature activation-1.15e-02

Pos logit contributions
ced+0.062
pen+0.060
 marker+0.055
+0.054
 pro+0.054
Neg logit contributions
 wolves-0.059
igators-0.059
eer-0.053
 bamboo-0.052
py-0.048
Token better
Token ID1365
Feature activation+1.55e-02

Pos logit contributions
igators+0.018
 wolves+0.017
eer+0.016
 bamboo+0.014
py+0.014
Neg logit contributions
ced-0.024
pen-0.023
 marker-0.022
 pro-0.021
-0.021
Token now
Token ID783
Feature activation+5.99e-03

Pos logit contributions
ced+0.028
pen+0.027
 marker+0.026
 pro+0.026
 str+0.025
Neg logit contributions
igators-0.029
 wolves-0.026
 bamboo-0.024
eer-0.024
unn-0.022
Token drew
Token ID9859
Feature activation+1.91e-02

Pos logit contributions
ced+0.052
pen+0.050
 widening+0.048
arse+0.047
+0.047
Neg logit contributions
igators-0.037
 wolves-0.035
eer-0.034
 lives-0.032
 bamboo-0.032
Token a
Token ID257
Feature activation+2.87e-02

Pos logit contributions
ced+0.034
pen+0.032
 marker+0.030
 pro+0.029
mine+0.028
Neg logit contributions
 wolves-0.035
igators-0.034
eer-0.031
 bamboo-0.029
unn-0.029
Token pink
Token ID11398
Feature activation+3.35e-02

Pos logit contributions
ced+0.048
pen+0.047
 marker+0.043
+0.042
 pro+0.042
Neg logit contributions
 wolves-0.055
igators-0.055
eer-0.049
 bamboo-0.048
py-0.045
Token flower
Token ID15061
Feature activation+7.60e-03

Pos logit contributions
ced+0.056
pen+0.053
+0.047
 marker+0.046
 pro+0.045
Neg logit contributions
 wolves-0.065
igators-0.064
eer-0.059
 bamboo-0.059
py-0.055
Token.
Token ID13
Feature activation-9.03e-03

Pos logit contributions
pen+0.013
ced+0.012
 marker+0.012
 pro+0.012
 dot+0.011
Neg logit contributions
 wolves-0.014
igators-0.014
eer-0.013
unn-0.012
 bamboo-0.011
Token Isn
Token ID25110
Feature activation+8.10e-02

Pos logit contributions
 wolves+0.018
igators+0.018
eer+0.016
 bamboo+0.016
py+0.015
Neg logit contributions
pen-0.014
ced-0.013
 marker-0.013
-0.013
 pro-0.013
Token't
Token ID470
Feature activation+2.05e-02

Pos logit contributions
ced+0.134
pen+0.124
 marker+0.114
 widening+0.110
 widened+0.106
Neg logit contributions
igators-0.158
 about-0.146
 wolves-0.144
 bamboo-0.136
py-0.134
Token it
Token ID340
Feature activation+3.24e-02

Pos logit contributions
ced+0.033
pen+0.032
+0.030
 marker+0.028
 widening+0.028
Neg logit contributions
 wolves-0.041
igators-0.041
eer-0.037
 bamboo-0.037
 about-0.035
Token beautiful
Token ID4950
Feature activation+4.15e-02

Pos logit contributions
ced+0.057
pen+0.055
 marker+0.051
 pro+0.049
+0.049
Neg logit contributions
 wolves-0.060
igators-0.059
eer-0.054
 bamboo-0.052
py-0.049
Token?"
Token ID1701
Feature activation+3.54e-02

Pos logit contributions
ced+0.092
pen+0.090
 marker+0.085
 pro+0.083
+0.083
Neg logit contributions
 wolves-0.057
igators-0.056
eer-0.049
 bamboo-0.047
py-0.043
Token she
Token ID673
Feature activation+1.03e-02

Pos logit contributions
ced+0.066
pen+0.064
 marker+0.058
+0.058
 pro+0.056
Neg logit contributions
 wolves-0.062
igators-0.061
eer-0.056
 bamboo-0.054
py-0.051
Token a
Token ID257
Feature activation+1.62e-02

Pos logit contributions
 wolves+0.037
igators+0.037
eer+0.035
unn+0.033
 bamboo+0.032
Neg logit contributions
ced-0.034
pen-0.030
 marker-0.028
-0.028
 pro-0.027
Token very
Token ID845
Feature activation-6.24e-02

Pos logit contributions
ced+0.032
pen+0.031
 marker+0.028
+0.028
mine+0.027
Neg logit contributions
 wolves-0.026
igators-0.026
 bamboo-0.023
eer-0.023
 gorilla-0.021
Token nice
Token ID3621
Feature activation-5.54e-03

Pos logit contributions
 wolves+0.119
igators+0.114
eer+0.107
py+0.104
 bamboo+0.099
Neg logit contributions
ced-0.101
 pro-0.096
 marker-0.091
pron-0.091
pen-0.090
Token k
Token ID479
Feature activation-1.72e-02

Pos logit contributions
 wolves+0.009
igators+0.009
eer+0.008
 bamboo+0.008
py+0.007
Neg logit contributions
ced-0.011
pen-0.011
 marker-0.010
-0.010
 pro-0.010
Tokenite
Token ID578
Feature activation-1.25e-02

Pos logit contributions
igators+0.034
 wolves+0.034
eer+0.031
 bamboo+0.031
 dogs+0.028
Neg logit contributions
ced-0.028
pen-0.026
 marker-0.024
 widened-0.024
 widening-0.024
Token isn
Token ID2125
Feature activation+8.06e-02

Pos logit contributions
 wolves+0.024
igators+0.023
 bamboo+0.021
eer+0.021
 habitats+0.020
Neg logit contributions
ced-0.020
pen-0.020
 marker-0.018
 pro-0.018
-0.017
Tokenâ
Token ID22940
Feature activation+4.18e-02

Pos logit contributions
ced+0.124
pen+0.116
 marker+0.110
 widening+0.103
 widened+0.102
Neg logit contributions
igators-0.167
 wolves-0.157
 about-0.143
 bamboo-0.142
py-0.140
Token
Token ID26391
Feature activation+4.11e-02

Pos logit contributions
ced+0.067
pen+0.066
+0.061
mine+0.059
 marker+0.058
Neg logit contributions
 wolves-0.085
igators-0.081
 bamboo-0.075
eer-0.074
py-0.070
Token
Token ID8151
Feature activation+5.91e-02

Pos logit contributions
ced+0.075
pen+0.072
 marker+0.067
 widening+0.064
 pro+0.064
Neg logit contributions
 wolves-0.072
igators-0.070
eer-0.063
 bamboo-0.062
 dogs-0.060
Tokent
Token ID83
Feature activation+1.56e-02

Pos logit contributions
ced+0.065
pen+0.060
 marker+0.053
 pro+0.049
+0.048
Neg logit contributions
igators-0.147
 wolves-0.145
eer-0.135
 bamboo-0.133
py-0.127
Token it
Token ID340
Feature activation+1.29e-02

Pos logit contributions
ced+0.027
pen+0.026
 pro+0.024
 marker+0.024
+0.023
Neg logit contributions
igators-0.029
 wolves-0.029
eer-0.026
 bamboo-0.026
py-0.024
Token merry
Token ID44570
Feature activation-2.28e-02

Pos logit contributions
 wolves+0.029
igators+0.028
eer+0.025
unn+0.025
 bamboo+0.025
Neg logit contributions
ced-0.029
pen-0.028
 marker-0.028
 pro-0.025
 markers-0.025
Token way
Token ID835
Feature activation-7.05e-03

Pos logit contributions
 wolves+0.039
igators+0.039
 bamboo+0.032
eer+0.032
 Fif+0.031
Neg logit contributions
ced-0.043
pen-0.041
 marker-0.038
 pro-0.037
 str-0.037
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
 wolves+0.012
igators+0.012
 bamboo+0.011
eer+0.011
py+0.010
Neg logit contributions
ced-0.013
pen-0.012
 marker-0.011
mine-0.011
 pro-0.011
Token<|endoftext|>
Token ID50256
Feature activation-5.89e-04

Pos logit contributions
 wolves+0.054
igators+0.052
eer+0.048
 choices+0.046
 bamboo+0.045
Neg logit contributions
-0.045
pen-0.044
ced-0.042
 pro-0.041
mine-0.040
TokenC
Token ID34
Feature activation-3.25e-02

Pos logit contributions
 wolves+0.001
igators+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.001
pen-0.001
 marker-0.001
-0.001
 pro-0.001
Tokenind
Token ID521
Feature activation-1.05e-01

Pos logit contributions
 wolves+0.056
igators+0.055
eer+0.050
 bamboo+0.049
py+0.045
Neg logit contributions
ced-0.061
pen-0.059
 marker-0.054
-0.054
 pro-0.053
Tokeny
Token ID88
Feature activation-3.73e-02

Pos logit contributions
 wolves+0.169
igators+0.160
 bamboo+0.147
 choices+0.142
 hay+0.129
Neg logit contributions
pen-0.199
ced-0.198
mine-0.193
hel-0.169
 str-0.168
Token and
Token ID290
Feature activation-8.21e-03

Pos logit contributions
igators+0.067
 wolves+0.067
 bamboo+0.060
eer+0.060
py+0.055
Neg logit contributions
ced-0.067
pen-0.066
 marker-0.059
-0.058
 pro-0.057
Token her
Token ID607
Feature activation-4.65e-02

Pos logit contributions
 wolves+0.015
igators+0.015
eer+0.014
 bamboo+0.013
 choices+0.013
Neg logit contributions
mine-0.013
pen-0.013
ced-0.013
-0.012
 str-0.012
Token mom
Token ID1995
Feature activation-1.64e-02

Pos logit contributions
 wolves+0.070
igators+0.069
eer+0.061
 bamboo+0.060
py+0.055
Neg logit contributions
ced-0.098
pen-0.095
 marker-0.088
-0.087
 pro-0.085
Tokenmy
Token ID1820
Feature activation-6.56e-04

Pos logit contributions
 wolves+0.034
igators+0.034
 bamboo+0.032
eer+0.031
 choices+0.030
Neg logit contributions
pen-0.023
ced-0.023
mine-0.021
 marker-0.020
 pro-0.019
Token to
Token ID284
Feature activation+4.60e-03

Pos logit contributions
ced+0.043
pen+0.041
 marker+0.038
+0.037
 pro+0.037
Neg logit contributions
 wolves-0.035
igators-0.035
eer-0.031
 bamboo-0.030
py-0.028
Token her
Token ID607
Feature activation-2.37e-02

Pos logit contributions
pen+0.007
ced+0.007
+0.007
mine+0.007
 marker+0.007
Neg logit contributions
igators-0.009
 wolves-0.009
unn-0.008
eer-0.008
 bamboo-0.008
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
igators+0.042
 wolves+0.040
eer+0.037
unn+0.035
py+0.035
Neg logit contributions
ced-0.043
pen-0.043
-0.039
 marker-0.039
 pro-0.038
Token<|endoftext|>
Token ID50256
Feature activation+8.75e-03

Pos logit contributions
 wolves+0.036
igators+0.036
eer+0.035
py+0.032
 bamboo+0.032
Neg logit contributions
-0.026
pen-0.025
ced-0.023
 pro-0.022
 Exc-0.021
TokenC
Token ID34
Feature activation-3.14e-02

Pos logit contributions
ced+0.017
pen+0.016
+0.015
 marker+0.015
 pro+0.014
Neg logit contributions
 wolves-0.015
igators-0.015
eer-0.013
 bamboo-0.013
py-0.012
Tokenind
Token ID521
Feature activation-1.03e-01

Pos logit contributions
 wolves+0.052
igators+0.051
eer+0.045
 bamboo+0.044
py+0.041
Neg logit contributions
ced-0.062
pen-0.061
 marker-0.055
-0.055
 pro-0.053
Tokeny
Token ID88
Feature activation-3.42e-02

Pos logit contributions
 wolves+0.204
igators+0.197
 bamboo+0.189
 choices+0.181
 Fif+0.167
Neg logit contributions
pen-0.153
ced-0.153
mine-0.148
hel-0.123
 marker-0.121
Token was
Token ID373
Feature activation-1.91e-02

Pos logit contributions
igators+0.066
 wolves+0.066
 bamboo+0.060
eer+0.059
py+0.055
Neg logit contributions
ced-0.057
pen-0.057
 marker-0.050
-0.049
 pro-0.048
Token a
Token ID257
Feature activation+1.05e-02

Pos logit contributions
igators+0.034
 wolves+0.033
eer+0.030
 bamboo+0.029
unn+0.028
Neg logit contributions
ced-0.035
pen-0.034
-0.031
 marker-0.031
 pro-0.030
Token cheerful
Token ID37999
Feature activation+4.23e-03

Pos logit contributions
ced+0.021
pen+0.021
 marker+0.019
+0.019
 widening+0.018
Neg logit contributions
 wolves-0.017
igators-0.016
eer-0.015
 bamboo-0.014
 gorilla-0.014
Token three
Token ID1115
Feature activation-2.98e-02

Pos logit contributions
ced+0.007
pen+0.007
 marker+0.006
 pro+0.006
+0.006
Neg logit contributions
igators-0.008
 wolves-0.008
eer-0.007
 bamboo-0.007
py-0.007
TokenThe
Token ID464
Feature activation-1.83e-02

Pos logit contributions
igators+0.023
 wolves+0.023
 bamboo+0.021
eer+0.020
py+0.019
Neg logit contributions
ced-0.019
pen-0.018
 marker-0.018
-0.016
 pro-0.016
Token end
Token ID886
Feature activation-4.29e-02

Pos logit contributions
igators+0.037
 wolves+0.036
eer+0.034
 bamboo+0.031
 hay+0.030
Neg logit contributions
ced-0.030
pen-0.027
 marker-0.025
 pro-0.025
-0.024
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
igators+0.100
 wolves+0.095
eer+0.095
unn+0.089
py+0.087
Neg logit contributions
ced-0.057
 pro-0.047
-0.046
pen-0.046
 marker-0.045
Token<|endoftext|>
Token ID50256
Feature activation+2.23e-02

Pos logit contributions
 wolves+0.037
igators+0.036
eer+0.033
 bamboo+0.032
py+0.030
Neg logit contributions
ced-0.037
pen-0.036
-0.033
 marker-0.033
 pro-0.032
TokenC
Token ID34
Feature activation-3.04e-02

Pos logit contributions
ced+0.048
pen+0.047
 marker+0.044
+0.043
 pro+0.043
Neg logit contributions
 wolves-0.031
igators-0.031
eer-0.027
 bamboo-0.027
py-0.024
Tokenind
Token ID521
Feature activation-1.03e-01

Pos logit contributions
igators+0.053
 wolves+0.052
eer+0.047
 bamboo+0.047
py+0.043
Neg logit contributions
ced-0.056
pen-0.053
 marker-0.050
-0.049
 pro-0.049
Tokeny
Token ID88
Feature activation-3.26e-02

Pos logit contributions
 wolves+0.222
igators+0.214
 bamboo+0.199
 choices+0.194
 dogs+0.183
Neg logit contributions
ced-0.148
pen-0.144
mine-0.137
 marker-0.119
 str-0.119
Token and
Token ID290
Feature activation+1.40e-03

Pos logit contributions
 wolves+0.061
igators+0.061
 bamboo+0.055
eer+0.054
py+0.051
Neg logit contributions
ced-0.056
pen-0.055
 marker-0.050
-0.049
 pro-0.048
Token Tim
Token ID5045
Feature activation+2.59e-02

Pos logit contributions
mine+0.002
pen+0.002
ced+0.002
 marker+0.002
 str+0.002
Neg logit contributions
 wolves-0.003
igators-0.002
eer-0.002
 bamboo-0.002
unn-0.002
Token were
Token ID547
Feature activation-2.86e-03

Pos logit contributions
ced+0.046
pen+0.046
 marker+0.042
mine+0.041
+0.040
Neg logit contributions
 wolves-0.047
igators-0.046
 bamboo-0.041
eer-0.040
py-0.037
Token good
Token ID922
Feature activation+3.14e-03

Pos logit contributions
igators+0.005
 wolves+0.005
eer+0.005
 bamboo+0.005
unn+0.004
Neg logit contributions
ced-0.005
pen-0.005
 marker-0.005
-0.005
 pro-0.005
Token playing
Token ID2712
Feature activation+5.57e-03

Pos logit contributions
ced+0.005
pen+0.005
 pro+0.005
 marker+0.004
 str+0.004
Neg logit contributions
 wolves-0.005
igators-0.005
eer-0.005
 bamboo-0.004
py-0.004
Token together
Token ID1978
Feature activation-1.74e-02

Pos logit contributions
ced+0.011
pen+0.010
+0.009
 marker+0.009
 pro+0.009
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.008
Token.
Token ID13
Feature activation-1.91e-02

Pos logit contributions
 wolves+0.028
igators+0.028
eer+0.025
 bamboo+0.024
py+0.023
Neg logit contributions
ced-0.035
pen-0.034
 marker-0.031
-0.031
 pro-0.030
Token<|endoftext|>
Token ID50256
Feature activation+1.55e-02

Pos logit contributions
 wolves+0.040
igators+0.039
eer+0.036
 bamboo+0.035
py+0.034
Neg logit contributions
-0.029
pen-0.028
ced-0.027
 pro-0.025
mine-0.024
TokenC
Token ID34
Feature activation-2.95e-02

Pos logit contributions
ced+0.031
pen+0.030
 marker+0.028
+0.028
 pro+0.027
Neg logit contributions
 wolves-0.024
igators-0.024
eer-0.021
 bamboo-0.021
py-0.019
Tokenind
Token ID521
Feature activation-1.01e-01

Pos logit contributions
igators+0.051
 wolves+0.049
eer+0.045
 bamboo+0.045
py+0.041
Neg logit contributions
ced-0.054
pen-0.052
 marker-0.050
-0.049
 pro-0.049
Tokeny
Token ID88
Feature activation-3.38e-02

Pos logit contributions
 wolves+0.215
igators+0.205
 bamboo+0.194
 choices+0.189
 hay+0.175
Neg logit contributions
ced-0.150
pen-0.145
mine-0.136
 str-0.117
 marker-0.116
Token wanted
Token ID2227
Feature activation-9.52e-03

Pos logit contributions
 wolves+0.062
igators+0.062
eer+0.055
 bamboo+0.055
py+0.051
Neg logit contributions
ced-0.060
pen-0.058
 marker-0.052
-0.052
 pro-0.051
Token to
Token ID284
Feature activation+1.65e-02

Pos logit contributions
 wolves+0.015
igators+0.014
eer+0.013
 bamboo+0.012
py+0.012
Neg logit contributions
ced-0.019
pen-0.019
 marker-0.018
 pro-0.017
 str-0.017
Token move
Token ID1445
Feature activation-3.95e-03

Pos logit contributions
ced+0.029
pen+0.029
 marker+0.026
+0.026
 pro+0.025
Neg logit contributions
 wolves-0.030
igators-0.030
eer-0.027
 bamboo-0.026
py-0.025
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
 wolves+0.007
igators+0.007
eer+0.006
unn+0.006
py+0.006
Neg logit contributions
ced-0.007
pen-0.007
 marker-0.007
mine-0.006
 pro-0.006
Token even
Token ID772
Feature activation-3.71e-02

Pos logit contributions
 wolves+0.002
igators+0.002
eer+0.002
 bamboo+0.002
py+0.002
Neg logit contributions
ced-0.003
pen-0.002
 marker-0.002
 pro-0.002
-0.002
Token better
Token ID1365
Feature activation-1.73e-03

Pos logit contributions
 wolves+0.064
igators+0.060
eer+0.057
 bamboo+0.055
unn+0.052
Neg logit contributions
ced-0.071
pen-0.066
 pro-0.064
 marker-0.063
 str-0.060
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
igators+0.003
 wolves+0.003
 bamboo+0.003
eer+0.003
unn+0.003
Neg logit contributions
ced-0.003
pen-0.003
 pro-0.003
 marker-0.003
-0.002
Token<|endoftext|>
Token ID50256
Feature activation+1.55e-02

Pos logit contributions
 wolves+0.032
igators+0.031
eer+0.028
 bamboo+0.027
py+0.027
Neg logit contributions
pen-0.026
-0.026
ced-0.023
 pro-0.023
 marker-0.021
TokenC
Token ID34
Feature activation-3.04e-02

Pos logit contributions
ced+0.032
pen+0.031
 marker+0.029
+0.028
 pro+0.028
Neg logit contributions
 wolves-0.024
igators-0.023
eer-0.021
 bamboo-0.020
py-0.019
Tokenind
Token ID521
Feature activation-1.00e-01

Pos logit contributions
igators+0.050
 wolves+0.050
eer+0.045
 bamboo+0.045
py+0.041
Neg logit contributions
ced-0.058
pen-0.055
 marker-0.052
-0.052
 pro-0.051
Tokeny
Token ID88
Feature activation-3.38e-02

Pos logit contributions
 wolves+0.219
igators+0.211
 bamboo+0.202
 choices+0.194
 Fif+0.184
Neg logit contributions
pen-0.136
ced-0.135
mine-0.127
 marker-0.108
 str-0.104
Token was
Token ID373
Feature activation-1.45e-02

Pos logit contributions
 wolves+0.064
igators+0.064
 bamboo+0.058
eer+0.057
py+0.054
Neg logit contributions
ced-0.058
pen-0.057
 marker-0.050
-0.049
 pro-0.049
Token a
Token ID257
Feature activation+1.03e-02

Pos logit contributions
 wolves+0.025
igators+0.025
eer+0.023
 bamboo+0.022
py+0.021
Neg logit contributions
ced-0.027
pen-0.026
 marker-0.024
-0.023
 pro-0.023
Token little
Token ID1310
Feature activation+1.47e-02

Pos logit contributions
ced+0.021
pen+0.021
 marker+0.019
+0.018
mine+0.018
Neg logit contributions
 wolves-0.016
igators-0.015
eer-0.014
 bamboo-0.014
 gorilla-0.013
Token girl
Token ID2576
Feature activation+1.33e-03

Pos logit contributions
ced+0.026
pen+0.026
 marker+0.024
 pro+0.024
+0.023
Neg logit contributions
igators-0.026
 wolves-0.025
eer-0.022
 bamboo-0.022
py-0.022
Token the
Token ID262
Feature activation+1.53e-02

Pos logit contributions
ced+0.021
pen+0.021
 pro+0.018
 str+0.018
 marker+0.018
Neg logit contributions
igators-0.022
 wolves-0.021
eer-0.020
unn-0.019
 bamboo-0.018
Token top
Token ID1353
Feature activation-7.92e-03

Pos logit contributions
ced+0.021
pen+0.020
 marker+0.018
 pro+0.018
+0.017
Neg logit contributions
igators-0.034
 wolves-0.033
eer-0.031
 bamboo-0.029
py-0.029
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
 wolves+0.012
igators+0.012
eer+0.011
 bamboo+0.011
py+0.010
Neg logit contributions
ced-0.016
pen-0.016
 marker-0.014
-0.014
 pro-0.014
Token From
Token ID3574
Feature activation-4.94e-02

Pos logit contributions
igators+0.018
 wolves+0.018
eer+0.016
 bamboo+0.015
py+0.015
Neg logit contributions
pen-0.025
-0.025
 marker-0.023
ced-0.023
 pro-0.023
Token the
Token ID262
Feature activation-1.79e-02

Pos logit contributions
 wolves+0.083
igators+0.080
eer+0.079
unn+0.069
py+0.069
Neg logit contributions
ced-0.097
pen-0.086
 pro-0.082
 marker-0.080
 str-0.079
Token very
Token ID845
Feature activation-9.89e-02

Pos logit contributions
igators+0.029
 wolves+0.029
eer+0.026
 bamboo+0.025
py+0.024
Neg logit contributions
ced-0.035
pen-0.034
 marker-0.032
-0.031
 pro-0.031
Token top
Token ID1353
Feature activation-4.14e-02

Pos logit contributions
 wolves+0.194
igators+0.188
eer+0.183
 bamboo+0.180
 dogs+0.167
Neg logit contributions
ced-0.155
 pro-0.133
pen-0.132
 tug-0.132
 marker-0.129
Token of
Token ID286
Feature activation-1.43e-02

Pos logit contributions
 wolves+0.073
igators+0.073
eer+0.066
 bamboo+0.064
py+0.059
Neg logit contributions
ced-0.077
pen-0.072
 pro-0.067
 marker-0.067
-0.064
Token the
Token ID262
Feature activation-5.86e-04

Pos logit contributions
igators+0.025
 wolves+0.024
eer+0.023
unn+0.023
 bamboo+0.021
Neg logit contributions
ced-0.028
pen-0.025
-0.024
 marker-0.024
 pro-0.023
Token pine
Token ID20161
Feature activation-3.18e-02

Pos logit contributions
 wolves+0.001
igators+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.001
pen-0.001
 marker-0.001
-0.001
 pro-0.001
Token tree
Token ID5509
Feature activation-3.05e-02

Pos logit contributions
igators+0.057
 wolves+0.056
eer+0.050
 bamboo+0.048
py+0.046
Neg logit contributions
ced-0.059
pen-0.057
-0.053
 pro-0.051
 marker-0.051
Token day
Token ID1110
Feature activation-1.88e-02

Pos logit contributions
 wolves+0.013
igators+0.013
eer+0.011
 bamboo+0.011
py+0.009
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.031
-0.031
 pro-0.030
Token on
Token ID319
Feature activation-1.88e-02

Pos logit contributions
igators+0.034
 wolves+0.033
eer+0.030
 bamboo+0.030
py+0.027
Neg logit contributions
ced-0.035
pen-0.034
-0.032
 marker-0.031
mine-0.030
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
igators+0.041
 wolves+0.040
eer+0.040
 habitats+0.036
 bamboo+0.036
Neg logit contributions
ced-0.026
-0.026
pen-0.024
 marker-0.023
mine-0.022
Token Lucy
Token ID22162
Feature activation-1.53e-02

Pos logit contributions
 wolves+0.016
eer+0.016
igators+0.016
py+0.014
unn+0.014
Neg logit contributions
ced-0.021
-0.020
pen-0.020
 pro-0.020
mine-0.019
Token took
Token ID1718
Feature activation-3.97e-02

Pos logit contributions
 wolves+0.022
igators+0.021
eer+0.020
py+0.018
 about+0.018
Neg logit contributions
ced-0.031
pen-0.030
-0.028
 marker-0.028
 widening-0.028
Token very
Token ID845
Feature activation-9.86e-02

Pos logit contributions
igators+0.069
 wolves+0.067
eer+0.061
 bamboo+0.059
py+0.056
Neg logit contributions
ced-0.077
pen-0.075
 marker-0.067
 pro-0.066
-0.064
Token good
Token ID922
Feature activation-1.65e-02

Pos logit contributions
 wolves+0.143
igators+0.142
 bamboo+0.123
eer+0.122
py+0.109
Neg logit contributions
ced-0.208
pen-0.206
-0.190
 marker-0.188
 pro-0.183
Token care
Token ID1337
Feature activation-2.11e-02

Pos logit contributions
 wolves+0.022
igators+0.020
eer+0.018
 bamboo+0.017
 dogs+0.017
Neg logit contributions
ced-0.037
pen-0.036
-0.034
 pro-0.034
 widened-0.034
Token of
Token ID286
Feature activation-1.21e-02

Pos logit contributions
 wolves+0.020
igators+0.019
eer+0.017
 about+0.015
 bamboo+0.015
Neg logit contributions
ced-0.054
pen-0.053
-0.051
 marker-0.050
 pro-0.049
Token her
Token ID607
Feature activation-3.35e-02

Pos logit contributions
 wolves+0.020
igators+0.020
eer+0.018
 bamboo+0.017
py+0.016
Neg logit contributions
ced-0.024
pen-0.023
 marker-0.022
-0.021
 pro-0.021
Token toy
Token ID13373
Feature activation-2.82e-02

Pos logit contributions
 wolves+0.041
igators+0.035
 choices+0.035
 dogs+0.035
eer+0.034
Neg logit contributions
pen-0.078
ced-0.076
mine-0.073
-0.070
 widened-0.070
Token relieved
Token ID22598
Feature activation+2.99e-04

Pos logit contributions
igators+0.036
 wolves+0.036
eer+0.033
 bamboo+0.031
py+0.031
Neg logit contributions
ced-0.028
pen-0.025
 pro-0.024
 widening-0.024
 widened-0.024
Token.
Token ID13
Feature activation-1.76e-02

Pos logit contributions
ced+0.000
pen+0.000
 pro+0.000
 marker+0.000
+0.000
Neg logit contributions
igators-0.001
 wolves-0.001
eer-0.001
unn-0.001
 bamboo-0.001
Token She
Token ID1375
Feature activation-2.88e-02

Pos logit contributions
igators+0.031
 wolves+0.031
eer+0.028
 bamboo+0.028
py+0.025
Neg logit contributions
pen-0.032
ced-0.031
-0.031
 pro-0.029
 marker-0.029
Token learned
Token ID4499
Feature activation-2.87e-02

Pos logit contributions
igators+0.057
 wolves+0.057
eer+0.051
 bamboo+0.050
py+0.047
Neg logit contributions
ced-0.048
pen-0.046
 marker-0.041
 pro-0.041
-0.040
Token a
Token ID257
Feature activation-1.49e-02

Pos logit contributions
igators+0.057
eer+0.054
 wolves+0.052
unn+0.046
py+0.046
Neg logit contributions
ced-0.046
pen-0.044
 marker-0.042
 str-0.041
 markers-0.040
Token very
Token ID845
Feature activation-9.69e-02

Pos logit contributions
igators+0.023
 wolves+0.023
eer+0.020
 bamboo+0.019
py+0.018
Neg logit contributions
ced-0.031
pen-0.029
 marker-0.028
 pro-0.028
-0.027
Token important
Token ID1593
Feature activation-2.46e-02

Pos logit contributions
igators+0.165
 wolves+0.164
eer+0.149
 bears+0.137
py+0.133
Neg logit contributions
ced-0.181
pen-0.162
pron-0.162
 pro-0.161
 marker-0.157
Token lesson
Token ID11483
Feature activation-3.88e-02

Pos logit contributions
igators+0.035
 wolves+0.035
 bamboo+0.029
eer+0.029
py+0.027
Neg logit contributions
ced-0.054
pen-0.052
 marker-0.049
-0.048
 pro-0.048
Token that
Token ID326
Feature activation-1.39e-02

Pos logit contributions
igators+0.069
 wolves+0.065
eer+0.061
 bamboo+0.057
unn+0.055
Neg logit contributions
ced-0.074
pen-0.069
hel-0.062
 pro-0.062
-0.060
Token day
Token ID1110
Feature activation-3.11e-03

Pos logit contributions
igators+0.018
 wolves+0.018
eer+0.015
 bamboo+0.015
py+0.013
Neg logit contributions
ced-0.032
pen-0.031
 marker-0.029
 pro-0.028
-0.028
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
igators+0.006
 wolves+0.005
eer+0.005
 bamboo+0.005
py+0.005
Neg logit contributions
ced-0.006
pen-0.006
-0.005
 marker-0.005
 pro-0.005
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
ced+0.070
pen+0.068
 marker+0.063
+0.062
 pro+0.061
Neg logit contributions
 wolves-0.054
igators-0.053
eer-0.047
 bamboo-0.045
py-0.042
Token
Token ID198
Feature activation-1.26e-02

Pos logit contributions
 wolves+0.028
igators+0.027
eer+0.025
 bamboo+0.025
py+0.023
Neg logit contributions
-0.021
pen-0.021
ced-0.020
 pro-0.019
 marker-0.019
Token
Token ID198
Feature activation-8.29e-03

Pos logit contributions
 wolves+0.021
igators+0.021
eer+0.018
 bamboo+0.018
py+0.017
Neg logit contributions
ced-0.025
pen-0.024
 marker-0.022
-0.022
 pro-0.021
TokenAfter
Token ID3260
Feature activation-2.52e-02

Pos logit contributions
 wolves+0.016
igators+0.016
 bamboo+0.014
eer+0.014
py+0.014
Neg logit contributions
ced-0.013
pen-0.013
 marker-0.012
-0.012
 pro-0.011
Token a
Token ID257
Feature activation-1.13e-02

Pos logit contributions
igators+0.050
eer+0.047
 wolves+0.047
unn+0.041
py+0.040
Neg logit contributions
ced-0.045
-0.041
pen-0.041
 marker-0.039
 pro-0.039
Token very
Token ID845
Feature activation-9.62e-02

Pos logit contributions
 wolves+0.022
igators+0.022
 bamboo+0.020
eer+0.020
 hay+0.019
Neg logit contributions
pen-0.018
ced-0.018
-0.015
 marker-0.015
mine-0.015
Token fun
Token ID1257
Feature activation-1.54e-02

Pos logit contributions
 wolves+0.209
igators+0.197
eer+0.192
py+0.185
 bamboo+0.185
Neg logit contributions
ced-0.141
 marker-0.122
 pro-0.120
pen-0.120
pron-0.117
Token day
Token ID1110
Feature activation-2.18e-03

Pos logit contributions
 wolves+0.025
igators+0.025
eer+0.023
 bamboo+0.021
py+0.021
Neg logit contributions
ced-0.030
pen-0.028
 marker-0.028
-0.028
 pro-0.026
Token,
Token ID11
Feature activation-4.76e-03

Pos logit contributions
igators+0.004
 wolves+0.004
eer+0.004
 bamboo+0.004
py+0.004
Neg logit contributions
ced-0.004
pen-0.004
-0.003
 pro-0.003
 marker-0.003
Token Sandy
Token ID17581
Feature activation-8.91e-03

Pos logit contributions
igators+0.008
 wolves+0.008
eer+0.007
 bamboo+0.007
py+0.006
Neg logit contributions
ced-0.010
pen-0.009
-0.009
 pro-0.008
 marker-0.008
Token and
Token ID290
Feature activation-8.80e-03

Pos logit contributions
 wolves+0.016
igators+0.016
eer+0.015
 bamboo+0.014
py+0.013
Neg logit contributions
ced-0.016
pen-0.015
 marker-0.014
-0.014
 pro-0.013
Token a
Token ID257
Feature activation+5.51e-03

Pos logit contributions
igators+0.047
 wolves+0.046
eer+0.043
 bamboo+0.041
py+0.040
Neg logit contributions
ced-0.049
pen-0.047
 marker-0.042
-0.041
 pro-0.041
Token bite
Token ID13197
Feature activation-2.06e-03

Pos logit contributions
ced+0.010
pen+0.010
mine+0.009
+0.009
 widened+0.009
Neg logit contributions
 wolves-0.010
igators-0.009
 bamboo-0.009
eer-0.009
 hay-0.008
Token!
Token ID0
Feature activation-1.52e-02

Pos logit contributions
 wolves+0.004
igators+0.003
eer+0.003
 bamboo+0.003
py+0.003
Neg logit contributions
pen-0.004
ced-0.004
 marker-0.003
-0.003
 pro-0.003
Token<|endoftext|>
Token ID50256
Feature activation+2.08e-02

Pos logit contributions
 wolves+0.029
igators+0.028
eer+0.026
 bamboo+0.025
py+0.024
Neg logit contributions
-0.027
pen-0.026
ced-0.025
mine-0.023
 pro-0.023
TokenC
Token ID34
Feature activation-2.56e-02

Pos logit contributions
ced+0.043
pen+0.041
 marker+0.038
+0.038
 pro+0.037
Neg logit contributions
 wolves-0.032
igators-0.032
eer-0.028
 bamboo-0.028
py-0.025
Tokenind
Token ID521
Feature activation-9.51e-02

Pos logit contributions
igators+0.042
 wolves+0.041
eer+0.037
 bamboo+0.037
py+0.034
Neg logit contributions
ced-0.049
pen-0.047
 marker-0.045
 pro-0.044
-0.044
Tokeny
Token ID88
Feature activation-2.91e-02

Pos logit contributions
 wolves+0.204
igators+0.198
 bamboo+0.185
 choices+0.177
 Fif+0.167
Neg logit contributions
ced-0.135
pen-0.134
mine-0.124
 marker-0.106
hel-0.104
Token and
Token ID290
Feature activation+3.46e-03

Pos logit contributions
 wolves+0.053
igators+0.053
 bamboo+0.047
eer+0.047
py+0.044
Neg logit contributions
ced-0.052
pen-0.051
 marker-0.045
-0.045
 pro-0.044
Token Peter
Token ID5613
Feature activation+1.58e-02

Pos logit contributions
mine+0.005
pen+0.005
ced+0.005
 marker+0.005
 str+0.005
Neg logit contributions
 wolves-0.007
igators-0.006
eer-0.006
 bamboo-0.006
unn-0.006
Token were
Token ID547
Feature activation-5.01e-03

Pos logit contributions
ced+0.023
pen+0.023
mine+0.020
 marker+0.020
 widened+0.019
Neg logit contributions
 wolves-0.034
igators-0.033
 bamboo-0.030
eer-0.029
 choices-0.028
Token playing
Token ID2712
Feature activation+1.59e-02

Pos logit contributions
igators+0.009
 wolves+0.009
eer+0.008
 bamboo+0.008
unn+0.007
Neg logit contributions
ced-0.009
pen-0.009
-0.008
 marker-0.008
 pro-0.008
Tokeny
Token ID88
Feature activation+9.05e-03

Pos logit contributions
ced+0.004
pen+0.004
mine+0.004
 marker+0.004
+0.004
Neg logit contributions
 wolves-0.007
igators-0.006
 bamboo-0.006
 gor-0.005
eer-0.005
Token again
Token ID757
Feature activation-2.41e-02

Pos logit contributions
ced+0.016
pen+0.015
 marker+0.014
 pro+0.014
+0.013
Neg logit contributions
 wolves-0.016
igators-0.016
eer-0.015
py-0.014
 bamboo-0.014
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
igators+0.044
 wolves+0.044
eer+0.040
 bamboo+0.038
py+0.036
Neg logit contributions
ced-0.045
pen-0.043
 marker-0.040
 pro-0.039
-0.039
Token She
Token ID1375
Feature activation-1.88e-02

Pos logit contributions
igators+0.022
 wolves+0.022
eer+0.021
 bamboo+0.019
py+0.019
Neg logit contributions
pen-0.018
-0.018
ced-0.017
 marker-0.016
 pro-0.016
Token worked
Token ID3111
Feature activation-1.27e-02

Pos logit contributions
 wolves+0.038
igators+0.038
eer+0.034
 bamboo+0.034
py+0.032
Neg logit contributions
ced-0.030
pen-0.029
 marker-0.026
 pro-0.026
 str-0.025
Token very
Token ID845
Feature activation-9.50e-02

Pos logit contributions
 wolves+0.017
igators+0.017
 bamboo+0.015
eer+0.014
 about+0.014
Neg logit contributions
pen-0.027
ced-0.027
 marker-0.025
-0.025
mine-0.024
Token hard
Token ID1327
Feature activation-1.75e-02

Pos logit contributions
 wolves+0.162
igators+0.159
eer+0.144
 bamboo+0.139
py+0.131
Neg logit contributions
ced-0.184
pen-0.176
-0.162
 marker-0.161
 pro-0.159
Token and
Token ID290
Feature activation-1.17e-02

Pos logit contributions
 wolves+0.028
igators+0.027
eer+0.024
 bamboo+0.024
py+0.022
Neg logit contributions
ced-0.036
pen-0.035
 marker-0.032
-0.032
 pro-0.031
Token soon
Token ID2582
Feature activation-2.18e-02

Pos logit contributions
 wolves+0.023
igators+0.023
eer+0.021
 bamboo+0.020
py+0.019
Neg logit contributions
ced-0.020
pen-0.019
 marker-0.017
 pro-0.017
-0.017
Token the
Token ID262
Feature activation+5.34e-04

Pos logit contributions
 wolves+0.036
igators+0.034
 bamboo+0.031
eer+0.030
 about+0.028
Neg logit contributions
ced-0.042
pen-0.041
 marker-0.038
-0.038
 widening-0.037
Token couch
Token ID18507
Feature activation-4.98e-03

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
+0.001
 pro+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 bamboo-0.001
py-0.001
Token Sue
Token ID26089
Feature activation-1.68e-02

Pos logit contributions
eer+0.018
 wolves+0.017
igators+0.016
ior+0.014
unn+0.014
Neg logit contributions
ced-0.025
 pro-0.023
pen-0.023
-0.023
 marker-0.021
Token and
Token ID290
Feature activation-9.81e-03

Pos logit contributions
 wolves+0.029
igators+0.029
eer+0.026
 bamboo+0.025
py+0.023
Neg logit contributions
ced-0.031
pen-0.030
 marker-0.028
-0.028
 pro-0.027
Token Carl
Token ID8124
Feature activation-1.24e-03

Pos logit contributions
 wolves+0.014
igators+0.014
eer+0.014
 bamboo+0.012
unn+0.012
Neg logit contributions
ced-0.019
pen-0.018
mine-0.017
 marker-0.017
 pro-0.017
Token learned
Token ID4499
Feature activation-3.00e-02

Pos logit contributions
igators+0.002
 wolves+0.002
eer+0.002
 bamboo+0.002
py+0.002
Neg logit contributions
ced-0.002
pen-0.002
-0.002
 marker-0.002
 widening-0.002
Token a
Token ID257
Feature activation-1.21e-02

Pos logit contributions
eer+0.055
igators+0.055
 wolves+0.051
unn+0.048
py+0.047
Neg logit contributions
ced-0.052
pen-0.048
 pro-0.047
 str-0.046
 marker-0.046
Token very
Token ID845
Feature activation-9.49e-02

Pos logit contributions
 wolves+0.017
igators+0.016
 bamboo+0.014
eer+0.014
py+0.013
Neg logit contributions
ced-0.027
pen-0.027
 marker-0.024
-0.024
mine-0.024
Token important
Token ID1593
Feature activation-1.98e-02

Pos logit contributions
 wolves+0.169
igators+0.165
eer+0.157
ior+0.140
py+0.139
Neg logit contributions
ced-0.163
 pro-0.148
pen-0.145
 marker-0.141
-0.137
Token lesson
Token ID11483
Feature activation-3.82e-02

Pos logit contributions
 wolves+0.021
igators+0.020
eer+0.017
 bamboo+0.016
py+0.014
Neg logit contributions
ced-0.051
pen-0.050
-0.046
 marker-0.046
 widened-0.046
Token:
Token ID25
Feature activation-1.01e-02

Pos logit contributions
igators+0.066
eer+0.061
 wolves+0.061
 bamboo+0.057
unn+0.055
Neg logit contributions
ced-0.073
pen-0.066
 pro-0.060
hel-0.059
 marker-0.057
Token it
Token ID340
Feature activation-1.53e-02

Pos logit contributions
igators+0.017
 wolves+0.017
eer+0.016
 bamboo+0.015
 gorilla+0.013
Neg logit contributions
ced-0.019
pen-0.019
 pro-0.017
 marker-0.017
-0.017
Token's
Token ID338
Feature activation-1.22e-02

Pos logit contributions
 wolves+0.030
igators+0.030
eer+0.027
 bamboo+0.027
py+0.025
Neg logit contributions
ced-0.025
pen-0.024
 marker-0.022
-0.021
 pro-0.021
Token idea
Token ID2126
Feature activation-6.99e-03

Pos logit contributions
 wolves+0.010
igators+0.010
eer+0.009
 bamboo+0.009
py+0.009
Neg logit contributions
ced-0.010
pen-0.010
-0.009
 marker-0.009
 pro-0.009
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
 wolves+0.012
igators+0.012
eer+0.011
 bamboo+0.010
py+0.010
Neg logit contributions
ced-0.013
pen-0.013
 marker-0.012
-0.011
 pro-0.011
Token He
Token ID679
Feature activation-2.32e-02

Pos logit contributions
 wolves+0.020
igators+0.020
 bamboo+0.018
eer+0.018
py+0.016
Neg logit contributions
pen-0.036
ced-0.035
 marker-0.034
-0.034
 pro-0.033
Token took
Token ID1718
Feature activation-3.59e-02

Pos logit contributions
 wolves+0.046
igators+0.045
 bamboo+0.041
eer+0.041
py+0.038
Neg logit contributions
ced-0.038
pen-0.036
 marker-0.033
 pro-0.032
 str-0.031
Token a
Token ID257
Feature activation-8.61e-03

Pos logit contributions
 wolves+0.059
igators+0.059
eer+0.053
 bamboo+0.052
unn+0.048
Neg logit contributions
ced-0.071
pen-0.068
 marker-0.063
 pro-0.061
-0.060
Token really
Token ID1107
Feature activation-9.46e-02

Pos logit contributions
igators+0.014
 wolves+0.014
 bamboo+0.012
eer+0.012
 hay+0.012
Neg logit contributions
ced-0.017
pen-0.016
-0.015
mine-0.015
 widened-0.015
Token big
Token ID1263
Feature activation-5.15e-03

Pos logit contributions
 wolves+0.198
igators+0.191
eer+0.180
 bamboo+0.174
py+0.170
Neg logit contributions
ced-0.146
pen-0.133
 marker-0.130
-0.121
 pro-0.120
Token stick
Token ID4859
Feature activation-5.37e-03

Pos logit contributions
 wolves+0.010
igators+0.010
 bamboo+0.009
eer+0.009
 hay+0.008
Neg logit contributions
ced-0.009
pen-0.008
-0.007
 widened-0.007
 widening-0.007
Token and
Token ID290
Feature activation+5.56e-03

Pos logit contributions
 wolves+0.008
igators+0.008
eer+0.007
 bamboo+0.007
py+0.006
Neg logit contributions
ced-0.011
pen-0.011
-0.010
 marker-0.010
 pro-0.010
Token started
Token ID2067
Feature activation-2.05e-02

Pos logit contributions
ced+0.009
pen+0.008
+0.007
 marker+0.007
 pro+0.007
Neg logit contributions
 wolves-0.011
igators-0.011
eer-0.010
 bamboo-0.010
py-0.010
Token to
Token ID284
Feature activation+1.71e-02

Pos logit contributions
 wolves+0.027
igators+0.026
 bamboo+0.022
eer+0.022
 dogs+0.020
Neg logit contributions
ced-0.046
pen-0.045
-0.042
 marker-0.041
mine-0.041
Token pan
Token ID3425
Feature activation-2.27e-02

Pos logit contributions
 wolves+0.079
igators+0.078
eer+0.070
 bamboo+0.069
py+0.064
Neg logit contributions
ced-0.087
pen-0.085
 marker-0.077
-0.077
 pro-0.075
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
 wolves+0.040
igators+0.039
eer+0.035
 bamboo+0.035
py+0.032
Neg logit contributions
ced-0.042
pen-0.041
 marker-0.038
-0.038
 pro-0.037
Token She
Token ID1375
Feature activation-2.74e-02

Pos logit contributions
 wolves+0.027
igators+0.027
eer+0.025
 bamboo+0.024
py+0.022
Neg logit contributions
-0.029
pen-0.028
ced-0.027
 pro-0.025
 marker-0.025
Token learned
Token ID4499
Feature activation-2.43e-02

Pos logit contributions
 wolves+0.053
igators+0.052
eer+0.047
 bamboo+0.046
py+0.044
Neg logit contributions
ced-0.046
pen-0.045
 marker-0.040
-0.040
 pro-0.039
Token a
Token ID257
Feature activation-1.37e-02

Pos logit contributions
igators+0.037
 wolves+0.035
eer+0.035
 bamboo+0.029
py+0.029
Neg logit contributions
ced-0.052
pen-0.050
 marker-0.047
 pro-0.046
-0.045
Token very
Token ID845
Feature activation-9.39e-02

Pos logit contributions
 wolves+0.018
igators+0.017
 bamboo+0.015
eer+0.014
 about+0.014
Neg logit contributions
pen-0.031
ced-0.031
-0.028
mine-0.028
 marker-0.027
Token important
Token ID1593
Feature activation-2.42e-02

Pos logit contributions
 wolves+0.145
igators+0.141
eer+0.130
 bamboo+0.117
py+0.116
Neg logit contributions
ced-0.199
pen-0.185
 pro-0.179
-0.177
 marker-0.177
Token lesson
Token ID11483
Feature activation-3.98e-02

Pos logit contributions
 wolves+0.027
igators+0.026
eer+0.022
 bamboo+0.021
py+0.018
Neg logit contributions
ced-0.060
pen-0.059
-0.054
 marker-0.054
 widened-0.053
Token that
Token ID326
Feature activation-1.52e-02

Pos logit contributions
igators+0.071
 wolves+0.067
eer+0.064
 bamboo+0.060
py+0.056
Neg logit contributions
ced-0.077
pen-0.071
 pro-0.065
-0.063
hel-0.063
Token day
Token ID1110
Feature activation-3.25e-03

Pos logit contributions
 wolves+0.017
igators+0.016
eer+0.014
 bamboo+0.013
py+0.012
Neg logit contributions
ced-0.038
pen-0.038
-0.035
 marker-0.035
 pro-0.034
Token:
Token ID25
Feature activation+2.44e-03

Pos logit contributions
igators+0.006
 wolves+0.006
eer+0.005
 bamboo+0.005
py+0.005
Neg logit contributions
ced-0.006
pen-0.006
-0.005
 marker-0.005
 pro-0.005
Token the
Token ID262
Feature activation+2.02e-02

Pos logit contributions
igators+0.051
 wolves+0.049
eer+0.046
unn+0.042
 bamboo+0.041
Neg logit contributions
ced-0.058
pen-0.055
 marker-0.050
 pro-0.050
-0.050
Token parade
Token ID16134
Feature activation+7.77e-03

Pos logit contributions
ced+0.038
pen+0.037
 marker+0.034
+0.034
 pro+0.033
Neg logit contributions
 wolves-0.034
igators-0.034
eer-0.031
 bamboo-0.030
py-0.028
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
ced+0.015
pen+0.014
 marker+0.013
 pro+0.013
+0.013
Neg logit contributions
 wolves-0.013
igators-0.013
 bamboo-0.012
eer-0.011
py-0.011
Token He
Token ID679
Feature activation-1.38e-02

Pos logit contributions
 wolves+0.033
igators+0.032
eer+0.030
 bamboo+0.028
 choices+0.027
Neg logit contributions
pen-0.030
-0.030
ced-0.028
 pro-0.028
mine-0.027
Token worked
Token ID3111
Feature activation-1.77e-02

Pos logit contributions
 wolves+0.027
igators+0.027
 bamboo+0.024
eer+0.024
py+0.023
Neg logit contributions
ced-0.022
pen-0.022
 pro-0.019
 marker-0.019
-0.019
Token very
Token ID845
Feature activation-9.37e-02

Pos logit contributions
 wolves+0.024
igators+0.024
 bamboo+0.021
eer+0.020
 about+0.020
Neg logit contributions
pen-0.038
ced-0.038
 marker-0.035
-0.035
mine-0.034
Token hard
Token ID1327
Feature activation-1.62e-02

Pos logit contributions
 wolves+0.150
igators+0.148
eer+0.132
 bamboo+0.129
py+0.119
Neg logit contributions
ced-0.189
pen-0.183
 marker-0.168
-0.167
 pro-0.164
Token on
Token ID319
Feature activation-1.14e-02

Pos logit contributions
 wolves+0.026
igators+0.026
eer+0.023
 bamboo+0.023
py+0.021
Neg logit contributions
ced-0.032
pen-0.031
 marker-0.029
-0.029
 pro-0.028
Token it
Token ID340
Feature activation-2.75e-02

Pos logit contributions
igators+0.017
 wolves+0.017
eer+0.015
 bamboo+0.014
unn+0.014
Neg logit contributions
ced-0.024
pen-0.024
 marker-0.022
 pro-0.021
-0.021
Token,
Token ID11
Feature activation+2.87e-02

Pos logit contributions
 wolves+0.047
igators+0.047
eer+0.042
 bamboo+0.041
py+0.038
Neg logit contributions
ced-0.053
pen-0.051
 marker-0.047
-0.046
 pro-0.046
Token making
Token ID1642
Feature activation-4.92e-03

Pos logit contributions
ced+0.054
pen+0.052
+0.048
 marker+0.047
mine+0.045
Neg logit contributions
 wolves-0.049
igators-0.048
eer-0.043
 bamboo-0.042
 dogs-0.039
Token glad
Token ID9675
Feature activation+4.43e-03

Pos logit contributions
 wolves+0.033
igators+0.031
eer+0.029
 bamboo+0.028
py+0.027
Neg logit contributions
ced-0.031
pen-0.029
-0.027
 pro-0.027
 marker-0.027
Token we
Token ID356
Feature activation+1.92e-02

Pos logit contributions
ced+0.006
 pro+0.006
 str+0.006
pen+0.005
 marker+0.005
Neg logit contributions
igators-0.009
eer-0.009
 wolves-0.009
py-0.008
 bamboo-0.008
Token got
Token ID1392
Feature activation-1.81e-02

Pos logit contributions
ced+0.031
pen+0.030
+0.028
 marker+0.027
 widening+0.026
Neg logit contributions
igators-0.037
 wolves-0.037
eer-0.034
 bamboo-0.032
py-0.031
Token<|endoftext|>
Token ID50256
Feature activation+1.96e-02

Pos logit contributions
 wolves+0.033
igators+0.032
eer+0.031
py+0.029
 bamboo+0.029
Neg logit contributions
ced-0.032
pen-0.031
 marker-0.029
 pro-0.029
 str-0.027
TokenC
Token ID34
Feature activation-1.85e-02

Pos logit contributions
ced+0.041
pen+0.040
 marker+0.037
+0.036
 pro+0.036
Neg logit contributions
 wolves-0.030
igators-0.029
eer-0.026
 bamboo-0.025
py-0.023
Tokenind
Token ID521
Feature activation-9.37e-02

Pos logit contributions
igators+0.032
 wolves+0.032
eer+0.029
 bamboo+0.028
py+0.026
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.031
-0.030
 pro-0.030
Tokeny
Token ID88
Feature activation-2.23e-02

Pos logit contributions
 wolves+0.208
igators+0.202
 bamboo+0.192
 choices+0.178
 hay+0.171
Neg logit contributions
ced-0.125
pen-0.122
mine-0.119
 str-0.098
 marker-0.097
Token was
Token ID373
Feature activation-1.34e-02

Pos logit contributions
 wolves+0.041
igators+0.041
eer+0.037
 bamboo+0.036
py+0.034
Neg logit contributions
ced-0.040
pen-0.039
-0.035
 marker-0.035
 pro-0.034
Token a
Token ID257
Feature activation+1.07e-02

Pos logit contributions
 wolves+0.022
igators+0.022
eer+0.020
 bamboo+0.019
py+0.018
Neg logit contributions
ced-0.026
pen-0.026
-0.023
 marker-0.023
 pro-0.023
Token cheerful
Token ID37999
Feature activation+7.63e-03

Pos logit contributions
ced+0.021
pen+0.021
 marker+0.018
+0.018
 widening+0.018
Neg logit contributions
 wolves-0.018
igators-0.017
eer-0.015
 bamboo-0.015
 gorilla-0.014
Token girl
Token ID2576
Feature activation+4.05e-03

Pos logit contributions
ced+0.012
pen+0.012
 marker+0.012
 pro+0.011
+0.011
Neg logit contributions
igators-0.014
 wolves-0.014
 bamboo-0.013
eer-0.013
py-0.012
Token sad
Token ID6507
Feature activation-5.27e-03

Pos logit contributions
igators+0.011
 wolves+0.011
eer+0.011
unn+0.011
 bamboo+0.010
Neg logit contributions
ced-0.008
 pro-0.007
pen-0.007
 tug-0.007
 widened-0.006
Token.
Token ID13
Feature activation-1.33e-02

Pos logit contributions
igators+0.012
 wolves+0.011
eer+0.010
 bamboo+0.010
py+0.009
Neg logit contributions
ced-0.008
pen-0.007
 pro-0.007
 marker-0.006
 widened-0.006
Token He
Token ID679
Feature activation-2.33e-02

Pos logit contributions
igators+0.023
 wolves+0.022
eer+0.021
 bamboo+0.020
py+0.019
Neg logit contributions
-0.024
pen-0.024
 pro-0.023
ced-0.022
 Exc-0.022
Token learned
Token ID4499
Feature activation-2.67e-02

Pos logit contributions
igators+0.052
 wolves+0.051
eer+0.047
 bamboo+0.046
unn+0.045
Neg logit contributions
ced-0.033
pen-0.030
 pro-0.029
 str-0.028
 widened-0.028
Token a
Token ID257
Feature activation-1.35e-02

Pos logit contributions
igators+0.055
eer+0.052
 wolves+0.049
unn+0.047
eers+0.044
Neg logit contributions
ced-0.039
pen-0.037
 str-0.036
 marker-0.035
T-0.033
Token very
Token ID845
Feature activation-9.36e-02

Pos logit contributions
igators+0.022
 wolves+0.021
eer+0.019
 bamboo+0.018
py+0.017
Neg logit contributions
ced-0.027
pen-0.025
 marker-0.025
 pro-0.025
 str-0.023
Token important
Token ID1593
Feature activation-2.40e-02

Pos logit contributions
igators+0.156
 wolves+0.156
eer+0.141
 bears+0.132
 bamboo+0.127
Neg logit contributions
ced-0.175
 pro-0.156
pen-0.152
pron-0.152
 marker-0.151
Token lesson
Token ID11483
Feature activation-3.71e-02

Pos logit contributions
igators+0.035
 wolves+0.034
eer+0.030
 bamboo+0.029
py+0.027
Neg logit contributions
ced-0.052
pen-0.049
 marker-0.048
-0.047
 pro-0.046
Token that
Token ID326
Feature activation-1.78e-02

Pos logit contributions
igators+0.069
 wolves+0.064
eer+0.059
 bamboo+0.057
unn+0.057
Neg logit contributions
ced-0.068
pen-0.064
hel-0.055
 pro-0.055
 marker-0.053
Token day
Token ID1110
Feature activation-2.05e-03

Pos logit contributions
igators+0.024
 wolves+0.024
eer+0.021
 bamboo+0.021
unn+0.019
Neg logit contributions
ced-0.039
pen-0.038
 marker-0.037
 pro-0.035
 str-0.034
Token -
Token ID532
Feature activation-5.11e-03

Pos logit contributions
igators+0.004
 wolves+0.004
eer+0.003
 bamboo+0.003
unn+0.003
Neg logit contributions
ced-0.004
pen-0.004
-0.003
 marker-0.003
 pro-0.003
Token
Token ID198
Feature activation-7.59e-03

Pos logit contributions
 wolves+0.016
igators+0.016
eer+0.014
 bamboo+0.014
py+0.013
Neg logit contributions
ced-0.020
pen-0.019
 marker-0.018
-0.017
 pro-0.017
TokenThe
Token ID464
Feature activation-2.12e-02

Pos logit contributions
igators+0.014
 wolves+0.014
 bamboo+0.012
eer+0.012
 hay+0.012
Neg logit contributions
ced-0.012
pen-0.012
 marker-0.011
-0.011
 pro-0.011
Token baby
Token ID5156
Feature activation-3.43e-02

Pos logit contributions
igators+0.038
 wolves+0.037
eer+0.034
 bamboo+0.033
py+0.031
Neg logit contributions
ced-0.038
pen-0.036
 marker-0.035
-0.034
 pro-0.033
Token learned
Token ID4499
Feature activation-2.60e-02

Pos logit contributions
igators+0.070
 wolves+0.067
 bamboo+0.063
eer+0.060
py+0.057
Neg logit contributions
ced-0.056
pen-0.052
 marker-0.047
 pro-0.047
 str-0.045
Token a
Token ID257
Feature activation-1.53e-02

Pos logit contributions
igators+0.055
eer+0.055
 wolves+0.049
unn+0.048
eers+0.046
Neg logit contributions
ced-0.039
pen-0.035
 str-0.035
 marker-0.033
 pro-0.033
Token very
Token ID845
Feature activation-9.36e-02

Pos logit contributions
igators+0.021
 wolves+0.021
eer+0.019
 bamboo+0.018
py+0.016
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.031
 pro-0.030
-0.030
Token important
Token ID1593
Feature activation-2.49e-02

Pos logit contributions
igators+0.161
 wolves+0.158
eer+0.148
 bears+0.133
py+0.132
Neg logit contributions
ced-0.176
 pro-0.154
pen-0.154
 marker-0.149
-0.148
Token lesson
Token ID11483
Feature activation-4.16e-02

Pos logit contributions
igators+0.037
 wolves+0.036
eer+0.032
 bamboo+0.031
py+0.029
Neg logit contributions
ced-0.053
pen-0.050
 marker-0.048
-0.047
 pro-0.047
Token that
Token ID326
Feature activation-1.57e-02

Pos logit contributions
igators+0.075
 wolves+0.069
eer+0.069
 bamboo+0.063
unn+0.063
Neg logit contributions
ced-0.076
pen-0.069
 pro-0.062
hel-0.062
 marker-0.059
Token day
Token ID1110
Feature activation-8.26e-03

Pos logit contributions
 wolves+0.018
igators+0.017
eer+0.015
 bamboo+0.014
py+0.013
Neg logit contributions
ced-0.039
pen-0.038
 marker-0.036
 pro-0.035
-0.035
Token -
Token ID532
Feature activation-6.42e-03

Pos logit contributions
igators+0.015
 wolves+0.014
eer+0.013
 bamboo+0.013
py+0.012
Neg logit contributions
ced-0.016
pen-0.015
-0.014
 marker-0.014
 pro-0.013
Token building
Token ID2615
Feature activation-1.45e-02

Pos logit contributions
igators+0.059
 wolves+0.058
eer+0.052
 bamboo+0.050
py+0.049
Neg logit contributions
ced-0.063
pen-0.061
 marker-0.058
-0.056
 pro-0.054
Token blocks
Token ID7021
Feature activation-5.14e-04

Pos logit contributions
 wolves+0.025
igators+0.024
eer+0.023
 bamboo+0.022
unn+0.021
Neg logit contributions
ced-0.027
pen-0.026
 marker-0.025
-0.024
 pro-0.024
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
 wolves+0.001
igators+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.001
pen-0.001
 marker-0.001
-0.001
 pro-0.001
Token She
Token ID1375
Feature activation-1.37e-02

Pos logit contributions
 wolves+0.030
igators+0.030
eer+0.028
 bamboo+0.026
 choices+0.025
Neg logit contributions
pen-0.030
-0.030
ced-0.029
 marker-0.028
 pro-0.028
Token worked
Token ID3111
Feature activation-1.42e-02

Pos logit contributions
 wolves+0.027
igators+0.026
eer+0.024
 bamboo+0.024
py+0.022
Neg logit contributions
ced-0.023
pen-0.022
 marker-0.020
 pro-0.020
-0.019
Token very
Token ID845
Feature activation-9.31e-02

Pos logit contributions
 wolves+0.016
igators+0.015
 about+0.015
 for+0.014
 bamboo+0.013
Neg logit contributions
pen-0.033
ced-0.032
-0.031
 marker-0.030
mine-0.030
Token hard
Token ID1327
Feature activation-1.58e-02

Pos logit contributions
 wolves+0.139
igators+0.138
eer+0.120
 bamboo+0.119
py+0.108
Neg logit contributions
ced-0.195
pen-0.192
 marker-0.176
-0.175
 pro-0.170
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
 wolves+0.024
igators+0.023
eer+0.020
 bamboo+0.020
py+0.018
Neg logit contributions
ced-0.033
pen-0.032
 marker-0.030
-0.030
 pro-0.029
Token soon
Token ID2582
Feature activation-2.56e-02

Pos logit contributions
 wolves+0.021
igators+0.021
 bamboo+0.018
eer+0.018
 about+0.017
Neg logit contributions
pen-0.020
ced-0.020
-0.018
 marker-0.018
mine-0.017
Token her
Token ID607
Feature activation-4.65e-02

Pos logit contributions
 wolves+0.047
igators+0.046
 bamboo+0.041
eer+0.041
py+0.038
Neg logit contributions
ced-0.045
pen-0.044
-0.040
 marker-0.040
 widening-0.038
Token palace
Token ID20562
Feature activation-3.64e-02

Pos logit contributions
 wolves+0.085
igators+0.084
eer+0.076
 bamboo+0.075
py+0.070
Neg logit contributions
ced-0.082
pen-0.079
 marker-0.074
-0.073
 pro-0.071
Token was
Token ID373
Feature activation-1.55e-02

Pos logit contributions
ced+0.058
pen+0.058
 marker+0.054
 widening+0.053
+0.053
Neg logit contributions
 wolves-0.044
igators-0.043
 bamboo-0.040
 about-0.038
eer-0.038
Token a
Token ID257
Feature activation+1.39e-02

Pos logit contributions
 wolves+0.023
igators+0.022
 bamboo+0.020
eer+0.019
 hay+0.018
Neg logit contributions
ced-0.034
pen-0.033
 marker-0.030
 pro-0.030
-0.030
Token human
Token ID1692
Feature activation-1.33e-02

Pos logit contributions
ced+0.029
pen+0.028
+0.025
mine+0.025
 marker+0.025
Neg logit contributions
 wolves-0.022
igators-0.020
 bamboo-0.019
eer-0.019
 gorilla-0.018
Token who
Token ID508
Feature activation-9.33e-03

Pos logit contributions
igators+0.020
 wolves+0.019
unn+0.017
 choices+0.017
eer+0.016
Neg logit contributions
pen-0.027
ced-0.026
 marker-0.025
 pro-0.024
 str-0.024
Token took
Token ID1718
Feature activation-2.31e-02

Pos logit contributions
 wolves+0.018
igators+0.018
 bamboo+0.016
unn+0.016
eer+0.015
Neg logit contributions
ced-0.015
pen-0.015
 marker-0.013
 widened-0.013
-0.013
Token very
Token ID845
Feature activation-9.31e-02

Pos logit contributions
igators+0.045
 wolves+0.039
loo+0.038
eer+0.038
py+0.037
Neg logit contributions
pen-0.038
ced-0.037
 marker-0.033
 markers-0.031
 str-0.030
Token good
Token ID922
Feature activation-1.69e-02

Pos logit contributions
 wolves+0.186
igators+0.181
eer+0.170
 bamboo+0.163
py+0.162
Neg logit contributions
ced-0.146
pen-0.137
 marker-0.126
-0.121
 str-0.118
Token care
Token ID1337
Feature activation-2.66e-02

Pos logit contributions
igators+0.033
 wolves+0.027
 bamboo+0.026
py+0.025
 Fif+0.024
Neg logit contributions
pen-0.029
ced-0.028
 marker-0.027
 str-0.025
 markers-0.024
Token of
Token ID286
Feature activation-9.03e-03

Pos logit contributions
 wolves+0.038
igators+0.038
 bamboo+0.032
eer+0.031
py+0.028
Neg logit contributions
ced-0.058
pen-0.057
 marker-0.052
-0.050
 pro-0.050
Token their
Token ID511
Feature activation-2.36e-02

Pos logit contributions
igators+0.017
unn+0.016
 wolves+0.015
eer+0.015
py+0.014
Neg logit contributions
ced-0.016
pen-0.015
 marker-0.014
 str-0.013
 markers-0.012
Token things
Token ID1243
Feature activation-7.76e-03

Pos logit contributions
igators+0.038
 wolves+0.034
py+0.032
eer+0.031
 bamboo+0.030
Neg logit contributions
ced-0.046
pen-0.045
 marker-0.044
-0.041
 markers-0.040
Token He
Token ID679
Feature activation-7.01e-03

Pos logit contributions
 wolves+0.008
igators+0.008
eer+0.007
 bamboo+0.007
py+0.007
Neg logit contributions
ced-0.009
pen-0.009
-0.009
 marker-0.009
 pro-0.008
Token asked
Token ID1965
Feature activation-1.97e-02

Pos logit contributions
 wolves+0.014
igators+0.014
eer+0.012
 bamboo+0.012
py+0.011
Neg logit contributions
ced-0.011
pen-0.011
-0.010
 marker-0.010
 widening-0.010
Token her
Token ID607
Feature activation-4.38e-02

Pos logit contributions
igators+0.038
 wolves+0.035
eer+0.033
unn+0.033
py+0.031
Neg logit contributions
ced-0.035
pen-0.033
mine-0.031
 marker-0.031
 pro-0.030
Token if
Token ID611
Feature activation-1.39e-02

Pos logit contributions
igators+0.078
 wolves+0.077
eer+0.072
 bamboo+0.067
py+0.065
Neg logit contributions
ced-0.080
pen-0.078
 marker-0.077
 pro-0.074
 markers-0.070
Token he
Token ID339
Feature activation-3.42e-03

Pos logit contributions
igators+0.027
 wolves+0.026
eer+0.024
 bamboo+0.023
py+0.023
Neg logit contributions
ced-0.023
pen-0.023
 marker-0.021
-0.020
 pro-0.020
Token could
Token ID714
Feature activation+5.28e-02

Pos logit contributions
 wolves+0.007
igators+0.007
eer+0.006
 bamboo+0.006
py+0.006
Neg logit contributions
ced-0.005
pen-0.005
 marker-0.004
-0.004
 pro-0.004
Token use
Token ID779
Feature activation-1.18e-02

Pos logit contributions
ced+0.085
pen+0.085
+0.078
 marker+0.078
 pro+0.073
Neg logit contributions
 wolves-0.105
igators-0.103
eer-0.094
 bamboo-0.092
py-0.087
Token the
Token ID262
Feature activation+1.09e-02

Pos logit contributions
 wolves+0.020
igators+0.020
eer+0.019
 bamboo+0.017
py+0.017
Neg logit contributions
ced-0.022
pen-0.021
 marker-0.020
-0.020
 pro-0.019
Token knife
Token ID9845
Feature activation-5.19e-03

Pos logit contributions
ced+0.016
pen+0.016
+0.014
 pro+0.014
 widened+0.013
Neg logit contributions
 wolves-0.023
igators-0.022
eer-0.021
 bamboo-0.020
 hay-0.020
Token too
Token ID1165
Feature activation-3.28e-02

Pos logit contributions
 wolves+0.009
igators+0.008
eer+0.007
 bamboo+0.007
 gor+0.007
Neg logit contributions
ced-0.010
pen-0.010
 marker-0.009
 pro-0.009
-0.009
Token.
Token ID13
Feature activation-3.68e-03

Pos logit contributions
 wolves+0.058
igators+0.058
eer+0.053
 bamboo+0.050
py+0.049
Neg logit contributions
ced-0.061
pen-0.059
-0.054
 marker-0.053
 pro-0.053
Token with
Token ID351
Feature activation+3.30e-03

Pos logit contributions
 wolves+0.000
igators+0.000
 bamboo+0.000
eer+0.000
 about+0.000
Neg logit contributions
ced-0.000
pen-0.000
-0.000
 marker-0.000
 widening-0.000
Token all
Token ID477
Feature activation-4.18e-02

Pos logit contributions
pen+0.008
pron+0.008
ced+0.008
+0.008
 pro+0.007
Neg logit contributions
 wolves-0.003
igators-0.003
 hay-0.003
 Rex-0.003
 about-0.003
Token her
Token ID607
Feature activation-2.42e-02

Pos logit contributions
igators+0.056
 wolves+0.055
eer+0.045
 bamboo+0.045
py+0.042
Neg logit contributions
ced-0.095
pen-0.094
-0.089
 marker-0.086
 pro-0.085
Token might
Token ID1244
Feature activation+2.81e-02

Pos logit contributions
 wolves+0.037
igators+0.033
 dogs+0.033
 bamboo+0.032
 about+0.032
Neg logit contributions
pen-0.046
ced-0.043
mine-0.042
 widening-0.042
-0.042
Token and
Token ID290
Feature activation+2.34e-02

Pos logit contributions
pen+0.063
ced+0.062
pron+0.061
+0.060
 marker+0.059
Neg logit contributions
 wolves-0.031
 about-0.030
 for-0.028
igators-0.026
 bamboo-0.025
Token,
Token ID11
Feature activation+4.19e-02

Pos logit contributions
pen+0.038
ced+0.038
+0.035
 marker+0.034
mine+0.033
Neg logit contributions
 wolves-0.045
igators-0.043
 bamboo-0.039
eer-0.038
 about-0.037
Token after
Token ID706
Feature activation-1.70e-02

Pos logit contributions
pen+0.077
ced+0.076
+0.072
 marker+0.069
mine+0.066
Neg logit contributions
 wolves-0.070
igators-0.064
 about-0.059
 bamboo-0.059
eer-0.057
Token some
Token ID617
Feature activation-2.63e-02

Pos logit contributions
 wolves+0.028
igators+0.028
eer+0.025
 bamboo+0.024
py+0.022
Neg logit contributions
ced-0.033
pen-0.032
 marker-0.030
-0.030
 pro-0.029
Token effort
Token ID3626
Feature activation-3.83e-03

Pos logit contributions
 wolves+0.043
igators+0.040
 bamboo+0.036
eer+0.035
 dogs+0.034
Neg logit contributions
pen-0.051
ced-0.050
 marker-0.047
-0.046
mine-0.046
Token,
Token ID11
Feature activation+1.47e-02

Pos logit contributions
 wolves+0.006
igators+0.005
 bamboo+0.005
 about+0.005
eer+0.004
Neg logit contributions
pen-0.008
ced-0.008
-0.007
 marker-0.007
mine-0.007
Token the
Token ID262
Feature activation-5.00e-03

Pos logit contributions
pen+0.028
ced+0.027
+0.025
mine+0.024
 marker+0.024
Neg logit contributions
 wolves-0.025
igators-0.023
 dogs-0.021
 bamboo-0.021
 about-0.020
Token sw
Token ID1509
Feature activation-1.17e-02

Pos logit contributions
 wolves+0.025
igators+0.024
eer+0.022
 bamboo+0.022
py+0.021
Neg logit contributions
ced-0.019
pen-0.019
 pro-0.017
 marker-0.017
-0.016
Tokenam
Token ID321
Feature activation-8.88e-03

Pos logit contributions
 wolves+0.015
igators+0.015
eer+0.012
 bamboo+0.011
 gor+0.010
Neg logit contributions
ced-0.028
pen-0.027
 marker-0.025
-0.024
mine-0.024
Token in
Token ID287
Feature activation+6.07e-03

Pos logit contributions
 wolves+0.014
igators+0.014
eer+0.012
 bamboo+0.012
py+0.011
Neg logit contributions
ced-0.018
pen-0.018
 marker-0.016
 pro-0.016
-0.016
Token the
Token ID262
Feature activation+1.10e-02

Pos logit contributions
ced+0.013
pen+0.013
 marker+0.012
+0.011
 pro+0.011
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.007
Token ocean
Token ID9151
Feature activation+5.99e-03

Pos logit contributions
ced+0.019
pen+0.018
 marker+0.017
 pro+0.016
 widened+0.016
Neg logit contributions
 wolves-0.020
igators-0.020
eer-0.018
py-0.018
unn-0.018
Token,
Token ID11
Feature activation+4.66e-02

Pos logit contributions
ced+0.011
pen+0.011
 marker+0.010
 pro+0.010
+0.009
Neg logit contributions
 wolves-0.011
igators-0.011
eer-0.009
 bamboo-0.009
py-0.009
Token collected
Token ID7723
Feature activation-1.03e-02

Pos logit contributions
ced+0.087
pen+0.084
 marker+0.077
+0.077
 pro+0.075
Neg logit contributions
 wolves-0.081
igators-0.080
eer-0.072
 bamboo-0.071
py-0.066
Token shells
Token ID19679
Feature activation+1.04e-02

Pos logit contributions
 wolves+0.019
igators+0.019
eer+0.017
py+0.016
 bamboo+0.016
Neg logit contributions
ced-0.018
pen-0.017
 marker-0.015
 pro-0.015
 widened-0.015
Token,
Token ID11
Feature activation+4.82e-02

Pos logit contributions
ced+0.018
pen+0.018
 marker+0.016
+0.016
 pro+0.016
Neg logit contributions
 wolves-0.019
igators-0.019
eer-0.017
 bamboo-0.016
py-0.016
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
ced+0.094
pen+0.091
+0.084
 marker+0.083
 pro+0.081
Neg logit contributions
 wolves-0.080
igators-0.079
eer-0.071
 bamboo-0.070
py-0.064
Token even
Token ID772
Feature activation-3.81e-02

Pos logit contributions
ced+0.022
pen+0.021
 marker+0.020
 pro+0.019
 str+0.019
Neg logit contributions
 wolves-0.028
igators-0.028
eer-0.025
 bamboo-0.024
py-0.024
Token And
Token ID843
Feature activation-3.00e-02

Pos logit contributions
igators+0.043
 wolves+0.042
eer+0.040
 strangers+0.038
 bamboo+0.038
Neg logit contributions
-0.020
pen-0.015
 Exc-0.014
 marker-0.014
ced-0.013
Token Betty
Token ID29504
Feature activation-9.87e-03

Pos logit contributions
igators+0.062
 wolves+0.060
eer+0.057
py+0.053
arl+0.050
Neg logit contributions
ced-0.041
pen-0.040
 pro-0.039
 mirac-0.038
 suddenly-0.037
Token learned
Token ID4499
Feature activation-2.38e-02

Pos logit contributions
 wolves+0.019
igators+0.019
eer+0.017
 bamboo+0.017
py+0.016
Neg logit contributions
ced-0.017
pen-0.016
 marker-0.014
 pro-0.014
-0.014
Token that
Token ID326
Feature activation-9.08e-03

Pos logit contributions
igators+0.042
eer+0.041
 wolves+0.038
unn+0.034
py+0.034
Neg logit contributions
ced-0.043
pen-0.041
 pro-0.039
 marker-0.039
 str-0.038
Token it
Token ID340
Feature activation-1.08e-02

Pos logit contributions
 wolves+0.016
igators+0.015
eer+0.014
 bamboo+0.014
py+0.013
Neg logit contributions
ced-0.017
pen-0.017
-0.015
 marker-0.015
 pro-0.015
Token doesn
Token ID1595
Feature activation+5.92e-02

Pos logit contributions
igators+0.019
 wolves+0.019
eer+0.016
 bamboo+0.016
py+0.015
Neg logit contributions
ced-0.020
pen-0.020
-0.018
 marker-0.018
 widening-0.018
Token't
Token ID470
Feature activation+8.96e-03

Pos logit contributions
ced+0.089
pen+0.082
 marker+0.073
 pro+0.072
 widening+0.071
Neg logit contributions
 wolves-0.126
igators-0.124
py-0.112
 about-0.110
 bamboo-0.109
Token matter
Token ID2300
Feature activation+1.22e-02

Pos logit contributions
ced+0.014
pen+0.013
 marker+0.012
 pro+0.012
mine+0.011
Neg logit contributions
 wolves-0.018
igators-0.018
eer-0.017
 bamboo-0.016
 hay-0.015
Token what
Token ID644
Feature activation+6.26e-03

Pos logit contributions
ced+0.026
pen+0.025
 marker+0.023
 str+0.022
mine+0.022
Neg logit contributions
igators-0.017
 wolves-0.017
eer-0.016
 bamboo-0.015
 camel-0.015
Token you
Token ID345
Feature activation-7.29e-03

Pos logit contributions
ced+0.012
pen+0.011
 marker+0.011
 pro+0.010
+0.010
Neg logit contributions
 wolves-0.011
igators-0.011
eer-0.010
 bamboo-0.010
py-0.009
Token look
Token ID804
Feature activation-9.91e-03

Pos logit contributions
igators+0.013
 wolves+0.012
eer+0.011
 bamboo+0.011
 dogs+0.010
Neg logit contributions
ced-0.014
pen-0.013
-0.012
 marker-0.012
 pro-0.012
Token to
Token ID284
Feature activation+1.08e-02

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
+0.001
 pro+0.001
Neg logit contributions
 wolves-0.000
igators-0.000
eer-0.000
 bamboo-0.000
py-0.000
Token speed
Token ID2866
Feature activation-2.81e-03

Pos logit contributions
ced+0.018
pen+0.017
 marker+0.016
+0.016
 pro+0.015
Neg logit contributions
 wolves-0.020
igators-0.020
eer-0.018
 bamboo-0.018
py-0.017
Token away
Token ID1497
Feature activation-2.36e-02

Pos logit contributions
 wolves+0.004
igators+0.004
eer+0.004
 bamboo+0.004
py+0.004
Neg logit contributions
ced-0.006
pen-0.006
 marker-0.005
-0.005
 pro-0.005
Token before
Token ID878
Feature activation+1.29e-02

Pos logit contributions
igators+0.040
 wolves+0.040
eer+0.037
 bamboo+0.034
py+0.033
Neg logit contributions
ced-0.045
pen-0.043
 pro-0.040
-0.039
 marker-0.039
Token it
Token ID340
Feature activation-6.22e-03

Pos logit contributions
ced+0.023
pen+0.022
 marker+0.020
+0.020
 pro+0.019
Neg logit contributions
 wolves-0.024
igators-0.024
eer-0.022
 bamboo-0.021
py-0.020
Token could
Token ID714
Feature activation+4.31e-02

Pos logit contributions
 wolves+0.013
igators+0.013
eer+0.012
 bamboo+0.012
py+0.011
Neg logit contributions
ced-0.009
pen-0.009
 pro-0.008
 marker-0.008
-0.008
Token reach
Token ID3151
Feature activation+6.67e-04

Pos logit contributions
ced+0.080
pen+0.077
 marker+0.070
+0.070
 pro+0.068
Neg logit contributions
 wolves-0.076
igators-0.075
eer-0.067
 bamboo-0.067
py-0.062
Token her
Token ID607
Feature activation-2.27e-02

Pos logit contributions
ced+0.001
pen+0.001
 pro+0.001
 marker+0.001
+0.001
Neg logit contributions
igators-0.001
 wolves-0.001
eer-0.001
unn-0.001
 bamboo-0.001
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
igators+0.041
 wolves+0.040
eer+0.036
 bamboo+0.034
py+0.033
Neg logit contributions
ced-0.041
pen-0.040
 marker-0.037
-0.036
 pro-0.036
Token
Token ID198
Feature activation-8.44e-03

Pos logit contributions
igators+0.024
 wolves+0.024
eer+0.023
 bamboo+0.021
py+0.021
Neg logit contributions
pen-0.019
ced-0.019
-0.019
 pro-0.017
 marker-0.017
Token
Token ID198
Feature activation-6.58e-03

Pos logit contributions
 wolves+0.014
igators+0.014
eer+0.012
 bamboo+0.012
py+0.011
Neg logit contributions
ced-0.016
pen-0.016
 marker-0.014
-0.014
 pro-0.014
Token "
Token ID366
Feature activation+4.96e-02

Pos logit contributions
ced+0.056
pen+0.054
+0.050
 marker+0.050
 pro+0.049
Neg logit contributions
igators-0.049
 wolves-0.049
eer-0.044
 bamboo-0.042
py-0.039
TokenDon
Token ID3987
Feature activation+3.12e-02

Pos logit contributions
pen+0.079
ced+0.077
+0.071
 marker+0.070
 widened+0.066
Neg logit contributions
 wolves-0.098
igators-0.092
eer-0.084
 bamboo-0.084
py-0.081
Token't
Token ID470
Feature activation-1.06e-02

Pos logit contributions
ced+0.038
pen+0.037
 marker+0.032
 pro+0.030
 widening+0.029
Neg logit contributions
 wolves-0.074
igators-0.073
 bamboo-0.066
eer-0.066
py-0.065
Token worry
Token ID5490
Feature activation+1.39e-02

Pos logit contributions
 wolves+0.024
igators+0.023
eer+0.022
 bamboo+0.021
py+0.020
Neg logit contributions
ced-0.015
pen-0.014
 marker-0.013
-0.012
 pro-0.012
Token,
Token ID11
Feature activation+3.07e-02

Pos logit contributions
ced+0.021
pen+0.020
 marker+0.019
 pro+0.018
+0.017
Neg logit contributions
igators-0.029
 wolves-0.027
eer-0.027
 bamboo-0.024
 habitats-0.024
Token we
Token ID356
Feature activation+2.25e-02

Pos logit contributions
ced+0.067
pen+0.064
 marker+0.060
 pro+0.059
+0.059
Neg logit contributions
igators-0.044
 wolves-0.044
eer-0.039
 bamboo-0.037
py-0.035
Token will
Token ID481
Feature activation+2.77e-02

Pos logit contributions
ced+0.039
pen+0.037
 marker+0.034
+0.034
 widening+0.034
Neg logit contributions
 wolves-0.041
igators-0.040
eer-0.037
 bamboo-0.036
py-0.034
Token get
Token ID651
Feature activation-2.29e-02

Pos logit contributions
ced+0.056
pen+0.053
 marker+0.049
+0.048
 pro+0.048
Neg logit contributions
 wolves-0.043
igators-0.041
 bamboo-0.037
eer-0.037
py-0.035
Token you
Token ID345
Feature activation-2.42e-03

Pos logit contributions
igators+0.040
 wolves+0.040
eer+0.036
py+0.034
 bamboo+0.034
Neg logit contributions
ced-0.043
pen-0.042
 marker-0.038
 pro-0.038
-0.037
Token another
Token ID1194
Feature activation-1.09e-02

Pos logit contributions
 wolves+0.004
igators+0.004
eer+0.004
py+0.004
 bamboo+0.004
Neg logit contributions
ced-0.004
pen-0.004
 marker-0.004
-0.004
 pro-0.004
Token balloon
Token ID21190
Feature activation-1.17e-02

Pos logit contributions
igators+0.017
 wolves+0.017
eer+0.016
 bamboo+0.015
 gorilla+0.015
Neg logit contributions
pen-0.022
ced-0.021
-0.019
 marker-0.019
 widening-0.019
Token to
Token ID284
Feature activation+2.75e-02

Pos logit contributions
igators+0.010
 wolves+0.009
eer+0.008
 bamboo+0.008
py+0.008
Neg logit contributions
ced-0.013
pen-0.012
 marker-0.012
 pro-0.011
 str-0.011
Token record
Token ID1700
Feature activation-9.63e-04

Pos logit contributions
ced+0.053
pen+0.052
+0.047
 marker+0.047
 pro+0.046
Neg logit contributions
igators-0.047
 wolves-0.047
 bamboo-0.041
eer-0.041
py-0.038
Token what
Token ID644
Feature activation+2.19e-02

Pos logit contributions
igators+0.002
 wolves+0.002
unn+0.002
eer+0.002
 bamboo+0.001
Neg logit contributions
ced-0.002
pen-0.002
 marker-0.001
 str-0.001
 pro-0.001
Token it
Token ID340
Feature activation+3.61e-03

Pos logit contributions
ced+0.031
pen+0.030
 marker+0.027
 pro+0.027
 str+0.026
Neg logit contributions
 wolves-0.045
igators-0.045
eer-0.043
 bamboo-0.041
py-0.041
Token saw
Token ID2497
Feature activation+9.52e-03

Pos logit contributions
ced+0.005
pen+0.005
 marker+0.005
 pro+0.005
 widened+0.004
Neg logit contributions
 wolves-0.007
igators-0.007
 bamboo-0.007
eer-0.007
py-0.006
Token.
Token ID13
Feature activation-7.33e-03

Pos logit contributions
ced+0.018
pen+0.018
 marker+0.016
 pro+0.015
+0.015
Neg logit contributions
 wolves-0.016
igators-0.016
eer-0.014
 bamboo-0.014
py-0.013
Token It
Token ID632
Feature activation+1.47e-02

Pos logit contributions
 wolves+0.013
igators+0.013
eer+0.011
 bamboo+0.011
py+0.011
Neg logit contributions
pen-0.013
ced-0.013
-0.013
 marker-0.012
 pro-0.012
Token recorded
Token ID6264
Feature activation+2.41e-03

Pos logit contributions
ced+0.023
pen+0.022
 marker+0.020
 pro+0.019
+0.019
Neg logit contributions
 wolves-0.030
igators-0.030
eer-0.027
 bamboo-0.027
py-0.025
Token the
Token ID262
Feature activation+1.29e-02

Pos logit contributions
ced+0.005
pen+0.004
 pro+0.004
 marker+0.004
 str+0.004
Neg logit contributions
igators-0.004
 wolves-0.004
eer-0.004
unn-0.004
 bamboo-0.004
Token wind
Token ID2344
Feature activation+2.74e-02

Pos logit contributions
ced+0.027
pen+0.026
 marker+0.024
+0.024
 pro+0.023
Neg logit contributions
 wolves-0.020
igators-0.020
eer-0.017
 bamboo-0.017
py-0.016
Token,
Token ID11
Feature activation+4.10e-02

Pos logit contributions
ced+0.050
pen+0.048
 marker+0.045
 pro+0.044
+0.042
Neg logit contributions
 wolves-0.049
igators-0.048
 bamboo-0.043
eer-0.042
unn-0.039
Token agreed
Token ID4987
Feature activation-1.98e-02

Pos logit contributions
igators+0.013
 wolves+0.013
eer+0.012
py+0.011
 bamboo+0.011
Neg logit contributions
ced-0.009
 pro-0.009
pen-0.008
 str-0.008
 widened-0.008
Token.
Token ID13
Feature activation-2.29e-02

Pos logit contributions
 wolves+0.032
igators+0.032
eer+0.028
 bamboo+0.027
py+0.025
Neg logit contributions
ced-0.040
pen-0.039
 marker-0.036
-0.035
 pro-0.035
Token They
Token ID1119
Feature activation-1.49e-02

Pos logit contributions
 wolves+0.040
igators+0.040
eer+0.037
py+0.035
 bamboo+0.033
Neg logit contributions
-0.041
pen-0.040
 pro-0.038
ced-0.037
 Exc-0.035
Token played
Token ID2826
Feature activation+8.27e-03

Pos logit contributions
igators+0.024
 wolves+0.024
 bamboo+0.021
eer+0.021
py+0.019
Neg logit contributions
ced-0.029
pen-0.029
-0.026
 marker-0.026
 pro-0.025
Token together
Token ID1978
Feature activation-2.39e-02

Pos logit contributions
ced+0.016
pen+0.015
 marker+0.014
+0.014
 pro+0.014
Neg logit contributions
 wolves-0.014
igators-0.014
eer-0.013
 bamboo-0.012
py-0.011
Token and
Token ID290
Feature activation-5.17e-03

Pos logit contributions
 wolves+0.033
igators+0.033
 bamboo+0.029
eer+0.028
 about+0.027
Neg logit contributions
ced-0.051
pen-0.050
 marker-0.047
-0.047
 widened-0.045
Token had
Token ID550
Feature activation-1.24e-02

Pos logit contributions
 wolves+0.011
igators+0.011
eer+0.010
 bamboo+0.010
py+0.009
Neg logit contributions
ced-0.008
pen-0.007
 pro-0.007
 marker-0.007
 str-0.006
Token fun
Token ID1257
Feature activation+2.56e-03

Pos logit contributions
 wolves+0.020
igators+0.019
eer+0.017
 bamboo+0.017
py+0.016
Neg logit contributions
ced-0.025
pen-0.024
 marker-0.022
-0.022
 pro-0.022
Token.
Token ID13
Feature activation-2.34e-02

Pos logit contributions
ced+0.006
pen+0.005
 marker+0.005
+0.005
mine+0.005
Neg logit contributions
 wolves-0.004
igators-0.003
 bamboo-0.003
eer-0.003
 dogs-0.003
Token From
Token ID3574
Feature activation-5.10e-02

Pos logit contributions
igators+0.047
 wolves+0.046
eer+0.042
py+0.040
unn+0.040
Neg logit contributions
-0.036
ced-0.035
pen-0.035
 pro-0.032
 widened-0.031
Token that
Token ID326
Feature activation-9.67e-03

Pos logit contributions
 wolves+0.090
igators+0.089
eer+0.085
unn+0.079
 gor+0.078
Neg logit contributions
ced-0.091
pen-0.078
 str-0.077
 pro-0.076
 marker-0.076
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
 wolves+0.038
igators+0.037
 bamboo+0.033
eer+0.033
py+0.031
Neg logit contributions
ced-0.040
pen-0.039
 marker-0.035
 pro-0.035
-0.034
Token The
Token ID383
Feature activation-8.46e-03

Pos logit contributions
 wolves+0.023
igators+0.023
 bamboo+0.021
eer+0.020
py+0.019
Neg logit contributions
pen-0.024
-0.024
ced-0.024
 pro-0.021
 marker-0.021
Token pot
Token ID1787
Feature activation-5.57e-03

Pos logit contributions
 wolves+0.012
igators+0.011
eer+0.010
 bamboo+0.009
 bears+0.009
Neg logit contributions
pen-0.019
ced-0.019
-0.017
 pro-0.017
mine-0.017
Token was
Token ID373
Feature activation+1.04e-02

Pos logit contributions
 wolves+0.011
igators+0.010
eer+0.010
 bamboo+0.009
 dogs+0.009
Neg logit contributions
ced-0.010
pen-0.009
 marker-0.008
-0.008
 pro-0.008
Token the
Token ID262
Feature activation+1.65e-02

Pos logit contributions
ced+0.021
pen+0.020
 marker+0.018
+0.018
 pro+0.018
Neg logit contributions
 wolves-0.017
igators-0.017
eer-0.015
 bamboo-0.015
py-0.014
Token star
Token ID3491
Feature activation+4.02e-03

Pos logit contributions
pen+0.037
ced+0.037
+0.034
mine+0.033
 widened+0.033
Neg logit contributions
 wolves-0.022
igators-0.021
eer-0.019
 bamboo-0.018
 choices-0.017
Token of
Token ID286
Feature activation+2.10e-03

Pos logit contributions
ced+0.008
pen+0.008
 marker+0.007
+0.007
 pro+0.007
Neg logit contributions
 wolves-0.006
igators-0.006
eer-0.006
 bamboo-0.006
py-0.005
Token the
Token ID262
Feature activation+1.31e-02

Pos logit contributions
ced+0.004
pen+0.004
 marker+0.004
+0.003
 pro+0.003
Neg logit contributions
igators-0.003
 wolves-0.003
eer-0.003
unn-0.003
 bamboo-0.003
Token show
Token ID905
Feature activation-9.52e-03

Pos logit contributions
ced+0.026
pen+0.026
+0.023
mine+0.023
 pro+0.023
Neg logit contributions
 wolves-0.022
igators-0.020
eer-0.019
 bamboo-0.018
 hay-0.017
Token and
Token ID290
Feature activation-4.13e-03

Pos logit contributions
 wolves+0.016
igators+0.016
 bamboo+0.014
eer+0.014
py+0.013
Neg logit contributions
ced-0.018
pen-0.018
 marker-0.016
 pro-0.016
-0.016
Token the
Token ID262
Feature activation-7.66e-03

Pos logit contributions
igators+0.008
 wolves+0.008
eer+0.007
 bamboo+0.007
unn+0.007
Neg logit contributions
ced-0.007
pen-0.006
 pro-0.006
 marker-0.006
 str-0.006
Token to
Token ID284
Feature activation+9.88e-03

Pos logit contributions
 wolves+0.037
igators+0.037
eer+0.036
py+0.033
 bamboo+0.032
Neg logit contributions
ced-0.040
 marker-0.039
pen-0.038
 markers-0.037
 str-0.035
Token use
Token ID779
Feature activation-2.17e-02

Pos logit contributions
ced+0.018
pen+0.018
 marker+0.016
+0.016
mine+0.015
Neg logit contributions
 wolves-0.018
igators-0.018
eer-0.016
 bamboo-0.015
py-0.015
Token other
Token ID584
Feature activation-2.74e-02

Pos logit contributions
 wolves+0.037
igators+0.036
eer+0.033
 bamboo+0.031
unn+0.030
Neg logit contributions
ced-0.041
pen-0.040
 marker-0.038
 markers-0.036
 pro-0.035
Token colors
Token ID7577
Feature activation+2.24e-02

Pos logit contributions
 wolves+0.046
igators+0.046
eer+0.041
 bamboo+0.041
py+0.037
Neg logit contributions
ced-0.052
pen-0.050
 marker-0.047
 pro-0.044
-0.044
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
ced+0.039
pen+0.039
 marker+0.038
mine+0.036
 markers+0.035
Neg logit contributions
 wolves-0.041
igators-0.036
eer-0.034
 bamboo-0.034
 gor-0.033
Token You
Token ID921
Feature activation+1.59e-03

Pos logit contributions
 wolves+0.039
igators+0.037
eer+0.036
 bamboo+0.034
 camel+0.033
Neg logit contributions
pen-0.035
-0.034
 marker-0.034
 markers-0.032
can-0.032
Token need
Token ID761
Feature activation-2.26e-02

Pos logit contributions
ced+0.003
pen+0.003
+0.003
 marker+0.003
 pro+0.003
Neg logit contributions
igators-0.003
 wolves-0.003
eer-0.002
 bamboo-0.002
py-0.002
Token to
Token ID284
Feature activation+8.33e-03

Pos logit contributions
 wolves+0.037
igators+0.037
eer+0.035
 bamboo+0.032
py+0.031
Neg logit contributions
ced-0.044
pen-0.042
 marker-0.042
 markers-0.039
 str-0.038
Token improve
Token ID2987
Feature activation+4.42e-04

Pos logit contributions
ced+0.016
pen+0.015
+0.014
 marker+0.014
 pro+0.013
Neg logit contributions
 wolves-0.014
igators-0.014
eer-0.013
 bamboo-0.013
py-0.012
Token your
Token ID534
Feature activation-1.86e-02

Pos logit contributions
ced+0.001
pen+0.001
 marker+0.001
 pro+0.001
 str+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 bamboo-0.000
unn-0.000
Token drawings
Token ID23388
Feature activation-5.13e-03

Pos logit contributions
 wolves+0.035
igators+0.035
eer+0.032
 bamboo+0.031
py+0.029
Neg logit contributions
ced-0.032
pen-0.030
 marker-0.028
-0.027
 pro-0.027
Token and
Token ID290
Feature activation+1.56e-02

Pos logit contributions
 wolves+0.006
igators+0.006
eer+0.006
py+0.005
unn+0.005
Neg logit contributions
ced-0.007
pen-0.007
 marker-0.006
-0.006
 pro-0.006
Token had
Token ID550
Feature activation+3.31e-03

Pos logit contributions
ced+0.026
 marker+0.025
 markers+0.025
 widened+0.024
pen+0.024
Neg logit contributions
 wolves-0.026
igators-0.026
eer-0.025
py-0.025
aring-0.024
Token so
Token ID523
Feature activation-4.01e-02

Pos logit contributions
ced+0.006
pen+0.005
 pro+0.005
 marker+0.005
+0.005
Neg logit contributions
 wolves-0.006
igators-0.006
eer-0.006
py-0.005
unn-0.005
Token much
Token ID881
Feature activation-5.71e-02

Pos logit contributions
 wolves+0.078
igators+0.074
eer+0.071
py+0.071
ior+0.064
Neg logit contributions
ced-0.065
pen-0.060
-0.057
 pro-0.055
 widened-0.053
Token fun
Token ID1257
Feature activation+2.46e-03

Pos logit contributions
eer+0.114
 wolves+0.114
igators+0.113
py+0.112
ior+0.101
Neg logit contributions
ced-0.079
-0.076
pen-0.074
 pro-0.074
 widened-0.072
Token!
Token ID0
Feature activation-1.72e-02

Pos logit contributions
ced+0.004
pen+0.004
+0.003
 pro+0.003
 marker+0.003
Neg logit contributions
 wolves-0.005
igators-0.005
eer-0.005
py-0.004
ior-0.004
Token But
Token ID887
Feature activation-3.80e-03

Pos logit contributions
 wolves+0.033
igators+0.032
eer+0.030
 bamboo+0.029
py+0.029
Neg logit contributions
pen-0.028
-0.028
ced-0.027
 pro-0.025
 marker-0.025
Token then
Token ID788
Feature activation+1.59e-02

Pos logit contributions
igators+0.008
 wolves+0.007
eer+0.007
unn+0.006
py+0.006
Neg logit contributions
ced-0.006
pen-0.006
 pro-0.006
-0.005
 str-0.005
Token,
Token ID11
Feature activation+1.02e-02

Pos logit contributions
ced+0.027
pen+0.025
 pro+0.023
 marker+0.023
+0.022
Neg logit contributions
igators-0.031
 wolves-0.030
eer-0.029
 bamboo-0.027
py-0.026
Token a
Token ID257
Feature activation+1.53e-02

Pos logit contributions
ced+0.019
pen+0.018
 marker+0.017
 pro+0.017
+0.017
Neg logit contributions
igators-0.018
 wolves-0.017
eer-0.016
 bamboo-0.015
py-0.015
Token big
Token ID1263
Feature activation+6.86e-03

Pos logit contributions
ced+0.028
pen+0.027
 marker+0.025
+0.025
 pro+0.024
Neg logit contributions
igators-0.027
 wolves-0.027
eer-0.024
 bamboo-0.024
py-0.022
Token chat
Token ID8537
Feature activation+5.83e-03

Pos logit contributions
ced+0.047
pen+0.046
 marker+0.042
+0.041
 pro+0.040
Neg logit contributions
 wolves-0.050
igators-0.049
eer-0.045
 bamboo-0.044
py-0.041
Token,
Token ID11
Feature activation+4.56e-02

Pos logit contributions
ced+0.012
pen+0.012
+0.011
 marker+0.011
 pro+0.010
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.007
Token play
Token ID711
Feature activation+2.26e-02

Pos logit contributions
ced+0.077
pen+0.074
 pro+0.069
 marker+0.068
 str+0.067
Neg logit contributions
 wolves-0.085
igators-0.084
eer-0.077
 bamboo-0.075
unn-0.072
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
ced+0.047
pen+0.046
+0.043
 marker+0.043
 pro+0.041
Neg logit contributions
 wolves-0.034
igators-0.033
eer-0.030
 bamboo-0.029
py-0.027
Token have
Token ID423
Feature activation-9.06e-03

Pos logit contributions
ced+0.017
pen+0.016
 pro+0.015
 marker+0.015
 str+0.014
Neg logit contributions
 wolves-0.021
igators-0.020
eer-0.019
 bamboo-0.018
unn-0.018
Token lots
Token ID6041
Feature activation-3.67e-02

Pos logit contributions
igators+0.015
 wolves+0.015
eer+0.014
 bamboo+0.013
py+0.013
Neg logit contributions
ced-0.017
pen-0.017
 marker-0.015
 pro-0.015
-0.015
Token of
Token ID286
Feature activation-7.18e-03

Pos logit contributions
 wolves+0.052
igators+0.050
eer+0.045
py+0.041
 bamboo+0.041
Neg logit contributions
ced-0.081
pen-0.079
 pro-0.072
-0.071
 marker-0.070
Token fun
Token ID1257
Feature activation+6.16e-03

Pos logit contributions
 wolves+0.011
igators+0.011
eer+0.010
 bamboo+0.009
py+0.009
Neg logit contributions
ced-0.015
pen-0.014
 marker-0.013
 pro-0.013
-0.013
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
ced+0.012
pen+0.012
 marker+0.011
+0.011
 pro+0.011
Neg logit contributions
 wolves-0.010
igators-0.010
eer-0.009
 bamboo-0.009
py-0.008
Token The
Token ID383
Feature activation-1.04e-02

Pos logit contributions
 wolves+0.026
igators+0.025
 bamboo+0.023
eer+0.023
py+0.021
Neg logit contributions
pen-0.033
-0.032
ced-0.032
 pro-0.029
mine-0.028
Token pirate
Token ID25868
Feature activation-2.29e-02

Pos logit contributions
 wolves+0.016
igators+0.015
eer+0.014
 bamboo+0.014
py+0.012
Neg logit contributions
ced-0.022
pen-0.021
-0.020
 marker-0.020
 pro-0.019
Token and
Token ID290
Feature activation+6.82e-03

Pos logit contributions
 wolves+0.029
igators+0.028
eer+0.026
 bamboo+0.026
py+0.025
Neg logit contributions
pen-0.022
ced-0.022
 marker-0.020
-0.019
 pro-0.018
Token got
Token ID1392
Feature activation-1.80e-02

Pos logit contributions
ced+0.012
pen+0.011
 marker+0.011
 pro+0.010
 str+0.010
Neg logit contributions
 wolves-0.013
igators-0.013
eer-0.012
 bamboo-0.012
py-0.011
Token the
Token ID262
Feature activation+2.09e-02

Pos logit contributions
 wolves+0.029
igators+0.028
eer+0.025
 bamboo+0.025
py+0.023
Neg logit contributions
ced-0.036
pen-0.035
 marker-0.033
-0.032
 pro-0.032
Token ball
Token ID2613
Feature activation+5.75e-03

Pos logit contributions
ced+0.040
pen+0.039
 widened+0.034
+0.034
 pro+0.034
Neg logit contributions
 wolves-0.036
igators-0.036
eer-0.032
 bamboo-0.031
 hay-0.030
Token back
Token ID736
Feature activation-5.77e-02

Pos logit contributions
ced+0.013
pen+0.013
+0.012
 marker+0.012
 pro+0.011
Neg logit contributions
igators-0.008
 wolves-0.008
 bamboo-0.007
eer-0.007
py-0.006
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
 wolves+0.102
igators+0.098
eer+0.089
 bamboo+0.087
py+0.082
Neg logit contributions
ced-0.109
pen-0.106
 marker-0.098
-0.097
 pro-0.095
Token Tim
Token ID5045
Feature activation+1.81e-02

Pos logit contributions
 wolves+0.026
igators+0.025
eer+0.023
 bamboo+0.022
py+0.021
Neg logit contributions
-0.033
pen-0.032
ced-0.031
 marker-0.030
 pro-0.030
Tokenmy
Token ID1820
Feature activation+1.97e-04

Pos logit contributions
ced+0.038
pen+0.037
+0.034
 marker+0.034
 pro+0.033
Neg logit contributions
 wolves-0.027
igators-0.027
eer-0.024
 bamboo-0.023
py-0.022
Token was
Token ID373
Feature activation-6.61e-03

Pos logit contributions
ced+0.000
pen+0.000
+0.000
 marker+0.000
 widening+0.000
Neg logit contributions
 wolves-0.000
igators-0.000
eer-0.000
 about-0.000
 bamboo-0.000
Token happy
Token ID3772
Feature activation+1.30e-02

Pos logit contributions
 wolves+0.010
igators+0.010
eer+0.009
 bamboo+0.009
py+0.008
Neg logit contributions
ced-0.014
pen-0.013
 marker-0.012
-0.012
 pro-0.012
Token he
Token ID339
Feature activation-2.88e-02

Pos logit contributions
ced+0.026
pen+0.025
 pro+0.024
 marker+0.023
+0.023
Neg logit contributions
igators-0.022
 wolves-0.021
eer-0.019
 bamboo-0.018
py-0.017
Token and
Token ID290
Feature activation-1.61e-02

Pos logit contributions
ced+0.024
pen+0.024
 pro+0.022
 marker+0.022
+0.021
Neg logit contributions
igators-0.025
 wolves-0.024
eer-0.022
 bamboo-0.021
py-0.020
Token thanked
Token ID26280
Feature activation-8.67e-03

Pos logit contributions
igators+0.033
 wolves+0.033
eer+0.030
 bamboo+0.029
py+0.028
Neg logit contributions
ced-0.025
pen-0.024
 pro-0.022
 marker-0.022
 str-0.022
Token the
Token ID262
Feature activation-5.31e-03

Pos logit contributions
igators+0.016
 wolves+0.015
eer+0.014
 bamboo+0.013
unn+0.013
Neg logit contributions
ced-0.015
pen-0.015
 marker-0.014
mine-0.014
-0.014
Token angel
Token ID18304
Feature activation-3.70e-02

Pos logit contributions
 wolves+0.007
igators+0.007
eer+0.006
 bamboo+0.006
py+0.005
Neg logit contributions
ced-0.012
pen-0.012
-0.011
 marker-0.011
 pro-0.011
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
igators+0.066
 wolves+0.062
 dangers+0.053
eer+0.053
unn+0.051
Neg logit contributions
pen-0.066
 pro-0.062
ced-0.061
mine-0.059
 str-0.058
Token She
Token ID1375
Feature activation-3.00e-02

Pos logit contributions
igators+0.020
 wolves+0.019
eer+0.017
 bamboo+0.016
 gor+0.015
Neg logit contributions
-0.020
pen-0.019
 marker-0.018
 pro-0.018
ced-0.018
Token had
Token ID550
Feature activation+1.48e-03

Pos logit contributions
igators+0.060
 wolves+0.060
eer+0.054
 bamboo+0.053
py+0.050
Neg logit contributions
ced-0.049
pen-0.047
 pro-0.043
 marker-0.042
 str-0.041
Token a
Token ID257
Feature activation+1.05e-02

Pos logit contributions
ced+0.003
pen+0.002
 marker+0.002
 pro+0.002
+0.002
Neg logit contributions
 wolves-0.003
igators-0.003
eer-0.003
 bamboo-0.003
py-0.002
Token great
Token ID1049
Feature activation-2.01e-02

Pos logit contributions
pen+0.023
ced+0.023
mine+0.021
 widening+0.020
 widened+0.020
Neg logit contributions
 wolves-0.014
 bamboo-0.014
igators-0.013
 gorilla-0.012
 hay-0.012
Token time
Token ID640
Feature activation+1.49e-02

Pos logit contributions
 wolves+0.026
igators+0.024
 bamboo+0.022
eer+0.022
 about+0.020
Neg logit contributions
ced-0.046
pen-0.045
 marker-0.041
-0.041
 widened-0.041
Token visiting
Token ID10013
Feature activation-1.76e-02

Pos logit contributions
ced+0.029
pen+0.028
+0.026
 pro+0.026
 marker+0.026
Neg logit contributions
igators-0.025
 wolves-0.025
eer-0.022
 bamboo-0.021
py-0.020
Token three
Token ID1115
Feature activation-2.99e-02

Pos logit contributions
ced+0.002
pen+0.002
 marker+0.002
 pro+0.002
+0.002
Neg logit contributions
igators-0.002
 wolves-0.002
 bamboo-0.002
eer-0.002
py-0.002
Token-
Token ID12
Feature activation-4.84e-02

Pos logit contributions
 wolves+0.056
igators+0.055
 bamboo+0.051
py+0.049
eer+0.049
Neg logit contributions
ced-0.050
pen-0.046
 pro-0.044
mine-0.041
-0.040
Tokenyear
Token ID1941
Feature activation-7.64e-02

Pos logit contributions
 wolves+0.068
igators+0.066
eer+0.057
 bamboo+0.056
py+0.051
Neg logit contributions
ced-0.108
pen-0.106
 marker-0.097
-0.095
 pro-0.095
Token-
Token ID12
Feature activation-5.98e-02

Pos logit contributions
igators+0.158
 wolves+0.156
 bamboo+0.138
 Rex+0.137
py+0.137
Neg logit contributions
pen-0.101
ced-0.099
 pro-0.087
 widening-0.082
 marker-0.082
Tokenold
Token ID727
Feature activation-1.37e-02

Pos logit contributions
 wolves+0.069
igators+0.064
 bamboo+0.053
eer+0.051
py+0.046
Neg logit contributions
pen-0.149
ced-0.149
mine-0.135
 marker-0.134
 pro-0.132
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
igators+0.026
 wolves+0.024
 bamboo+0.022
eer+0.021
py+0.021
Neg logit contributions
pen-0.024
ced-0.023
 pro-0.022
 marker-0.021
mine-0.020
Token He
Token ID679
Feature activation-1.63e-02

Pos logit contributions
 wolves+0.017
igators+0.016
eer+0.015
 bamboo+0.014
py+0.014
Neg logit contributions
pen-0.024
ced-0.023
-0.023
 marker-0.022
 pro-0.022
Token had
Token ID550
Feature activation+1.11e-02

Pos logit contributions
 wolves+0.033
igators+0.033
eer+0.029
 bamboo+0.029
 choices+0.028
Neg logit contributions
ced-0.026
pen-0.025
 marker-0.022
 pro-0.022
 str-0.022
Token an
Token ID281
Feature activation+1.72e-04

Pos logit contributions
ced+0.019
pen+0.018
 marker+0.017
 str+0.016
 pro+0.016
Neg logit contributions
igators-0.021
 wolves-0.021
eer-0.019
 bamboo-0.019
unn-0.018
Token unusual
Token ID8468
Feature activation-4.89e-04

Pos logit contributions
ced+0.000
pen+0.000
 marker+0.000
+0.000
 markers+0.000
Neg logit contributions
 wolves-0.000
igators-0.000
 bamboo-0.000
eer-0.000
unn-0.000
Token sc
Token ID629
Feature activation-6.13e-02

Pos logit contributions
 wolves+0.001
igators+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.001
pen-0.001
-0.001
 marker-0.001
 pro-0.001
Token their
Token ID511
Feature activation-1.95e-02

Pos logit contributions
igators+0.009
 wolves+0.009
eer+0.008
unn+0.007
 bamboo+0.007
Neg logit contributions
ced-0.018
pen-0.017
 marker-0.016
 pro-0.016
 str-0.016
Token voices
Token ID10839
Feature activation+1.13e-02

Pos logit contributions
igators+0.037
 wolves+0.037
 about+0.033
py+0.033
 bamboo+0.033
Neg logit contributions
 marker-0.029
ced-0.029
pen-0.028
 tug-0.026
 markers-0.025
Token and
Token ID290
Feature activation+1.48e-02

Pos logit contributions
ced+0.023
pen+0.022
+0.021
 marker+0.020
 pro+0.020
Neg logit contributions
 wolves-0.018
igators-0.017
eer-0.015
 bamboo-0.015
py-0.014
Token made
Token ID925
Feature activation+8.94e-04

Pos logit contributions
ced+0.023
pen+0.021
 marker+0.020
 pro+0.019
 widened+0.019
Neg logit contributions
igators-0.031
 wolves-0.030
eer-0.028
 bamboo-0.028
py-0.027
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
ced+0.002
pen+0.002
 marker+0.002
 pro+0.002
+0.002
Neg logit contributions
 wolves-0.001
igators-0.001
eer-0.001
 bamboo-0.001
py-0.001
Token lot
Token ID1256
Feature activation-5.76e-02

Pos logit contributions
ced+0.037
pen+0.036
+0.033
 marker+0.033
 pro+0.032
Neg logit contributions
 wolves-0.034
igators-0.034
eer-0.030
 bamboo-0.030
py-0.028
Token of
Token ID286
Feature activation-6.31e-03

Pos logit contributions
 wolves+0.091
igators+0.082
eer+0.079
py+0.076
 Dod+0.072
Neg logit contributions
ced-0.115
pen-0.114
 pro-0.101
 widened-0.100
 marker-0.100
Token noise
Token ID7838
Feature activation+1.53e-02

Pos logit contributions
igators+0.010
 wolves+0.010
eer+0.009
 bamboo+0.009
py+0.008
Neg logit contributions
ced-0.013
pen-0.012
 marker-0.011
 pro-0.011
-0.011
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
ced+0.029
pen+0.027
 pro+0.025
 marker+0.025
 widened+0.024
Neg logit contributions
igators-0.027
 wolves-0.027
eer-0.024
 bamboo-0.024
py-0.023
Token
Token ID198
Feature activation-1.14e-02

Pos logit contributions
igators+0.019
 wolves+0.018
eer+0.016
 bamboo+0.015
py+0.015
Neg logit contributions
-0.034
ced-0.034
pen-0.033
 marker-0.032
 widened-0.031
Token
Token ID198
Feature activation-9.23e-03

Pos logit contributions
 wolves+0.025
igators+0.025
eer+0.023
 bamboo+0.022
py+0.021
Neg logit contributions
ced-0.017
pen-0.015
-0.014
 marker-0.014
 pro-0.013
TokenThey
Token ID2990
Feature activation-9.68e-03

Pos logit contributions
igators+0.014
 wolves+0.014
 bamboo+0.012
 hay+0.011
eer+0.011
Neg logit contributions
pen-0.014
ced-0.014
 marker-0.014
-0.013
 markers-0.012
Token laughed
Token ID13818
Feature activation+1.88e-02

Pos logit contributions
 wolves+0.018
igators+0.018
eer+0.016
 bamboo+0.016
py+0.015
Neg logit contributions
ced-0.016
pen-0.016
-0.015
 marker-0.014
 pro-0.014
Token and
Token ID290
Feature activation+1.98e-03

Pos logit contributions
ced+0.037
pen+0.036
 marker+0.033
+0.033
 pro+0.032
Neg logit contributions
 wolves-0.031
igators-0.030
eer-0.027
 bamboo-0.026
py-0.024
Token had
Token ID550
Feature activation+2.22e-03

Pos logit contributions
ced+0.003
pen+0.003
 pro+0.003
 marker+0.002
 str+0.002
Neg logit contributions
 wolves-0.004
igators-0.004
eer-0.004
 bamboo-0.004
py-0.004
Token so
Token ID523
Feature activation-4.34e-02

Pos logit contributions
ced+0.005
pen+0.005
 marker+0.004
+0.004
 pro+0.004
Neg logit contributions
 wolves-0.003
igators-0.003
 bamboo-0.003
eer-0.003
py-0.003
Token much
Token ID881
Feature activation-5.78e-02

Pos logit contributions
 wolves+0.071
igators+0.069
eer+0.064
py+0.060
 bamboo+0.058
Neg logit contributions
ced-0.088
pen-0.082
-0.077
 pro-0.077
 widened-0.073
Token fun
Token ID1257
Feature activation+5.29e-03

Pos logit contributions
 wolves+0.102
igators+0.101
eer+0.096
py+0.089
 bamboo+0.083
Neg logit contributions
ced-0.108
pen-0.102
 pro-0.097
-0.097
 marker-0.095
Token together
Token ID1978
Feature activation-2.67e-02

Pos logit contributions
ced+0.010
pen+0.009
+0.009
 pro+0.008
 marker+0.008
Neg logit contributions
 wolves-0.010
igators-0.009
eer-0.009
 bamboo-0.008
py-0.008
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
 wolves+0.047
igators+0.047
eer+0.043
 bamboo+0.041
py+0.039
Neg logit contributions
ced-0.051
pen-0.049
 pro-0.045
-0.044
 marker-0.044
Token Suddenly
Token ID24975
Feature activation+1.00e-02

Pos logit contributions
 wolves+0.032
igators+0.032
eer+0.029
 bamboo+0.028
py+0.027
Neg logit contributions
-0.035
ced-0.035
pen-0.035
 pro-0.033
 marker-0.031
Token,
Token ID11
Feature activation+1.36e-02

Pos logit contributions
ced+0.020
pen+0.019
 marker+0.017
+0.017
 pro+0.017
Neg logit contributions
 wolves-0.017
igators-0.016
eer-0.015
 bamboo-0.014
py-0.013
Token the
Token ID262
Feature activation+1.40e-02

Pos logit contributions
igators+0.001
 wolves+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.002
pen-0.002
 marker-0.002
-0.002
 pro-0.001
Token swings
Token ID26728
Feature activation+4.42e-03

Pos logit contributions
ced+0.026
pen+0.024
 marker+0.023
+0.022
 pro+0.022
Neg logit contributions
 wolves-0.024
igators-0.024
eer-0.022
 bamboo-0.020
py-0.020
Token and
Token ID290
Feature activation+1.39e-02

Pos logit contributions
ced+0.008
pen+0.007
+0.007
 marker+0.007
 pro+0.007
Neg logit contributions
 wolves-0.008
igators-0.008
eer-0.008
 bamboo-0.007
py-0.007
Token had
Token ID550
Feature activation-3.38e-03

Pos logit contributions
ced+0.023
pen+0.021
 pro+0.020
 str+0.020
 marker+0.020
Neg logit contributions
 wolves-0.026
igators-0.025
eer-0.023
py-0.022
 choices-0.022
Token a
Token ID257
Feature activation+1.34e-02

Pos logit contributions
 wolves+0.005
igators+0.005
eer+0.005
 bamboo+0.005
py+0.004
Neg logit contributions
ced-0.007
pen-0.007
 marker-0.006
-0.006
 pro-0.006
Token lot
Token ID1256
Feature activation-6.22e-02

Pos logit contributions
pen+0.034
ced+0.032
mine+0.030
can+0.028
neath+0.028
Neg logit contributions
 wolves-0.015
 bamboo-0.015
 hay-0.013
 gorilla-0.013
igators-0.013
Token of
Token ID286
Feature activation-1.16e-03

Pos logit contributions
 wolves+0.106
igators+0.094
eer+0.093
py+0.086
 bears+0.084
Neg logit contributions
ced-0.116
pen-0.116
 marker-0.104
-0.103
 pro-0.103
Token fun
Token ID1257
Feature activation-2.03e-03

Pos logit contributions
 wolves+0.002
igators+0.002
eer+0.002
 bamboo+0.002
py+0.001
Neg logit contributions
ced-0.002
pen-0.002
 marker-0.002
-0.002
 pro-0.002
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
 wolves+0.003
igators+0.003
eer+0.003
 bamboo+0.003
py+0.003
Neg logit contributions
ced-0.004
pen-0.004
-0.003
 marker-0.003
 pro-0.003
Token
Token ID198
Feature activation-8.10e-03

Pos logit contributions
 wolves+0.031
igators+0.031
eer+0.029
py+0.027
 bamboo+0.026
Neg logit contributions
ced-0.021
-0.021
pen-0.020
 marker-0.019
 pro-0.018
Token
Token ID198
Feature activation-4.99e-03

Pos logit contributions
 wolves+0.013
igators+0.013
eer+0.012
 bamboo+0.011
py+0.011
Neg logit contributions
ced-0.016
pen-0.015
 marker-0.014
-0.014
 pro-0.014
Token the
Token ID262
Feature activation+1.23e-02

Pos logit contributions
ced+0.012
pen+0.011
 marker+0.010
+0.010
 pro+0.010
Neg logit contributions
 wolves-0.009
igators-0.009
eer-0.008
 bamboo-0.008
py-0.008
Token road
Token ID2975
Feature activation-8.63e-03

Pos logit contributions
ced+0.021
pen+0.021
 marker+0.020
+0.019
 pro+0.019
Neg logit contributions
igators-0.021
 wolves-0.021
eer-0.020
py-0.019
unn-0.018
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
 wolves+0.015
igators+0.014
eer+0.013
 bamboo+0.013
py+0.012
Neg logit contributions
ced-0.016
pen-0.016
 pro-0.014
-0.014
 marker-0.014
Token
Token ID198
Feature activation-3.75e-03

Pos logit contributions
 wolves+0.032
igators+0.032
eer+0.030
py+0.029
 bamboo+0.028
Neg logit contributions
pen-0.023
ced-0.022
-0.022
 pro-0.020
 marker-0.019
Token
Token ID198
Feature activation-6.08e-04

Pos logit contributions
 wolves+0.006
igators+0.006
eer+0.005
 bamboo+0.005
py+0.005
Neg logit contributions
ced-0.007
pen-0.007
 marker-0.006
-0.006
 pro-0.006
TokenOne
Token ID3198
Feature activation-5.89e-02

Pos logit contributions
 wolves+0.001
igators+0.001
eer+0.001
 bamboo+0.001
py+0.001
Neg logit contributions
ced-0.001
pen-0.001
 marker-0.001
-0.001
 pro-0.001
Token time
Token ID640
Feature activation+1.55e-02

Pos logit contributions
 wolves+0.109
py+0.106
igators+0.104
girls+0.104
unn+0.102
Neg logit contributions
ced-0.088
 str-0.079
 marker-0.076
pron-0.076
he-0.074
Token,
Token ID11
Feature activation+7.72e-03

Pos logit contributions
ced+0.030
pen+0.030
 marker+0.027
+0.027
 pro+0.026
Neg logit contributions
 wolves-0.025
igators-0.025
eer-0.022
 bamboo-0.022
py-0.020
Token the
Token ID262
Feature activation-5.73e-03

Pos logit contributions
ced+0.017
pen+0.016
 marker+0.015
+0.015
 pro+0.015
Neg logit contributions
 wolves-0.011
igators-0.011
eer-0.009
 bamboo-0.009
py-0.008
Token ball
Token ID2613
Feature activation-3.01e-03

Pos logit contributions
 wolves+0.012
igators+0.012
eer+0.011
 bamboo+0.011
 dogs+0.010
Neg logit contributions
ced-0.009
pen-0.009
 marker-0.007
-0.007
 pro-0.007
Token went
Token ID1816
Feature activation-9.94e-03

Pos logit contributions
 wolves+0.006
igators+0.006
eer+0.006
 bamboo+0.005
py+0.005
Neg logit contributions
ced-0.005
pen-0.005
 marker-0.004
-0.004
 pro-0.004
Token't
Token ID470
Feature activation+1.87e-02

Pos logit contributions
ced+0.077
pen+0.073
 marker+0.063
 pro+0.061
+0.059
Neg logit contributions
igators-0.157
 wolves-0.156
 bamboo-0.141
eer-0.140
py-0.138
Token food
Token ID2057
Feature activation+2.23e-02

Pos logit contributions
ced+0.033
 marker+0.030
pen+0.030
 str+0.029
 pro+0.028
Neg logit contributions
igators-0.030
 wolves-0.029
 enclosure-0.028
unn-0.028
 habitats-0.028
Token!
Token ID0
Feature activation-2.09e-03

Pos logit contributions
ced+0.040
pen+0.040
 marker+0.036
+0.035
 pro+0.035
Neg logit contributions
 wolves-0.040
igators-0.040
eer-0.036
 bamboo-0.035
py-0.034
Token
Token ID198
Feature activation+7.21e-04

Pos logit contributions
 wolves+0.004
igators+0.004
eer+0.004
 bamboo+0.003
py+0.003
Neg logit contributions
ced-0.004
pen-0.003
-0.003
 marker-0.003
 pro-0.003
Token
Token ID198
Feature activation+1.29e-03

Pos logit contributions
ced+0.002
pen+0.002
 marker+0.001
 pro+0.001
+0.001
Neg logit contributions
 wolves-0.001
igators-0.001
 bamboo-0.001
eer-0.001
 about-0.001
TokenOne
Token ID3198
Feature activation-6.07e-02

Pos logit contributions
ced+0.002
pen+0.002
+0.002
 marker+0.002
 pro+0.002
Neg logit contributions
 wolves-0.002
igators-0.002
 bamboo-0.002
eer-0.002
py-0.002
Token day
Token ID1110
Feature activation+2.44e-02

Pos logit contributions
igators+0.108
 wolves+0.103
py+0.094
eer+0.093
 bamboo+0.093
Neg logit contributions
ced-0.103
 marker-0.102
pron-0.101
 str-0.096
pen-0.093
Token,
Token ID11
Feature activation+4.62e-03

Pos logit contributions
ced+0.052
pen+0.051
 marker+0.046
+0.046
 pro+0.045
Neg logit contributions
 wolves-0.036
igators-0.033
 bamboo-0.031
eer-0.030
 dogs-0.027
Token M
Token ID337
Feature activation-2.10e-02

Pos logit contributions
ced+0.011
pen+0.010
 marker+0.009
+0.009
 pro+0.009
Neg logit contributions
 wolves-0.006
igators-0.006
 bamboo-0.005
eer-0.005
 Fif-0.005
Tokenilly
Token ID6548
Feature activation-7.04e-03

Pos logit contributions
 wolves+0.036
igators+0.034
eer+0.032
 bamboo+0.031
py+0.029
Neg logit contributions
ced-0.040
pen-0.038
 pro-0.035
 marker-0.035
-0.034
Token was
Token ID373
Feature activation-1.99e-03

Pos logit contributions
igators+0.015
 wolves+0.014
 bamboo+0.013
eer+0.013
py+0.012
Neg logit contributions
ced-0.011
pen-0.010
 marker-0.009
-0.009
 pro-0.009