TOP ACTIVATIONS
MAX = 9.541

the people kept on cheering him on . And they all
the people kept on cheering him on . And they all
it made her smile come back . <|endoftext|> Once there was
be much better than throwing them away ." Tom
afraid they wouldn 't pass him . He
the other animals would cheer him on ! It
to come and sn uggle him . One night
them safe instead of showing them off to everyone . <|endoftext|>
and never let fear hold them back . <|endoftext|> Once upon
peaceful feeling it always gave him . <|endoftext|> Once upon a
tried to make them lift him up . He worked really
and was willing to try them with her mom by her
and the crowd was cheering them on . The
tw igs it would give him a reward . The bird
and believed they would bring him good luck . <|endoftext|> Once
available so he could pick them and make tasty dishes with
nice and you can pick them and make a bou quet
Sally still wouldn 't give him back the violin .
try to loosen the b ram bles . As he was
was and wanted to cheer him up . They

MIN ACTIVATIONS
MIN = -10.503

Lily . She had a pair of pink m ittens that
a boy had a funny pair of boots . He loved
Sue . She had a pair of incredible m ittens .
. He had a big pair of scissors that he loved
time , there was a cater pillar who was very lonely
, there was a small cater pillar . He wanted to
time , there was a cater pillar named Sammy . Sammy
time there was a magical cater pillar living in a mysterious
time , there was a cater pillar who didn 't like
, there was a little cater pillar . She was very
time there was a wide cater pillar . He was alone
time , there was a cater pillar who was very obedient
a time there was a cater pillar . It lived outside
, there was an enormous cater pillar . He was looking
time , there was a cater pillar named Cindy . She
time , there was an elderly cat named Tom . Tom
in the garden . A cater pillar was eating all the
, there was a fat cater pillar called Tom . Tom
time , there was an elderly man who loved rockets .
<|endoftext|> Once there was a cater pillar in a garden who

INTERVAL 4.530 - 9.541
CONTAINS 4.049%

a spoon and scoop ed out the inside . It was
Tim my felt happy again , and the bigger boy and
. He would always ask his friends to come along and
who warned him to stay away from the hole . She
to shoot their cars over the cone . They see how

INTERVAL -0.481 - 4.530
CONTAINS 55.259%

she created . When she was done , the
to hear from Lily and Ben . She loved them very
leave his t eddy bear alone . He said , "
tried to play , but it sounded loud and noisy .
floor . She didn 't notice . She put the pan

INTERVAL -5.492 - -0.481
CONTAINS 38.670%

. <|endoftext|> Once upon a time , there was a little
. Lily was scared , but her mom my told her
inky , " What happened to your knee ?" B inky
. But she was too small . She could
was happy to be inside with her mom my , safe

INTERVAL -10.503 - -5.492
CONTAINS 2.022%

says to Sam , " I am the boss of the
played , she saw a shiny glass on the ground .
in it . Suddenly , a nos y bird flew over
a large tray . The tray was made of wood ,
. Within minutes , a delicious chocolate cake was done .
Token the
Token ID262
Feature activation+4.28e+00

Pos logit contributions
angers+0.051
ail+0.046
aj+0.045
bled+0.044
uing+0.044
Neg logit contributions
 course-0.029
 sorts-0.028
 juicy-0.026
 tiger-0.025
 animal-0.023
Token people
Token ID661
Feature activation+1.52e+00

Pos logit contributions
angers+0.152
ail+0.152
aj+0.147
 conscience+0.137
immers+0.136
Neg logit contributions
 sorts-0.106
 course-0.097
 juicy-0.083
e-0.082
leaf-0.081
Token kept
Token ID4030
Feature activation+3.75e+00

Pos logit contributions
angers+0.058
ail+0.054
uing+0.053
bled+0.052
aj+0.052
Neg logit contributions
 course-0.036
 sorts-0.035
 juicy-0.034
 tiger-0.033
 snowball-0.030
Token on
Token ID319
Feature activation-6.51e-01

Pos logit contributions
angers+0.130
bled+0.118
ail+0.116
uing+0.114
aj+0.113
Neg logit contributions
 course-0.106
 sorts-0.102
 juicy-0.098
 tiger-0.097
 gir-0.089
Token cheering
Token ID29732
Feature activation+3.67e+00

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.016
 tiger+0.016
igator+0.015
Neg logit contributions
angers-0.024
ail-0.022
aj-0.021
uing-0.021
bled-0.021
Token him
Token ID683
Feature activation+9.46e+00

Pos logit contributions
angers+0.146
ail+0.132
aj+0.130
bled+0.129
uing+0.127
Neg logit contributions
 course-0.092
 sorts-0.088
 juicy-0.082
 tiger-0.079
 animal-0.073
Token on
Token ID319
Feature activation+6.24e-01

Pos logit contributions
angers+0.345
ail+0.316
aj+0.312
uing+0.309
bled+0.308
Neg logit contributions
 course-0.262
 sorts-0.249
 juicy-0.236
 tiger-0.224
 elephant-0.209
Token.
Token ID13
Feature activation+7.35e-01

Pos logit contributions
angers+0.022
uing+0.019
ail+0.019
aj+0.019
bled+0.018
Neg logit contributions
 sorts-0.016
 juicy-0.016
 course-0.016
 tiger-0.015
 elephant-0.014
Token And
Token ID843
Feature activation-4.64e-01

Pos logit contributions
angers+0.025
ail+0.022
aj+0.022
bled+0.021
uing+0.021
Neg logit contributions
 course-0.022
 sorts-0.022
 juicy-0.021
 tiger-0.020
 piece-0.019
Token they
Token ID484
Feature activation-8.05e-01

Pos logit contributions
 course+0.013
 sorts+0.012
 juicy+0.012
 tiger+0.011
 snowball+0.011
Neg logit contributions
angers-0.015
ail-0.014
bled-0.014
uing-0.014
aj-0.013
Token all
Token ID477
Feature activation-1.44e+00

Pos logit contributions
 juicy+0.020
 course+0.020
 sorts+0.020
 tiger+0.019
 snowball+0.019
Neg logit contributions
ail-0.027
angers-0.027
bled-0.026
uing-0.025
aj-0.024
Token the
Token ID262
Feature activation+4.28e+00

Pos logit contributions
angers+0.051
ail+0.046
aj+0.045
bled+0.044
uing+0.044
Neg logit contributions
 course-0.029
 sorts-0.028
 juicy-0.026
 tiger-0.025
 animal-0.023
Token people
Token ID661
Feature activation+1.52e+00

Pos logit contributions
angers+0.152
ail+0.152
aj+0.147
 conscience+0.137
immers+0.136
Neg logit contributions
 sorts-0.106
 course-0.097
 juicy-0.083
e-0.082
leaf-0.081
Token kept
Token ID4030
Feature activation+3.75e+00

Pos logit contributions
angers+0.058
ail+0.054
uing+0.053
bled+0.052
aj+0.052
Neg logit contributions
 course-0.036
 sorts-0.035
 juicy-0.034
 tiger-0.033
 snowball-0.030
Token on
Token ID319
Feature activation-6.51e-01

Pos logit contributions
angers+0.130
bled+0.118
ail+0.116
uing+0.114
aj+0.113
Neg logit contributions
 course-0.106
 sorts-0.102
 juicy-0.098
 tiger-0.097
 gir-0.089
Token cheering
Token ID29732
Feature activation+3.67e+00

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.016
 tiger+0.016
igator+0.015
Neg logit contributions
angers-0.024
ail-0.022
aj-0.021
uing-0.021
bled-0.021
Token him
Token ID683
Feature activation+9.46e+00

Pos logit contributions
angers+0.146
ail+0.132
aj+0.130
bled+0.129
uing+0.127
Neg logit contributions
 course-0.092
 sorts-0.088
 juicy-0.082
 tiger-0.079
 animal-0.073
Token on
Token ID319
Feature activation+6.24e-01

Pos logit contributions
angers+0.345
ail+0.316
aj+0.312
uing+0.309
bled+0.308
Neg logit contributions
 course-0.262
 sorts-0.249
 juicy-0.236
 tiger-0.224
 elephant-0.209
Token.
Token ID13
Feature activation+7.35e-01

Pos logit contributions
angers+0.022
uing+0.019
ail+0.019
aj+0.019
bled+0.018
Neg logit contributions
 sorts-0.016
 juicy-0.016
 course-0.016
 tiger-0.015
 elephant-0.014
Token And
Token ID843
Feature activation-4.64e-01

Pos logit contributions
angers+0.025
ail+0.022
aj+0.022
bled+0.021
uing+0.021
Neg logit contributions
 course-0.022
 sorts-0.022
 juicy-0.021
 tiger-0.020
 piece-0.019
Token they
Token ID484
Feature activation-8.05e-01

Pos logit contributions
 course+0.013
 sorts+0.012
 juicy+0.012
 tiger+0.011
 snowball+0.011
Neg logit contributions
angers-0.015
ail-0.014
bled-0.014
uing-0.014
aj-0.013
Token all
Token ID477
Feature activation-1.44e+00

Pos logit contributions
 juicy+0.020
 course+0.020
 sorts+0.020
 tiger+0.019
 snowball+0.019
Neg logit contributions
ail-0.027
angers-0.027
bled-0.026
uing-0.025
aj-0.024
Token it
Token ID340
Feature activation+6.11e+00

Pos logit contributions
angers+0.098
ail+0.091
bled+0.089
aj+0.088
uing+0.087
Neg logit contributions
 course-0.056
 sorts-0.051
 tiger-0.048
 juicy-0.047
 elephant-0.043
Token made
Token ID925
Feature activation+2.43e+00

Pos logit contributions
angers+0.208
ail+0.199
bled+0.188
uing+0.186
aj+0.182
Neg logit contributions
 course-0.168
 sorts-0.158
 tiger-0.154
 juicy-0.152
 snowball-0.141
Token her
Token ID607
Feature activation+7.32e+00

Pos logit contributions
angers+0.087
ail+0.080
bled+0.077
uing+0.076
aj+0.075
Neg logit contributions
 course-0.066
 sorts-0.064
 juicy-0.061
 tiger-0.060
 elephant-0.055
Token smile
Token ID8212
Feature activation+4.41e+00

Pos logit contributions
angers+0.211
ail+0.206
aj+0.195
uing+0.189
 conscience+0.188
Neg logit contributions
 course-0.243
 sorts-0.222
 tiger-0.219
 juicy-0.208
leaf-0.205
Token come
Token ID1282
Feature activation+7.66e+00

Pos logit contributions
angers+0.161
ail+0.146
bled+0.146
uing+0.145
aj+0.142
Neg logit contributions
 course-0.121
 sorts-0.114
 juicy-0.107
 tiger-0.105
 elephant-0.096
Token back
Token ID736
Feature activation+9.41e+00

Pos logit contributions
angers+0.284
ail+0.261
uing+0.255
bled+0.253
aj+0.251
Neg logit contributions
 course-0.213
 sorts-0.196
 tiger-0.183
 juicy-0.183
 animal-0.163
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
angers+0.351
ail+0.319
aj+0.311
uing+0.309
bled+0.305
Neg logit contributions
 course-0.260
 sorts-0.240
 juicy-0.229
 tiger-0.224
 elephant-0.203
Token<|endoftext|>
Token ID50256
Feature activation-2.24e+00

Pos logit contributions
angers+0.055
ail+0.049
aj+0.048
bled+0.046
uing+0.046
Neg logit contributions
 course-0.048
 sorts-0.046
 juicy-0.045
 tiger-0.043
 piece-0.041
TokenOnce
Token ID7454
Feature activation+2.69e+00

Pos logit contributions
 course+0.071
 sorts+0.069
 juicy+0.068
 tiger+0.064
 gir+0.061
Neg logit contributions
angers-0.072
ail-0.064
aj-0.062
bled-0.061
uing-0.058
Token there
Token ID612
Feature activation+2.27e-01

Pos logit contributions
angers+0.091
immers+0.079
anks+0.078
bled+0.078
uing+0.074
Neg logit contributions
 course-0.086
 sorts-0.085
 juicy-0.077
 piece-0.075
 of-0.074
Token was
Token ID373
Feature activation-3.45e+00

Pos logit contributions
angers+0.011
aj+0.010
bled+0.009
ail+0.009
uing+0.009
Neg logit contributions
 course-0.005
 sorts-0.004
 juicy-0.004
 tiger-0.004
 animal-0.003
Token be
Token ID307
Feature activation+2.64e+00

Pos logit contributions
 course+0.062
 sorts+0.062
 juicy+0.058
 tiger+0.055
 animal+0.053
Neg logit contributions
angers-0.078
bled-0.072
ail-0.072
uing-0.069
aj-0.069
Token much
Token ID881
Feature activation-8.57e-01

Pos logit contributions
angers+0.086
bled+0.086
ail+0.081
aj+0.080
uing+0.079
Neg logit contributions
 course-0.075
 sorts-0.074
 tiger-0.071
 juicy-0.067
 gir-0.064
Token better
Token ID1365
Feature activation+3.84e+00

Pos logit contributions
 course+0.026
 sorts+0.025
 tiger+0.024
 deer+0.021
e+0.021
Neg logit contributions
angers-0.027
aj-0.026
ail-0.024
uing-0.024
ups-0.024
Token than
Token ID621
Feature activation+8.03e-01

Pos logit contributions
angers+0.151
ail+0.136
aj+0.136
bled+0.134
uing+0.132
Neg logit contributions
 course-0.098
 sorts-0.093
 juicy-0.087
 tiger-0.083
 elephant-0.077
Token throwing
Token ID9644
Feature activation+1.11e+00

Pos logit contributions
angers+0.031
bled+0.027
ail+0.027
aj+0.027
uing+0.027
Neg logit contributions
 sorts-0.020
 course-0.020
 juicy-0.018
 tiger-0.018
 animal-0.016
Token them
Token ID606
Feature activation+9.23e+00

Pos logit contributions
angers+0.038
ail+0.034
bled+0.034
uing+0.034
immers+0.034
Neg logit contributions
 sorts-0.030
 course-0.028
 juicy-0.027
 tiger-0.027
 spe-0.025
Token away
Token ID1497
Feature activation+8.00e+00

Pos logit contributions
angers+0.315
ail+0.287
aj+0.285
uing+0.282
bled+0.278
Neg logit contributions
 course-0.265
 sorts-0.262
 juicy-0.245
 tiger-0.242
 deer-0.225
Token."
Token ID526
Feature activation-6.57e-01

Pos logit contributions
angers+0.280
aj+0.258
ail+0.253
uing+0.253
bled+0.245
Neg logit contributions
 course-0.220
 sorts-0.208
 juicy-0.197
 tiger-0.196
 elephant-0.180
Token
Token ID198
Feature activation+8.60e-01

Pos logit contributions
 course+0.019
 sorts+0.018
 juicy+0.017
 tiger+0.017
 animal+0.016
Neg logit contributions
angers-0.023
ail-0.021
aj-0.021
bled-0.020
uing-0.020
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
angers+0.031
ail+0.028
aj+0.028
bled+0.027
uing+0.027
Neg logit contributions
 course-0.024
 sorts-0.023
 juicy-0.022
 tiger-0.021
 animal-0.020
TokenTom
Token ID13787
Feature activation-4.01e-01

Pos logit contributions
angers+0.006
ail+0.005
aj+0.005
uing+0.005
bled+0.005
Neg logit contributions
 sorts-0.005
 course-0.005
 juicy-0.005
 tiger-0.005
 piece-0.005
Token afraid
Token ID7787
Feature activation-1.20e+00

Pos logit contributions
 course+0.013
 sorts+0.012
 juicy+0.011
 tiger+0.010
 ribbon+0.010
Neg logit contributions
angers-0.015
bled-0.014
ail-0.014
aj-0.014
uing-0.013
Token they
Token ID484
Feature activation+1.16e+00

Pos logit contributions
 course+0.027
 sorts+0.026
 juicy+0.024
 tiger+0.022
 piece+0.021
Neg logit contributions
angers-0.049
ail-0.045
aj-0.044
uing-0.044
bled-0.043
Token wouldn
Token ID3636
Feature activation+2.32e+00

Pos logit contributions
angers+0.038
ail+0.036
bled+0.034
uing+0.034
aj+0.033
Neg logit contributions
 course-0.034
 sorts-0.033
 juicy-0.031
 tiger-0.030
 turkey-0.029
Token't
Token ID470
Feature activation+1.33e+00

Pos logit contributions
angers+0.077
ail+0.070
bled+0.068
uing+0.066
aj+0.066
Neg logit contributions
 course-0.072
 sorts-0.071
 juicy-0.068
 tiger-0.064
 animal-0.060
Token pass
Token ID1208
Feature activation+1.81e+00

Pos logit contributions
angers+0.055
aj+0.049
ail+0.049
bled+0.049
uing+0.047
Neg logit contributions
 course-0.032
 sorts-0.031
 juicy-0.029
 tiger-0.028
 animal-0.026
Token him
Token ID683
Feature activation+9.14e+00

Pos logit contributions
angers+0.066
ail+0.059
bled+0.058
aj+0.057
uing+0.057
Neg logit contributions
 course-0.050
 sorts-0.048
 juicy-0.046
 tiger-0.044
 piece-0.041
Token.
Token ID13
Feature activation+9.34e-01

Pos logit contributions
angers+0.330
ail+0.300
aj+0.295
uing+0.290
bled+0.289
Neg logit contributions
 course-0.257
 sorts-0.247
 juicy-0.233
 tiger-0.223
 elephant-0.207
Token
Token ID220
Feature activation+5.14e+00

Pos logit contributions
angers+0.035
bled+0.032
ail+0.032
uing+0.031
aj+0.031
Neg logit contributions
 course-0.026
 sorts-0.024
 tiger-0.023
 juicy-0.023
 elephant-0.021
Token
Token ID198
Feature activation+1.80e+00

Pos logit contributions
angers+0.238
bled+0.218
uing+0.217
immers+0.217
 spine+0.215
Neg logit contributions
 sorts-0.075
 course-0.075
-0.073
 a-0.063
 tiger-0.061
Token
Token ID198
Feature activation+1.01e+00

Pos logit contributions
angers+0.071
bled+0.063
ail+0.063
aj+0.063
uing+0.062
Neg logit contributions
 course-0.047
 sorts-0.044
 juicy-0.040
 tiger-0.040
 animal-0.036
TokenHe
Token ID1544
Feature activation+6.88e-02

Pos logit contributions
angers+0.034
ail+0.031
aj+0.030
bled+0.030
uing+0.030
Neg logit contributions
 course-0.030
 sorts-0.029
 juicy-0.028
 tiger-0.026
 elephant-0.025
Token the
Token ID262
Feature activation+1.98e+00

Pos logit contributions
 ribbon+0.018
 juicy+0.018
 course+0.018
leaf+0.017
 arrow+0.016
Neg logit contributions
ail-0.030
angers-0.029
ups-0.028
bled-0.028
uing-0.027
Token other
Token ID584
Feature activation+1.49e+00

Pos logit contributions
angers+0.059
ail+0.054
immers+0.051
ups+0.051
aj+0.051
Neg logit contributions
 course-0.058
 sorts-0.057
 juicy-0.053
 spe-0.051
bug-0.050
Token animals
Token ID4695
Feature activation-1.53e+00

Pos logit contributions
angers+0.047
ail+0.043
uing+0.041
immers+0.040
ups+0.040
Neg logit contributions
 course-0.043
 juicy-0.040
 sorts-0.038
 spe-0.038
 nut-0.037
Token would
Token ID561
Feature activation+1.06e-01

Pos logit contributions
 course+0.041
 sorts+0.039
 juicy+0.039
 tiger+0.038
 snowball+0.037
Neg logit contributions
angers-0.050
ail-0.049
uing-0.047
bled-0.047
iked-0.043
Token cheer
Token ID14042
Feature activation+2.61e+00

Pos logit contributions
uing+0.003
angers+0.003
ail+0.003
 conscience+0.003
line+0.003
Neg logit contributions
 sorts-0.003
 course-0.003
 juicy-0.003
 tiger-0.003
 turkey-0.003
Token him
Token ID683
Feature activation+9.14e+00

Pos logit contributions
angers+0.101
ail+0.090
aj+0.089
bled+0.088
uing+0.086
Neg logit contributions
 course-0.069
 sorts-0.066
 juicy-0.062
 tiger-0.060
 animal-0.056
Token on
Token ID319
Feature activation+5.96e-01

Pos logit contributions
angers+0.300
ail+0.275
uing+0.274
bled+0.272
aj+0.266
Neg logit contributions
 course-0.287
 sorts-0.269
 juicy-0.252
 tiger-0.242
 elephant-0.233
Token!
Token ID0
Feature activation+6.28e-01

Pos logit contributions
angers+0.021
uing+0.020
bled+0.019
ail+0.019
immers+0.018
Neg logit contributions
 sorts-0.015
 course-0.014
 juicy-0.014
igator-0.013
leaf-0.013
Token
Token ID198
Feature activation+1.80e+00

Pos logit contributions
angers+0.021
ail+0.019
aj+0.018
bled+0.018
uing+0.018
Neg logit contributions
 course-0.019
 sorts-0.018
 juicy-0.018
 tiger-0.016
 piece-0.016
Token
Token ID198
Feature activation+1.06e+00

Pos logit contributions
angers+0.060
ail+0.055
bled+0.053
aj+0.053
uing+0.052
Neg logit contributions
 course-0.054
 sorts-0.053
 juicy-0.051
 tiger-0.048
 elephant-0.046
TokenIt
Token ID1026
Feature activation+1.36e+00

Pos logit contributions
bled+0.029
uing+0.029
angers+0.029
ail+0.028
ups+0.027
Neg logit contributions
 sorts-0.030
 elephant-0.028
 juicy-0.028
 piece-0.028
 spe-0.027
Token to
Token ID284
Feature activation-1.44e+00

Pos logit contributions
angers+0.022
aj+0.020
ail+0.020
uing+0.019
bled+0.018
Neg logit contributions
 course-0.017
 sorts-0.017
 juicy-0.016
 tiger-0.016
 spe-0.015
Token come
Token ID1282
Feature activation+6.16e+00

Pos logit contributions
 sorts+0.038
 course+0.036
 juicy+0.035
 tiger+0.033
 gir+0.031
Neg logit contributions
angers-0.049
ail-0.046
uing-0.045
aj-0.044
bled-0.044
Token and
Token ID290
Feature activation-4.62e-01

Pos logit contributions
angers+0.237
ail+0.217
aj+0.214
uing+0.211
bled+0.211
Neg logit contributions
 course-0.163
 sorts-0.153
 juicy-0.141
 tiger-0.134
 gir-0.124
Token sn
Token ID3013
Feature activation+1.05e+00

Pos logit contributions
 course+0.012
 sorts+0.012
 juicy+0.011
 tiger+0.010
 animal+0.010
Neg logit contributions
angers-0.017
ail-0.016
aj-0.015
uing-0.015
bled-0.015
Tokenuggle
Token ID33498
Feature activation+4.66e+00

Pos logit contributions
angers+0.031
uing+0.026
bled+0.026
ail+0.025
aj+0.025
Neg logit contributions
 course-0.036
 sorts-0.032
 juicy-0.031
 tiger-0.030
 balloon-0.029
Token him
Token ID683
Feature activation+9.13e+00

Pos logit contributions
angers+0.207
ail+0.182
uing+0.179
bled+0.178
anks+0.177
Neg logit contributions
 course-0.085
 sorts-0.082
 juicy-0.081
 tiger-0.074
 balloon-0.072
Token.
Token ID13
Feature activation+1.11e-01

Pos logit contributions
angers+0.368
ail+0.334
aj+0.329
bled+0.328
uing+0.323
Neg logit contributions
 course-0.222
 sorts-0.212
 juicy-0.198
 tiger-0.190
 animal-0.175
Token
Token ID198
Feature activation+8.66e-01

Pos logit contributions
angers+0.004
aj+0.003
ail+0.003
bled+0.003
uing+0.003
Neg logit contributions
 course-0.004
 sorts-0.003
 juicy-0.003
 tiger-0.003
 piece-0.003
Token
Token ID198
Feature activation+1.97e-01

Pos logit contributions
angers+0.029
ail+0.027
aj+0.026
bled+0.025
uing+0.025
Neg logit contributions
 course-0.026
 sorts-0.025
 juicy-0.024
 tiger-0.023
 elephant-0.022
TokenOne
Token ID3198
Feature activation-1.13e+00

Pos logit contributions
angers+0.006
aj+0.006
ail+0.006
uing+0.006
bled+0.006
Neg logit contributions
 sorts-0.006
 course-0.006
 juicy-0.006
 tiger-0.005
 elephant-0.005
Token night
Token ID1755
Feature activation+1.40e+00

Pos logit contributions
 course+0.037
leaf+0.033
 elephant+0.032
 ribbon+0.032
 juicy+0.032
Neg logit contributions
ail-0.028
aj-0.028
angers-0.027
 conscience-0.024
ippers-0.023
Token them
Token ID606
Feature activation+7.50e+00

Pos logit contributions
angers+0.074
ail+0.067
bled+0.066
aj+0.066
uing+0.064
Neg logit contributions
 course-0.046
 sorts-0.044
 juicy-0.041
 tiger-0.040
 elephant-0.036
Token safe
Token ID3338
Feature activation+4.70e+00

Pos logit contributions
angers+0.268
ail+0.252
aj+0.249
uing+0.244
bled+0.243
Neg logit contributions
 course-0.211
 sorts-0.203
 tiger-0.189
 juicy-0.185
 elephant-0.171
Token instead
Token ID2427
Feature activation+5.42e+00

Pos logit contributions
angers+0.179
ail+0.162
aj+0.160
bled+0.160
uing+0.156
Neg logit contributions
 course-0.123
 sorts-0.119
 juicy-0.111
 tiger-0.107
 elephant-0.098
Token of
Token ID286
Feature activation-3.11e-01

Pos logit contributions
angers+0.222
ail+0.205
bled+0.201
aj+0.200
uing+0.197
Neg logit contributions
 course-0.125
 sorts-0.120
 juicy-0.113
 tiger-0.109
 elephant-0.098
Token showing
Token ID4478
Feature activation+1.79e+00

Pos logit contributions
 sorts+0.008
 course+0.008
 juicy+0.008
 tiger+0.007
leaf+0.007
Neg logit contributions
angers-0.011
bled-0.010
aj-0.010
ail-0.010
uing-0.010
Token them
Token ID606
Feature activation+9.10e+00

Pos logit contributions
angers+0.063
ail+0.057
aj+0.056
bled+0.055
uing+0.055
Neg logit contributions
 course-0.052
 sorts-0.050
 juicy-0.048
 tiger-0.046
 animal-0.043
Token off
Token ID572
Feature activation+3.73e+00

Pos logit contributions
angers+0.334
ail+0.311
aj+0.305
uing+0.302
bled+0.298
Neg logit contributions
 course-0.244
 sorts-0.230
 juicy-0.221
 tiger-0.216
 elephant-0.199
Token to
Token ID284
Feature activation+1.90e+00

Pos logit contributions
angers+0.131
aj+0.121
ail+0.120
uing+0.116
bled+0.114
Neg logit contributions
 course-0.104
 sorts-0.098
 juicy-0.093
 tiger-0.092
 elephant-0.085
Token everyone
Token ID2506
Feature activation+3.99e+00

Pos logit contributions
angers+0.071
ail+0.064
aj+0.063
bled+0.063
uing+0.062
Neg logit contributions
 course-0.050
 sorts-0.048
 juicy-0.046
 tiger-0.044
 piece-0.041
Token.
Token ID13
Feature activation+4.81e-01

Pos logit contributions
angers+0.136
ail+0.129
uing+0.124
aj+0.123
bled+0.118
Neg logit contributions
 course-0.112
 juicy-0.105
 sorts-0.104
 tiger-0.101
 gir-0.093
Token<|endoftext|>
Token ID50256
Feature activation-2.30e+00

Pos logit contributions
angers+0.016
ail+0.014
aj+0.014
bled+0.013
uing+0.013
Neg logit contributions
 course-0.015
 sorts-0.014
 juicy-0.014
 tiger-0.013
 piece-0.013
Token and
Token ID290
Feature activation-3.04e+00

Pos logit contributions
angers+0.059
ail+0.054
bled+0.052
aj+0.052
uing+0.050
Neg logit contributions
 course-0.044
 sorts-0.044
 juicy-0.043
 tiger-0.041
 gir-0.037
Token never
Token ID1239
Feature activation+8.82e-01

Pos logit contributions
 course+0.079
 sorts+0.074
 tiger+0.069
 juicy+0.068
 turkey+0.063
Neg logit contributions
angers-0.113
ail-0.104
bled-0.102
aj-0.101
uing-0.098
Token let
Token ID1309
Feature activation-1.12e+00

Pos logit contributions
angers+0.034
ail+0.031
aj+0.031
bled+0.031
uing+0.030
Neg logit contributions
 course-0.022
 sorts-0.021
 juicy-0.020
 tiger-0.019
 animal-0.017
Token fear
Token ID3252
Feature activation+2.68e+00

Pos logit contributions
 course+0.030
 sorts+0.030
 juicy+0.028
 tiger+0.026
 piece+0.024
Neg logit contributions
angers-0.041
ail-0.038
bled-0.036
uing-0.036
aj-0.036
Token hold
Token ID1745
Feature activation+3.73e+00

Pos logit contributions
angers+0.103
ail+0.092
aj+0.092
bled+0.090
uing+0.088
Neg logit contributions
 course-0.071
 sorts-0.067
 juicy-0.064
 tiger-0.061
 deer-0.057
Token them
Token ID606
Feature activation+9.08e+00

Pos logit contributions
angers+0.137
ail+0.128
bled+0.125
aj+0.119
uing+0.119
Neg logit contributions
 course-0.100
 sorts-0.099
 juicy-0.092
 tiger-0.090
 gir-0.085
Token back
Token ID736
Feature activation+8.45e+00

Pos logit contributions
angers+0.316
ail+0.291
bled+0.284
aj+0.284
uing+0.281
Neg logit contributions
 course-0.264
 sorts-0.258
 juicy-0.239
 tiger-0.234
 elephant-0.218
Token.
Token ID13
Feature activation+4.32e-01

Pos logit contributions
angers+0.302
ail+0.278
aj+0.273
bled+0.268
uing+0.265
Neg logit contributions
 course-0.238
 sorts-0.230
 juicy-0.215
 tiger-0.209
 turkey-0.194
Token<|endoftext|>
Token ID50256
Feature activation-2.45e+00

Pos logit contributions
angers+0.015
ail+0.013
aj+0.013
bled+0.013
uing+0.013
Neg logit contributions
 course-0.013
 sorts-0.012
 juicy-0.012
 tiger-0.011
 piece-0.011
TokenOnce
Token ID7454
Feature activation+1.99e+00

Pos logit contributions
 course+0.076
 sorts+0.074
 juicy+0.072
 tiger+0.067
 elephant+0.064
Neg logit contributions
angers-0.081
ail-0.073
aj-0.070
bled-0.070
uing-0.066
Token upon
Token ID2402
Feature activation-2.47e+00

Pos logit contributions
angers+0.068
anks+0.058
immers+0.058
bled+0.056
uing+0.056
Neg logit contributions
 course-0.061
 sorts-0.060
 juicy-0.056
 tiger-0.054
 piece-0.054
Token peaceful
Token ID12309
Feature activation-5.36e-01

Pos logit contributions
ail+0.105
immers+0.104
angers+0.103
aj+0.101
 surroundings+0.099
Neg logit contributions
 course-0.084
 sorts-0.084
 tiger-0.081
igator-0.080
 spe-0.079
Token feeling
Token ID4203
Feature activation-4.91e-01

Pos logit contributions
 course+0.015
 juicy+0.015
 sorts+0.014
 tiger+0.014
leaf+0.013
Neg logit contributions
angers-0.017
ail-0.016
immers-0.015
uing-0.015
aj-0.015
Token it
Token ID340
Feature activation+5.70e+00

Pos logit contributions
 course+0.009
 sorts+0.009
 juicy+0.008
 tiger+0.008
 elephant+0.007
Neg logit contributions
angers-0.022
ail-0.020
bled-0.020
uing-0.019
aj-0.019
Token always
Token ID1464
Feature activation+3.42e+00

Pos logit contributions
angers+0.227
ail+0.212
bled+0.211
uing+0.205
aj+0.201
Neg logit contributions
 course-0.133
 sorts-0.126
 juicy-0.119
 tiger-0.117
 animal-0.106
Token gave
Token ID2921
Feature activation+2.92e+00

Pos logit contributions
angers+0.146
ail+0.132
aj+0.129
bled+0.128
uing+0.126
Neg logit contributions
 course-0.079
 sorts-0.075
 juicy-0.070
 tiger-0.065
 animal-0.061
Token him
Token ID683
Feature activation+9.06e+00

Pos logit contributions
angers+0.102
ail+0.092
bled+0.090
aj+0.089
uing+0.088
Neg logit contributions
 course-0.086
 sorts-0.083
 juicy-0.079
 tiger-0.076
 elephant-0.071
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
ail+0.341
angers+0.341
aj+0.335
uing+0.318
bled+0.313
Neg logit contributions
 course-0.204
 sorts-0.185
 tiger-0.178
 juicy-0.172
 spe-0.164
Token<|endoftext|>
Token ID50256
Feature activation-2.01e+00

Pos logit contributions
angers+0.050
ail+0.045
aj+0.043
bled+0.041
uing+0.041
Neg logit contributions
 course-0.050
 sorts-0.048
 juicy-0.047
 piece-0.043
 tiger-0.043
TokenOnce
Token ID7454
Feature activation+2.74e+00

Pos logit contributions
 course+0.067
 sorts+0.066
 juicy+0.065
 tiger+0.061
 gir+0.059
Neg logit contributions
angers-0.061
ail-0.054
aj-0.051
bled-0.051
uing-0.048
Token upon
Token ID2402
Feature activation-1.93e+00

Pos logit contributions
angers+0.092
anks+0.078
bled+0.077
immers+0.077
uing+0.074
Neg logit contributions
 course-0.089
 sorts-0.089
 juicy-0.080
 tiger-0.078
 piece-0.077
Token a
Token ID257
Feature activation-6.08e+00

Pos logit contributions
 course+0.043
 sorts+0.043
 elephant+0.038
 spe+0.037
 tiger+0.037
Neg logit contributions
angers-0.066
bled-0.065
aj-0.063
ail-0.062
iece-0.061
Token tried
Token ID3088
Feature activation+2.92e+00

Pos logit contributions
 course+0.047
 sorts+0.045
 turkey+0.042
 juicy+0.042
 tiger+0.041
Neg logit contributions
angers-0.070
bled-0.069
ail-0.066
iece-0.063
aj-0.063
Token to
Token ID284
Feature activation+2.01e+00

Pos logit contributions
angers+0.117
ail+0.106
aj+0.105
bled+0.104
uing+0.101
Neg logit contributions
 course-0.072
 sorts-0.069
 juicy-0.065
 tiger-0.063
 animal-0.057
Token make
Token ID787
Feature activation+1.38e+00

Pos logit contributions
uing+0.064
angers+0.062
ail+0.061
bled+0.061
iece+0.058
Neg logit contributions
 sorts-0.056
 juicy-0.053
 course-0.053
 tiger-0.049
 gir-0.047
Token them
Token ID606
Feature activation+7.97e+00

Pos logit contributions
angers+0.058
ail+0.054
bled+0.052
uing+0.052
aj+0.052
Neg logit contributions
 course-0.030
 sorts-0.028
 juicy-0.027
 tiger-0.025
igator-0.023
Token lift
Token ID10303
Feature activation+3.46e+00

Pos logit contributions
angers+0.287
ail+0.267
uing+0.266
aj+0.257
bled+0.256
Neg logit contributions
 course-0.221
 sorts-0.200
 tiger-0.189
 juicy-0.188
 turkey-0.174
Token him
Token ID683
Feature activation+9.04e+00

Pos logit contributions
angers+0.129
ail+0.117
bled+0.115
uing+0.115
aj+0.114
Neg logit contributions
 course-0.092
 sorts-0.089
 juicy-0.083
 tiger-0.080
 elephant-0.075
Token up
Token ID510
Feature activation+5.06e+00

Pos logit contributions
angers+0.322
ail+0.295
uing+0.290
bled+0.286
aj+0.286
Neg logit contributions
 course-0.260
 sorts-0.249
 juicy-0.231
 tiger-0.223
 elephant-0.208
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
angers+0.161
uing+0.148
ail+0.147
aj+0.144
bled+0.142
Neg logit contributions
 course-0.154
 sorts-0.143
 tiger-0.139
leaf-0.135
 juicy-0.135
Token He
Token ID679
Feature activation+4.51e-01

Pos logit contributions
angers+0.053
ail+0.049
bled+0.049
uing+0.048
aj+0.048
Neg logit contributions
 course-0.040
 sorts-0.038
 juicy-0.036
 tiger-0.035
-0.032
Token worked
Token ID3111
Feature activation+1.35e+00

Pos logit contributions
ail+0.014
bled+0.014
angers+0.014
uing+0.013
aj+0.012
Neg logit contributions
 course-0.013
 juicy-0.012
 sorts-0.012
 turkey-0.012
 tiger-0.011
Token really
Token ID1107
Feature activation+6.56e-01

Pos logit contributions
angers+0.057
ail+0.053
bled+0.052
uing+0.052
aj+0.051
Neg logit contributions
 course-0.030
 sorts-0.028
 juicy-0.026
 tiger-0.026
 elephant-0.024
Token and
Token ID290
Feature activation-1.64e+00

Pos logit contributions
angers+0.063
ail+0.058
uing+0.056
bled+0.056
aj+0.056
Neg logit contributions
 course-0.044
 sorts-0.043
 tiger-0.040
 juicy-0.040
 animal-0.037
Token was
Token ID373
Feature activation+4.84e-01

Pos logit contributions
 course+0.041
 sorts+0.038
 tiger+0.037
 juicy+0.036
 turkey+0.033
Neg logit contributions
angers-0.063
ail-0.057
bled-0.057
aj-0.056
uing-0.055
Token willing
Token ID4684
Feature activation+8.98e-01

Pos logit contributions
angers+0.016
bled+0.015
ail+0.015
aj+0.015
uing+0.015
Neg logit contributions
 course-0.014
 tiger-0.013
 sorts-0.012
 juicy-0.011
 deer-0.011
Token to
Token ID284
Feature activation+1.66e+00

Pos logit contributions
angers+0.031
ail+0.027
aj+0.027
bled+0.026
uing+0.026
Neg logit contributions
 course-0.028
 sorts-0.026
 juicy-0.025
 tiger-0.024
 elephant-0.022
Token try
Token ID1949
Feature activation+4.91e+00

Pos logit contributions
angers+0.060
ail+0.055
uing+0.054
bled+0.054
aj+0.053
Neg logit contributions
 course-0.044
 sorts-0.044
 juicy-0.041
 tiger-0.040
 turkey-0.037
Token them
Token ID606
Feature activation+9.03e+00

Pos logit contributions
angers+0.182
ail+0.164
aj+0.160
bled+0.160
uing+0.158
Neg logit contributions
 course-0.135
 sorts-0.129
 juicy-0.122
 tiger-0.118
 animal-0.109
Token with
Token ID351
Feature activation+1.41e+00

Pos logit contributions
angers+0.364
ail+0.329
aj+0.326
bled+0.323
uing+0.314
Neg logit contributions
 course-0.222
 sorts-0.212
 juicy-0.199
 tiger-0.188
 animal-0.175
Token her
Token ID607
Feature activation+6.60e+00

Pos logit contributions
angers+0.051
ail+0.046
aj+0.045
bled+0.044
uing+0.044
Neg logit contributions
 course-0.037
 sorts-0.037
 tiger-0.035
 juicy-0.035
 elephant-0.032
Token mom
Token ID1995
Feature activation+2.91e+00

Pos logit contributions
angers+0.221
ail+0.208
aj+0.206
uing+0.194
ippers+0.190
Neg logit contributions
 sorts-0.194
 course-0.192
 juicy-0.175
 tiger-0.170
 deer-0.160
Token by
Token ID416
Feature activation+3.47e+00

Pos logit contributions
angers+0.088
ail+0.085
aj+0.080
uing+0.080
ups+0.076
Neg logit contributions
 course-0.087
 sorts-0.086
 juicy-0.083
 tiger-0.083
 deer-0.078
Token her
Token ID607
Feature activation+4.88e+00

Pos logit contributions
angers+0.120
ail+0.110
bled+0.110
uing+0.107
aj+0.105
Neg logit contributions
 sorts-0.095
 course-0.095
 juicy-0.091
 tiger-0.090
 deer-0.083
Token and
Token ID290
Feature activation-2.01e+00

Pos logit contributions
angers+0.042
aj+0.039
ail+0.037
bled+0.036
uing+0.036
Neg logit contributions
 course-0.018
 sorts-0.017
 juicy-0.015
 tiger-0.015
-0.014
Token the
Token ID262
Feature activation+2.52e+00

Pos logit contributions
 course+0.051
 sorts+0.048
 juicy+0.046
 tiger+0.043
 turkey+0.041
Neg logit contributions
angers-0.078
ail-0.072
bled-0.070
uing-0.069
aj-0.068
Token crowd
Token ID4315
Feature activation-1.75e+00

Pos logit contributions
angers+0.092
ail+0.085
bled+0.083
immers+0.079
balls+0.079
Neg logit contributions
 sorts-0.067
 course-0.064
 juicy-0.058
 spe-0.052
 tiger-0.051
Token was
Token ID373
Feature activation+9.91e-01

Pos logit contributions
 course+0.045
 juicy+0.044
 sorts+0.043
 tiger+0.041
 turkey+0.041
Neg logit contributions
angers-0.062
ail-0.058
bled-0.057
uing-0.055
iece-0.053
Token cheering
Token ID29732
Feature activation+2.85e+00

Pos logit contributions
angers+0.036
bled+0.034
ail+0.033
aj+0.033
uing+0.033
Neg logit contributions
 course-0.027
 sorts-0.025
 juicy-0.023
 tiger-0.023
 turkey-0.022
Token them
Token ID606
Feature activation+9.02e+00

Pos logit contributions
angers+0.113
ail+0.102
bled+0.101
aj+0.100
uing+0.100
Neg logit contributions
 course-0.071
 sorts-0.068
 juicy-0.064
 tiger-0.061
 piece-0.056
Token on
Token ID319
Feature activation+8.22e-01

Pos logit contributions
angers+0.316
ail+0.285
bled+0.284
uing+0.278
aj+0.276
Neg logit contributions
 course-0.267
 sorts-0.252
 juicy-0.240
 tiger-0.228
 animal-0.216
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
angers+0.027
bled+0.025
uing+0.025
ail+0.024
immers+0.023
Neg logit contributions
 sorts-0.023
 course-0.023
 juicy-0.022
igator-0.021
 tiger-0.020
Token
Token ID198
Feature activation+1.94e+00

Pos logit contributions
angers+0.054
ail+0.048
aj+0.048
bled+0.047
uing+0.047
Neg logit contributions
 course-0.041
 sorts-0.039
 juicy-0.036
 tiger-0.036
 animal-0.033
Token
Token ID198
Feature activation+1.17e+00

Pos logit contributions
angers+0.080
aj+0.071
ail+0.070
bled+0.070
uing+0.069
Neg logit contributions
 course-0.047
 sorts-0.044
 juicy-0.040
 tiger-0.039
-0.037
TokenThe
Token ID464
Feature activation+3.25e-02

Pos logit contributions
angers+0.039
bled+0.035
ail+0.035
uing+0.034
aj+0.033
Neg logit contributions
 course-0.035
 sorts-0.035
 juicy-0.034
 tiger-0.033
 elephant-0.031
Token tw
Token ID665
Feature activation-1.24e+00

Pos logit contributions
 sorts+0.018
 tiger+0.018
 course+0.018
 elephant+0.016
leaf+0.016
Neg logit contributions
bled-0.026
angers-0.026
ail-0.025
uing-0.024
 conscience-0.024
Tokenigs
Token ID9235
Feature activation+5.95e-01

Pos logit contributions
 course+0.048
 sorts+0.047
 juicy+0.044
 tiger+0.042
 piece+0.041
Neg logit contributions
angers-0.032
bled-0.026
ail-0.025
aj-0.025
uing-0.024
Token it
Token ID340
Feature activation+6.07e+00

Pos logit contributions
angers+0.025
ail+0.023
bled+0.023
aj+0.022
uing+0.022
Neg logit contributions
 course-0.013
 sorts-0.013
 juicy-0.012
 tiger-0.011
 animal-0.010
Token would
Token ID561
Feature activation+1.35e+00

Pos logit contributions
angers+0.244
ail+0.224
bled+0.221
aj+0.219
uing+0.217
Neg logit contributions
 course-0.143
 sorts-0.140
 juicy-0.128
 tiger-0.126
 animal-0.115
Token give
Token ID1577
Feature activation+2.51e+00

Pos logit contributions
angers+0.044
ail+0.042
uing+0.042
bled+0.040
aj+0.038
Neg logit contributions
 sorts-0.037
 course-0.037
 tiger-0.036
 juicy-0.035
 turkey-0.033
Token him
Token ID683
Feature activation+9.00e+00

Pos logit contributions
angers+0.088
ail+0.079
bled+0.078
aj+0.077
uing+0.076
Neg logit contributions
 course-0.073
 sorts-0.071
 juicy-0.066
 tiger-0.065
 elephant-0.060
Token a
Token ID257
Feature activation-1.84e+00

Pos logit contributions
angers+0.337
ail+0.325
aj+0.320
uing+0.310
bled+0.307
Neg logit contributions
 course-0.217
 sorts-0.209
 tiger-0.199
 juicy-0.189
 elephant-0.178
Token reward
Token ID6721
Feature activation+1.46e+00

Pos logit contributions
 course+0.048
 sorts+0.045
 tiger+0.041
 elephant+0.040
e+0.039
Neg logit contributions
ail-0.063
uing-0.061
aj-0.060
angers-0.059
 conscience-0.056
Token.
Token ID13
Feature activation+5.00e-01

Pos logit contributions
angers+0.053
ail+0.048
bled+0.047
uing+0.046
aj+0.046
Neg logit contributions
 course-0.040
 sorts-0.039
 juicy-0.037
 tiger-0.036
 gir-0.033
Token The
Token ID383
Feature activation+1.76e-01

Pos logit contributions
angers+0.016
ail+0.014
aj+0.014
uing+0.013
bled+0.013
Neg logit contributions
 course-0.016
 sorts-0.015
 juicy-0.015
 tiger-0.014
 piece-0.014
Token bird
Token ID6512
Feature activation-2.37e+00

Pos logit contributions
ail+0.007
angers+0.006
bled+0.006
aj+0.006
 conscience+0.006
Neg logit contributions
 sorts-0.005
 course-0.004
leaf-0.003
e-0.003
 juicy-0.003
Token and
Token ID290
Feature activation-1.51e+00

Pos logit contributions
 course+0.002
 sorts+0.002
 juicy+0.002
 tiger+0.002
 turkey+0.002
Neg logit contributions
angers-0.004
ail-0.004
bled-0.004
uing-0.004
aj-0.004
Token believed
Token ID4762
Feature activation+3.10e+00

Pos logit contributions
 course+0.039
 sorts+0.036
 juicy+0.035
 tiger+0.034
 turkey+0.032
Neg logit contributions
angers-0.055
ail-0.050
bled-0.050
aj-0.049
uing-0.048
Token they
Token ID484
Feature activation+2.50e+00

Pos logit contributions
angers+0.131
ail+0.120
bled+0.119
aj+0.117
uing+0.116
Neg logit contributions
 course-0.069
 sorts-0.066
 juicy-0.061
 tiger-0.058
 piece-0.053
Token would
Token ID561
Feature activation+1.69e+00

Pos logit contributions
angers+0.094
ail+0.086
bled+0.085
uing+0.083
aj+0.082
Neg logit contributions
 course-0.065
 sorts-0.063
 juicy-0.060
 tiger-0.059
 turkey-0.054
Token bring
Token ID2222
Feature activation+2.08e+00

Pos logit contributions
angers+0.058
ail+0.055
uing+0.053
bled+0.052
aj+0.051
Neg logit contributions
 sorts-0.045
 course-0.044
 juicy-0.043
 tiger-0.042
 turkey-0.040
Token him
Token ID683
Feature activation+8.98e+00

Pos logit contributions
angers+0.075
ail+0.069
bled+0.068
uing+0.068
aj+0.067
Neg logit contributions
 course-0.053
 sorts-0.051
 juicy-0.049
 tiger-0.048
 elephant-0.044
Token good
Token ID922
Feature activation+1.75e+00

Pos logit contributions
angers+0.280
ail+0.265
aj+0.261
uing+0.252
immers+0.245
Neg logit contributions
 course-0.276
 sorts-0.265
 tiger-0.252
 juicy-0.251
 spe-0.234
Token luck
Token ID8458
Feature activation+4.62e+00

Pos logit contributions
angers+0.053
ail+0.047
aj+0.046
uing+0.046
ippers+0.045
Neg logit contributions
 course-0.056
 sorts-0.054
 juicy-0.053
 tiger-0.052
igator-0.049
Token.
Token ID13
Feature activation+1.24e+00

Pos logit contributions
angers+0.182
ail+0.166
bled+0.162
aj+0.162
uing+0.159
Neg logit contributions
 course-0.116
 sorts-0.111
 juicy-0.105
 tiger-0.101
 elephant-0.093
Token<|endoftext|>
Token ID50256
Feature activation-2.25e+00

Pos logit contributions
angers+0.043
ail+0.038
aj+0.037
bled+0.037
uing+0.036
Neg logit contributions
 course-0.036
 sorts-0.035
 juicy-0.034
 tiger-0.032
 animal-0.030
TokenOnce
Token ID7454
Feature activation+2.48e+00

Pos logit contributions
 course+0.070
 sorts+0.068
 juicy+0.067
 tiger+0.063
 gir+0.060
Neg logit contributions
angers-0.073
ail-0.065
aj-0.063
bled-0.063
uing-0.060
Token available
Token ID1695
Feature activation+2.88e+00

Pos logit contributions
angers+0.112
aj+0.104
ail+0.102
bled+0.102
uing+0.097
Neg logit contributions
 course-0.074
 sorts-0.068
 tiger-0.066
 juicy-0.061
 elephant-0.058
Token so
Token ID523
Feature activation+1.13e+00

Pos logit contributions
angers+0.109
ail+0.100
aj+0.097
bled+0.096
uing+0.096
Neg logit contributions
 course-0.074
 sorts-0.071
 tiger-0.068
 juicy-0.068
 elephant-0.061
Token he
Token ID339
Feature activation+3.16e+00

Pos logit contributions
angers+0.041
ail+0.037
bled+0.037
aj+0.036
uing+0.036
Neg logit contributions
 course-0.032
 sorts-0.031
 juicy-0.029
 tiger-0.028
 elephant-0.026
Token could
Token ID714
Feature activation+9.79e-01

Pos logit contributions
angers+0.103
ail+0.100
aj+0.095
bled+0.093
uing+0.092
Neg logit contributions
 course-0.096
 sorts-0.091
 tiger-0.083
 juicy-0.083
 turkey-0.077
Token pick
Token ID2298
Feature activation+2.24e+00

Pos logit contributions
angers+0.032
ail+0.031
uing+0.030
bled+0.028
aj+0.028
Neg logit contributions
 course-0.028
 sorts-0.028
 tiger-0.026
 juicy-0.026
 gir-0.024
Token them
Token ID606
Feature activation+8.98e+00

Pos logit contributions
angers+0.072
ail+0.067
bled+0.065
uing+0.063
immers+0.062
Neg logit contributions
 course-0.064
 sorts-0.061
 tiger-0.060
 juicy-0.057
 spe-0.055
Token and
Token ID290
Feature activation-9.24e-01

Pos logit contributions
angers+0.312
ail+0.284
bled+0.276
aj+0.275
uing+0.275
Neg logit contributions
 course-0.266
 sorts-0.254
 juicy-0.240
 tiger-0.238
 elephant-0.222
Token make
Token ID787
Feature activation+9.85e-01

Pos logit contributions
 course+0.025
 sorts+0.022
 tiger+0.022
 juicy+0.021
 snowball+0.020
Neg logit contributions
angers-0.032
ail-0.030
uing-0.028
aj-0.028
bled-0.028
Token tasty
Token ID25103
Feature activation-4.75e-01

Pos logit contributions
angers+0.037
ail+0.035
bled+0.033
uing+0.033
aj+0.033
Neg logit contributions
 course-0.025
 sorts-0.023
 tiger-0.023
 juicy-0.022
 elephant-0.021
Token dishes
Token ID16759
Feature activation+1.09e+00

Pos logit contributions
 course+0.013
 tiger+0.012
 sorts+0.012
 elephant+0.011
 arrow+0.011
Neg logit contributions
angers-0.016
ail-0.014
uing-0.014
immers-0.014
anks-0.014
Token with
Token ID351
Feature activation+7.16e-01

Pos logit contributions
angers+0.040
ail+0.037
uing+0.036
bled+0.036
aj+0.035
Neg logit contributions
 course-0.030
 sorts-0.028
 tiger-0.027
 juicy-0.026
 animal-0.024
Token nice
Token ID3621
Feature activation+5.32e-01

Pos logit contributions
 course+0.026
 tiger+0.026
 sorts+0.025
 elephant+0.023
 arrow+0.022
Neg logit contributions
angers-0.040
uing-0.038
bled-0.037
ail-0.037
aj-0.036
Token and
Token ID290
Feature activation-8.64e-01

Pos logit contributions
angers+0.017
aj+0.015
ail+0.014
uing+0.014
bled+0.014
Neg logit contributions
 course-0.017
 sorts-0.016
 tiger-0.015
 juicy-0.015
 arrow-0.014
Token you
Token ID345
Feature activation+9.24e-01

Pos logit contributions
 course+0.020
 sorts+0.017
 tiger+0.017
 elephant+0.015
 snowball+0.015
Neg logit contributions
angers-0.034
ail-0.032
bled-0.032
aj-0.032
uing-0.031
Token can
Token ID460
Feature activation+6.46e-01

Pos logit contributions
angers+0.031
ail+0.030
uing+0.029
aj+0.028
immers+0.027
Neg logit contributions
 course-0.024
 tiger-0.023
 sorts-0.023
 juicy-0.021
 elephant-0.021
Token pick
Token ID2298
Feature activation+2.04e+00

Pos logit contributions
angers+0.026
ail+0.024
bled+0.024
aj+0.023
uing+0.023
Neg logit contributions
 course-0.015
 sorts-0.015
 juicy-0.014
 tiger-0.013
 animal-0.012
Token them
Token ID606
Feature activation+8.97e+00

Pos logit contributions
angers+0.064
ail+0.058
ups+0.054
bled+0.054
aj+0.054
Neg logit contributions
 course-0.059
 sorts-0.058
 tiger-0.054
 juicy-0.052
 piece-0.052
Token and
Token ID290
Feature activation-1.40e+00

Pos logit contributions
angers+0.328
ail+0.298
aj+0.293
uing+0.289
bled+0.288
Neg logit contributions
 course-0.251
 sorts-0.240
 tiger-0.221
 juicy-0.220
 elephant-0.202
Token make
Token ID787
Feature activation+1.11e+00

Pos logit contributions
 course+0.036
 sorts+0.035
 tiger+0.031
 juicy+0.030
 snowball+0.028
Neg logit contributions
angers-0.049
ail-0.045
aj-0.045
uing-0.043
anks-0.042
Token a
Token ID257
Feature activation-1.62e+00

Pos logit contributions
angers+0.035
ail+0.031
aj+0.030
uing+0.030
bled+0.030
Neg logit contributions
 course-0.035
 sorts-0.034
 tiger-0.032
 juicy-0.032
 piece-0.029
Token bou
Token ID35833
Feature activation-1.14e+00

Pos logit contributions
 course+0.041
 sorts+0.038
 tiger+0.032
igator+0.032
leaf+0.031
Neg logit contributions
angers-0.060
ail-0.058
aj-0.057
uing-0.055
 conscience-0.054
Tokenquet
Token ID21108
Feature activation-2.36e+00

Pos logit contributions
 course+0.031
 sorts+0.030
 juicy+0.028
 tiger+0.027
 animal+0.025
Neg logit contributions
angers-0.043
ail-0.039
uing-0.038
bled-0.038
aj-0.037
Token Sally
Token ID25737
Feature activation+1.01e+00

Pos logit contributions
 course+0.001
 sorts+0.001
 juicy+0.001
 tiger+0.001
 animal+0.001
Neg logit contributions
angers-0.001
ail-0.001
bled-0.001
aj-0.001
uing-0.001
Token still
Token ID991
Feature activation+1.88e+00

Pos logit contributions
angers+0.034
ail+0.034
bled+0.031
aj+0.031
uing+0.030
Neg logit contributions
 sorts-0.029
 course-0.029
 juicy-0.026
 tiger-0.025
 turkey-0.024
Token wouldn
Token ID3636
Feature activation+2.29e+00

Pos logit contributions
angers+0.067
ail+0.062
bled+0.061
aj+0.061
uing+0.059
Neg logit contributions
 course-0.053
 sorts-0.050
 juicy-0.047
 tiger-0.047
 deer-0.043
Token't
Token ID470
Feature activation+1.40e+00

Pos logit contributions
angers+0.077
ail+0.069
bled+0.068
uing+0.066
aj+0.066
Neg logit contributions
 course-0.071
 sorts-0.070
 juicy-0.066
 tiger-0.063
 animal-0.060
Token give
Token ID1577
Feature activation+2.27e+00

Pos logit contributions
angers+0.056
ail+0.050
aj+0.050
bled+0.049
uing+0.048
Neg logit contributions
 course-0.035
 sorts-0.034
 juicy-0.032
 tiger-0.030
 animal-0.028
Token him
Token ID683
Feature activation+8.97e+00

Pos logit contributions
angers+0.083
ail+0.075
bled+0.073
aj+0.073
uing+0.072
Neg logit contributions
 course-0.064
 sorts-0.061
 juicy-0.057
 tiger-0.056
 animal-0.051
Token back
Token ID736
Feature activation+8.04e+00

Pos logit contributions
angers+0.329
ail+0.317
uing+0.304
aj+0.303
bled+0.302
Neg logit contributions
 course-0.225
 sorts-0.215
 tiger-0.201
 juicy-0.195
 spe-0.184
Token the
Token ID262
Feature activation+5.45e+00

Pos logit contributions
angers+0.275
ail+0.253
aj+0.246
uing+0.242
bled+0.237
Neg logit contributions
 course-0.232
 sorts-0.217
 juicy-0.212
 tiger-0.209
 gir-0.193
Token violin
Token ID38283
Feature activation-9.74e-01

Pos logit contributions
angers+0.187
ail+0.176
uing+0.170
aj+0.170
ippers+0.168
Neg logit contributions
 course-0.139
 sorts-0.138
 juicy-0.137
 tiger-0.128
 spe-0.127
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
 course+0.028
 sorts+0.027
 juicy+0.026
 tiger+0.025
 deer+0.024
Neg logit contributions
angers-0.032
ail-0.030
uing-0.029
aj-0.028
bled-0.028
Token
Token ID198
Feature activation+1.88e+00

Pos logit contributions
angers+0.044
bled+0.041
aj+0.040
ail+0.040
uing+0.040
Neg logit contributions
 course-0.031
 sorts-0.030
 juicy-0.028
 tiger-0.026
 elephant-0.025
Token try
Token ID1949
Feature activation+3.63e+00

Pos logit contributions
 course+0.001
 sorts+0.001
 tiger+0.001
 juicy+0.001
 gir+0.001
Neg logit contributions
uing-0.001
ail-0.001
angers-0.001
 conscience-0.001
immers-0.001
Token to
Token ID284
Feature activation+1.60e+00

Pos logit contributions
angers+0.148
ail+0.134
aj+0.132
bled+0.132
uing+0.129
Neg logit contributions
 course-0.088
 sorts-0.084
 juicy-0.078
 tiger-0.075
 animal-0.069
Token loosen
Token ID40953
Feature activation+1.34e+00

Pos logit contributions
uing+0.049
ail+0.047
bled+0.047
angers+0.045
immers+0.044
Neg logit contributions
 sorts-0.046
 course-0.045
 gir-0.041
 juicy-0.040
 tiger-0.040
Token the
Token ID262
Feature activation+4.00e+00

Pos logit contributions
angers+0.051
bled+0.048
ail+0.047
uing+0.046
immers+0.044
Neg logit contributions
 sorts-0.030
 course-0.029
leaf-0.025
 juicy-0.025
 tiger-0.024
Token b
Token ID275
Feature activation-3.90e-02

Pos logit contributions
rier+0.141
 spine+0.132
bled+0.132
ail+0.129
bles+0.128
Neg logit contributions
 sorts-0.106
 course-0.077
ris-0.067
-0.066
leaf-0.066
Tokenram
Token ID859
Feature activation+8.95e+00

Pos logit contributions
 course+0.001
 sorts+0.001
 juicy+0.001
 tiger+0.001
 animal+0.001
Neg logit contributions
angers-0.001
ail-0.001
aj-0.001
bled-0.001
uing-0.001
Tokenbles
Token ID7689
Feature activation+6.11e-01

Pos logit contributions
angers+0.177
aj+0.155
 conscience+0.140
 spine+0.128
uddled+0.125
Neg logit contributions
 course-0.359
 a-0.335
 sorts-0.335
 piece-0.335
 tiger-0.334
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
angers+0.023
ail+0.021
uing+0.020
bled+0.020
aj+0.019
Neg logit contributions
 course-0.016
 sorts-0.016
 juicy-0.015
 tiger-0.015
 deer-0.013
Token As
Token ID1081
Feature activation-8.70e-01

Pos logit contributions
angers+0.009
ail+0.008
aj+0.008
bled+0.008
uing+0.008
Neg logit contributions
 course-0.009
 sorts-0.009
 juicy-0.008
 tiger-0.008
 animal-0.008
Token he
Token ID339
Feature activation+1.35e+00

Pos logit contributions
 course+0.029
 sorts+0.028
 juicy+0.026
leaf+0.025
 tiger+0.025
Neg logit contributions
angers-0.024
bled-0.023
ail-0.022
uing-0.020
aj-0.020
Token was
Token ID373
Feature activation-9.51e-01

Pos logit contributions
ail+0.043
bled+0.042
angers+0.042
uddled+0.040
uing+0.038
Neg logit contributions
 sorts-0.037
 course-0.035
 turkey-0.035
 juicy-0.034
 tiger-0.034
Token was
Token ID373
Feature activation+7.58e-01

Pos logit contributions
angers+0.104
ail+0.099
uing+0.094
bled+0.093
immers+0.090
Neg logit contributions
 course-0.086
 sorts-0.085
 juicy-0.082
 turkey-0.076
 tiger-0.076
Token and
Token ID290
Feature activation-2.78e+00

Pos logit contributions
angers+0.030
ail+0.027
aj+0.027
uing+0.027
bled+0.026
Neg logit contributions
 course-0.018
 sorts-0.017
 juicy-0.016
 tiger-0.016
 snowball-0.014
Token wanted
Token ID2227
Feature activation-2.20e+00

Pos logit contributions
 course+0.078
 sorts+0.074
 juicy+0.068
 tiger+0.066
 piece+0.063
Neg logit contributions
angers-0.096
ail-0.089
aj-0.087
bled-0.087
uing-0.085
Token to
Token ID284
Feature activation+1.03e-01

Pos logit contributions
 course+0.061
 sorts+0.060
 juicy+0.056
 tiger+0.054
 deer+0.050
Neg logit contributions
angers-0.080
ail-0.072
bled-0.070
aj-0.070
uing-0.069
Token cheer
Token ID14042
Feature activation+2.72e+00

Pos logit contributions
angers+0.003
ail+0.003
uing+0.003
bled+0.003
immers+0.003
Neg logit contributions
 course-0.003
 sorts-0.003
 juicy-0.003
 tiger-0.003
 gir-0.003
Token him
Token ID683
Feature activation+8.95e+00

Pos logit contributions
angers+0.107
aj+0.099
ail+0.098
bled+0.092
uddled+0.090
Neg logit contributions
 course-0.068
 sorts-0.064
 tiger-0.061
 animal-0.058
 juicy-0.058
Token up
Token ID510
Feature activation+4.79e+00

Pos logit contributions
angers+0.293
ail+0.264
aj+0.259
uing+0.258
bled+0.258
Neg logit contributions
 course-0.288
 sorts-0.271
 juicy-0.257
 tiger-0.246
 elephant-0.232
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
angers+0.155
aj+0.142
uing+0.142
ail+0.142
bled+0.141
Neg logit contributions
 course-0.146
 sorts-0.140
 tiger-0.131
 juicy-0.130
 elephant-0.123
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
angers+0.028
bled+0.025
ail+0.025
uing+0.025
aj+0.024
Neg logit contributions
 course-0.019
 sorts-0.018
 tiger-0.017
 juicy-0.017
 elephant-0.016
Token
Token ID198
Feature activation+6.53e-01

Pos logit contributions
angers+0.051
ail+0.046
aj+0.045
bled+0.045
uing+0.044
Neg logit contributions
 course-0.038
 sorts-0.037
 juicy-0.035
 tiger-0.033
 animal-0.031
TokenThey
Token ID2990
Feature activation-2.19e+00

Pos logit contributions
angers+0.021
uing+0.019
ail+0.019
aj+0.018
bled+0.018
Neg logit contributions
 sorts-0.020
 juicy-0.019
 course-0.019
 spe-0.018
 tiger-0.018
Token Lily
Token ID20037
Feature activation-2.56e+00

Pos logit contributions
 course+0.159
 sorts+0.153
 juicy+0.144
 tiger+0.136
 elephant+0.131
Neg logit contributions
angers-0.227
aj-0.204
bled-0.202
uing-0.202
ail-0.201
Token.
Token ID13
Feature activation-2.58e+00

Pos logit contributions
 course+0.075
 sorts+0.071
 juicy+0.070
 tiger+0.067
 turkey+0.062
Neg logit contributions
angers-0.088
ail-0.082
aj-0.080
bled-0.076
uing-0.075
Token She
Token ID1375
Feature activation-2.93e+00

Pos logit contributions
 course+0.073
 sorts+0.071
 juicy+0.067
 tiger+0.064
 elephant+0.060
Neg logit contributions
angers-0.094
ail-0.085
bled-0.085
aj-0.083
uing-0.083
Token had
Token ID550
Feature activation-5.40e+00

Pos logit contributions
 course+0.089
 sorts+0.084
 juicy+0.078
 tiger+0.075
 turkey+0.071
Neg logit contributions
angers-0.093
ail-0.092
aj-0.087
bled-0.085
uddled-0.082
Token a
Token ID257
Feature activation-6.03e+00

Pos logit contributions
 course+0.127
 sorts+0.119
igator+0.112
 tiger+0.102
oc+0.102
Neg logit contributions
angers-0.213
ail-0.195
ups-0.190
aj-0.189
bled-0.188
Token pair
Token ID5166
Feature activation-9.96e+00

Pos logit contributions
 course+0.159
 sorts+0.157
leaf+0.128
igator+0.125
e+0.124
Neg logit contributions
angers-0.212
ail-0.210
aj-0.202
 conscience-0.196
 parents-0.184
Token of
Token ID286
Feature activation-5.81e+00

Pos logit contributions
 tiger+0.204
 course+0.202
 sorts+0.192
 snowball+0.191
 turkey+0.182
Neg logit contributions
angers-0.419
ail-0.382
bled-0.376
ippers-0.356
line-0.353
Token pink
Token ID11398
Feature activation-5.67e+00

Pos logit contributions
 sorts+0.185
 course+0.184
 tiger+0.168
oc+0.166
 spe+0.164
Neg logit contributions
angers-0.174
ippers-0.150
ail-0.149
aj-0.146
bled-0.136
Token m
Token ID285
Feature activation-2.02e+00

Pos logit contributions
 sorts+0.214
 course+0.205
 juicy+0.196
 tiger+0.185
igator+0.183
Neg logit contributions
angers-0.161
ail-0.136
aj-0.134
ippers-0.129
bled-0.117
Tokenittens
Token ID34978
Feature activation-1.90e+00

Pos logit contributions
 course+0.072
 sorts+0.069
 juicy+0.066
 tiger+0.063
 gir+0.062
Neg logit contributions
angers-0.053
bled-0.049
uing-0.047
ail-0.045
aj-0.045
Token that
Token ID326
Feature activation+5.74e-02

Pos logit contributions
 course+0.047
 sorts+0.046
 juicy+0.042
 tiger+0.040
 snowball+0.037
Neg logit contributions
angers-0.078
ail-0.071
bled-0.069
aj-0.067
uing-0.066
Token a
Token ID257
Feature activation-6.94e+00

Pos logit contributions
angers+0.023
bled+0.021
ail+0.021
aj+0.020
uing+0.020
Neg logit contributions
 course-0.015
 sorts-0.015
 juicy-0.013
 tiger-0.013
leaf-0.012
Token boy
Token ID2933
Feature activation-5.41e+00

Pos logit contributions
 sorts+0.178
 course+0.176
 juicy+0.136
 kinds+0.129
leaf+0.129
Neg logit contributions
angers-0.266
ail-0.252
aj-0.248
bled-0.232
ippers-0.231
Token had
Token ID550
Feature activation-6.22e+00

Pos logit contributions
 sorts+0.091
 course+0.089
 juicy+0.087
 tiger+0.084
leaf+0.077
Neg logit contributions
angers-0.233
ail-0.227
aj-0.211
bled-0.207
uing-0.204
Token a
Token ID257
Feature activation-6.69e+00

Pos logit contributions
 course+0.102
 sorts+0.098
 tiger+0.088
igator+0.079
 juicy+0.078
Neg logit contributions
angers-0.294
aj-0.274
bled-0.272
ail-0.263
ippers-0.256
Token funny
Token ID8258
Feature activation-5.21e+00

Pos logit contributions
 sorts+0.173
 course+0.171
leaf+0.135
igator+0.130
 juicy+0.129
Neg logit contributions
angers-0.242
ail-0.232
aj-0.227
 conscience-0.214
uing-0.209
Token pair
Token ID5166
Feature activation-9.92e+00

Pos logit contributions
 course+0.152
 sorts+0.147
 juicy+0.131
leaf+0.126
igator+0.122
Neg logit contributions
angers-0.179
ail-0.165
aj-0.159
 conscience-0.153
ippers-0.152
Token of
Token ID286
Feature activation-5.89e+00

Pos logit contributions
 juicy+0.217
 sorts+0.208
 tiger+0.207
 turkey+0.205
 course+0.203
Neg logit contributions
angers-0.379
bled-0.336
ail-0.331
line-0.326
iece-0.322
Token boots
Token ID14412
Feature activation-5.14e+00

Pos logit contributions
 sorts+0.182
 course+0.175
+0.158
 spe+0.158
oc+0.154
Neg logit contributions
angers-0.189
ail-0.164
aj-0.160
ippers-0.159
bled-0.151
Token.
Token ID13
Feature activation-1.98e+00

Pos logit contributions
 sorts+0.125
 juicy+0.120
 course+0.116
 tiger+0.107
 turkey+0.102
Neg logit contributions
angers-0.207
ail-0.187
bled-0.178
uddled-0.174
uing-0.173
Token He
Token ID679
Feature activation-1.61e+00

Pos logit contributions
 course+0.064
 sorts+0.061
 juicy+0.058
 tiger+0.056
 deer+0.053
Neg logit contributions
angers-0.065
ail-0.057
aj-0.056
bled-0.056
uing-0.055
Token loved
Token ID6151
Feature activation-3.79e+00

Pos logit contributions
 course+0.043
 sorts+0.042
 juicy+0.037
 tiger+0.036
 turkey+0.034
Neg logit contributions
angers-0.060
ail-0.056
aj-0.055
bled-0.053
uing-0.051
Token Sue
Token ID26089
Feature activation-1.91e+00

Pos logit contributions
 course+0.149
 sorts+0.144
 juicy+0.135
 tiger+0.127
 elephant+0.124
Neg logit contributions
angers-0.226
aj-0.204
bled-0.203
uing-0.202
ail-0.199
Token.
Token ID13
Feature activation-2.46e+00

Pos logit contributions
 course+0.060
 sorts+0.059
 juicy+0.055
 tiger+0.054
leaf+0.051
Neg logit contributions
angers-0.058
ail-0.057
aj-0.055
uing-0.050
bled-0.050
Token She
Token ID1375
Feature activation-2.81e+00

Pos logit contributions
 course+0.069
 sorts+0.066
 juicy+0.062
 tiger+0.060
 piece+0.057
Neg logit contributions
angers-0.089
ail-0.079
aj-0.078
bled-0.077
uing-0.075
Token had
Token ID550
Feature activation-5.28e+00

Pos logit contributions
 course+0.085
 sorts+0.080
 juicy+0.075
 tiger+0.072
 snowball+0.068
Neg logit contributions
ail-0.088
angers-0.088
aj-0.082
bled-0.080
uddled-0.079
Token a
Token ID257
Feature activation-5.96e+00

Pos logit contributions
 course+0.121
 sorts+0.111
igator+0.106
 tiger+0.100
oc+0.096
Neg logit contributions
angers-0.211
ail-0.195
ups-0.191
bled-0.188
aj-0.187
Token pair
Token ID5166
Feature activation-9.87e+00

Pos logit contributions
 course+0.155
 sorts+0.153
leaf+0.127
igator+0.123
e+0.121
Neg logit contributions
angers-0.210
ail-0.209
aj-0.200
 conscience-0.194
ippers-0.183
Token of
Token ID286
Feature activation-5.73e+00

Pos logit contributions
 tiger+0.208
 course+0.206
 snowball+0.192
 sorts+0.192
 turkey+0.188
Neg logit contributions
angers-0.413
ail-0.377
bled-0.368
ippers-0.349
line-0.348
Token incredible
Token ID8082
Feature activation-4.27e+00

Pos logit contributions
 course+0.180
 sorts+0.179
 tiger+0.166
oc+0.163
 spe+0.162
Neg logit contributions
angers-0.173
ippers-0.149
ail-0.149
aj-0.145
bled-0.137
Token m
Token ID285
Feature activation-1.87e+00

Pos logit contributions
 course+0.148
 sorts+0.140
 juicy+0.139
 tiger+0.137
igator+0.131
Neg logit contributions
angers-0.122
ail-0.112
aj-0.110
ippers-0.104
uing-0.099
Tokenittens
Token ID34978
Feature activation-1.72e+00

Pos logit contributions
 course+0.062
 sorts+0.060
 juicy+0.055
 tiger+0.053
 gir+0.053
Neg logit contributions
angers-0.053
bled-0.049
uing-0.047
aj-0.046
ail-0.044
Token.
Token ID13
Feature activation-8.27e-01

Pos logit contributions
 course+0.043
 sorts+0.042
 juicy+0.038
 tiger+0.037
 snowball+0.035
Neg logit contributions
angers-0.070
ail-0.064
bled-0.062
aj-0.059
uing-0.058
Token.
Token ID13
Feature activation-2.52e+00

Pos logit contributions
 course+0.063
 sorts+0.060
 juicy+0.058
 tiger+0.053
 turkey+0.050
Neg logit contributions
angers-0.077
ail-0.071
aj-0.071
bled-0.067
uing-0.067
Token He
Token ID679
Feature activation-2.32e+00

Pos logit contributions
 course+0.077
 sorts+0.072
 juicy+0.068
 animal+0.064
 piece+0.064
Neg logit contributions
angers-0.084
aj-0.074
ail-0.073
bled-0.070
uing-0.068
Token had
Token ID550
Feature activation-5.32e+00

Pos logit contributions
 course+0.067
 sorts+0.064
 juicy+0.059
 tiger+0.053
leaf+0.053
Neg logit contributions
angers-0.075
ail-0.073
aj-0.073
bled-0.069
uddled-0.066
Token a
Token ID257
Feature activation-6.13e+00

Pos logit contributions
 course+0.118
 sorts+0.108
igator+0.094
 tiger+0.085
 juicy+0.083
Neg logit contributions
angers-0.215
bled-0.198
aj-0.194
ups-0.192
ail-0.191
Token big
Token ID1263
Feature activation-7.70e+00

Pos logit contributions
 course+0.154
 sorts+0.153
leaf+0.121
e+0.116
 kinds+0.115
Neg logit contributions
angers-0.226
ail-0.217
aj-0.216
 conscience-0.209
ippers-0.202
Token pair
Token ID5166
Feature activation-9.80e+00

Pos logit contributions
 course+0.221
 sorts+0.219
leaf+0.203
 juicy+0.190
 tiger+0.180
Neg logit contributions
angers-0.250
aj-0.233
ail-0.231
 conscience-0.226
ippers-0.218
Token of
Token ID286
Feature activation-5.80e+00

Pos logit contributions
 course+0.203
 tiger+0.186
 sorts+0.185
 turkey+0.179
 deer+0.178
Neg logit contributions
angers-0.412
bled-0.375
ail-0.368
ippers-0.353
line-0.352
Token scissors
Token ID41786
Feature activation-3.43e+00

Pos logit contributions
 sorts+0.182
 course+0.180
+0.162
 spe+0.159
 tiger+0.156
Neg logit contributions
angers-0.177
ippers-0.153
aj-0.149
ail-0.147
bled-0.139
Token that
Token ID326
Feature activation-5.70e-02

Pos logit contributions
 course+0.075
 sorts+0.073
 juicy+0.067
 tiger+0.064
 deer+0.057
Neg logit contributions
angers-0.150
bled-0.135
ail-0.135
uing-0.131
aj-0.131
Token he
Token ID339
Feature activation+6.45e-01

Pos logit contributions
 course+0.002
 sorts+0.002
 juicy+0.002
 tiger+0.002
 deer+0.001
Neg logit contributions
angers-0.002
ail-0.002
bled-0.002
aj-0.002
uing-0.002
Token loved
Token ID6151
Feature activation-2.50e+00

Pos logit contributions
angers+0.023
ail+0.022
bled+0.021
aj+0.020
uing+0.020
Neg logit contributions
 course-0.018
 sorts-0.017
 tiger-0.015
 juicy-0.015
 turkey-0.015
Token time
Token ID640
Feature activation-1.23e+00

Pos logit contributions
 course+0.145
 sorts+0.144
 juicy+0.129
 tiger+0.127
 elephant+0.119
Neg logit contributions
angers-0.275
aj-0.263
ail-0.259
uing-0.250
bled-0.246
Token,
Token ID11
Feature activation+3.01e-01

Pos logit contributions
 course+0.024
 sorts+0.021
 juicy+0.020
 tiger+0.020
+0.018
Neg logit contributions
angers-0.057
bled-0.051
uing-0.051
aj-0.050
immers-0.050
Token there
Token ID612
Feature activation-8.13e-01

Pos logit contributions
angers+0.011
bled+0.011
ail+0.011
aj+0.010
uing+0.010
Neg logit contributions
 course-0.008
 sorts-0.008
 juicy-0.007
 tiger-0.006
leaf-0.006
Token was
Token ID373
Feature activation-4.05e+00

Pos logit contributions
 course+0.019
 sorts+0.018
 juicy+0.017
 tiger+0.016
 elephant+0.014
Neg logit contributions
angers-0.034
ail-0.031
bled-0.030
aj-0.030
uing-0.030
Token a
Token ID257
Feature activation-6.82e+00

Pos logit contributions
 sorts+0.099
 course+0.099
 tiger+0.089
igator+0.087
 gir+0.086
Neg logit contributions
angers-0.129
bled-0.126
aj-0.113
ooks-0.111
icker-0.107
Token cater
Token ID20825
Feature activation-9.75e+00

Pos logit contributions
 sorts+0.197
 course+0.195
leaf+0.154
 kinds+0.152
e+0.141
Neg logit contributions
angers-0.233
ail-0.220
aj-0.215
bled-0.198
 conscience-0.198
Tokenpillar
Token ID41643
Feature activation-5.92e+00

Pos logit contributions
 sorts+0.201
 course+0.200
 ribbon+0.183
 juicy+0.182
 balloon+0.176
Neg logit contributions
angers-0.391
ail-0.363
line-0.324
ails-0.321
bles-0.316
Token who
Token ID508
Feature activation-5.39e+00

Pos logit contributions
 juicy+0.143
 sorts+0.142
 course+0.138
leaf+0.129
 helium+0.121
Neg logit contributions
angers-0.215
ail-0.207
aj-0.186
uddled-0.180
 conscience-0.179
Token was
Token ID373
Feature activation-2.77e+00

Pos logit contributions
 course+0.166
 sorts+0.145
leaf+0.144
 balloon+0.142
 tiger+0.139
Neg logit contributions
ail-0.154
angers-0.153
bled-0.137
aj-0.135
 conscience-0.131
Token very
Token ID845
Feature activation-3.16e+00

Pos logit contributions
 course+0.081
 sorts+0.070
 ribbon+0.061
 tiger+0.060
 balloon+0.059
Neg logit contributions
angers-0.102
ail-0.095
bled-0.089
aj-0.087
balls-0.082
Token lonely
Token ID21757
Feature activation-2.25e+00

Pos logit contributions
 course+0.072
 sorts+0.070
 juicy+0.066
 tiger+0.062
 animal+0.057
Neg logit contributions
angers-0.132
ail-0.119
aj-0.118
bled-0.118
uing-0.117
Token,
Token ID11
Feature activation+2.60e-01

Pos logit contributions
 course+0.024
 sorts+0.020
 juicy+0.019
 tiger+0.019
+0.018
Neg logit contributions
angers-0.058
bled-0.052
aj-0.051
uing-0.051
immers-0.051
Token there
Token ID612
Feature activation-8.17e-01

Pos logit contributions
angers+0.009
bled+0.009
ail+0.008
aj+0.008
uing+0.008
Neg logit contributions
 course-0.007
 sorts-0.007
leaf-0.006
 gir-0.006
 juicy-0.006
Token was
Token ID373
Feature activation-4.05e+00

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.016
 tiger+0.015
 animal+0.014
Neg logit contributions
angers-0.035
ail-0.032
bled-0.031
aj-0.031
uing-0.030
Token a
Token ID257
Feature activation-6.85e+00

Pos logit contributions
 sorts+0.106
 course+0.103
 tiger+0.094
oc+0.092
igator+0.092
Neg logit contributions
bled-0.126
angers-0.121
aj-0.107
ooks-0.105
 themselves-0.103
Token small
Token ID1402
Feature activation-6.01e+00

Pos logit contributions
 sorts+0.194
 course+0.192
leaf+0.154
 kinds+0.150
e+0.143
Neg logit contributions
angers-0.234
ail-0.223
aj-0.216
 conscience-0.201
bled-0.201
Token cater
Token ID20825
Feature activation-9.68e+00

Pos logit contributions
 course+0.181
 sorts+0.178
leaf+0.173
+0.150
e+0.149
Neg logit contributions
angers-0.181
 conscience-0.165
ail-0.164
aj-0.153
tub-0.152
Tokenpillar
Token ID41643
Feature activation-5.89e+00

Pos logit contributions
 sorts+0.202
 course+0.198
 juicy+0.183
 ribbon+0.182
 balloon+0.172
Neg logit contributions
angers-0.377
ail-0.354
line-0.312
ails-0.309
bles-0.307
Token.
Token ID13
Feature activation-2.39e+00

Pos logit contributions
 juicy+0.146
 sorts+0.143
 course+0.140
leaf+0.132
 helium+0.125
Neg logit contributions
angers-0.209
ail-0.201
aj-0.177
ails-0.175
abies-0.174
Token He
Token ID679
Feature activation-2.02e+00

Pos logit contributions
 course+0.081
 sorts+0.073
 deer+0.070
leaf+0.070
 juicy+0.070
Neg logit contributions
angers-0.069
anks-0.057
ail-0.054
aj-0.053
 conscience-0.053
Token wanted
Token ID2227
Feature activation-4.31e+00

Pos logit contributions
 course+0.061
 sorts+0.061
 juicy+0.055
leaf+0.053
 tiger+0.052
Neg logit contributions
angers-0.062
ail-0.059
bled-0.058
aj-0.053
uddled-0.052
Token to
Token ID284
Feature activation-1.51e+00

Pos logit contributions
 course+0.127
 sorts+0.121
 juicy+0.113
 tiger+0.110
 elephant+0.102
Neg logit contributions
angers-0.153
ail-0.136
bled-0.132
aj-0.132
uing-0.128
Token time
Token ID640
Feature activation-1.19e+00

Pos logit contributions
 course+0.147
 sorts+0.144
 juicy+0.129
 tiger+0.129
 elephant+0.121
Neg logit contributions
angers-0.280
aj-0.267
ail-0.264
uing-0.254
bled-0.250
Token,
Token ID11
Feature activation+4.05e-01

Pos logit contributions
 course+0.023
 sorts+0.019
 juicy+0.018
 tiger+0.018
+0.017
Neg logit contributions
angers-0.057
bled-0.051
aj-0.050
uing-0.050
immers-0.050
Token there
Token ID612
Feature activation-8.54e-01

Pos logit contributions
angers+0.015
ail+0.014
bled+0.014
aj+0.014
uing+0.013
Neg logit contributions
 course-0.010
 sorts-0.010
 juicy-0.009
 tiger-0.009
leaf-0.008
Token was
Token ID373
Feature activation-4.06e+00

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.016
 tiger+0.015
 animal+0.014
Neg logit contributions
angers-0.038
ail-0.034
aj-0.034
bled-0.034
uing-0.033
Token a
Token ID257
Feature activation-6.88e+00

Pos logit contributions
 course+0.100
 sorts+0.099
 tiger+0.093
 gir+0.089
 spe+0.087
Neg logit contributions
angers-0.126
bled-0.126
ooks-0.110
aj-0.110
 themselves-0.107
Token cater
Token ID20825
Feature activation-9.68e+00

Pos logit contributions
 sorts+0.199
 course+0.194
leaf+0.158
 kinds+0.154
e+0.143
Neg logit contributions
angers-0.234
ail-0.224
aj-0.219
bled-0.200
uing-0.199
Tokenpillar
Token ID41643
Feature activation-5.87e+00

Pos logit contributions
 sorts+0.209
 course+0.203
 juicy+0.185
 balloon+0.180
 ribbon+0.179
Neg logit contributions
angers-0.379
ail-0.357
ails-0.310
line-0.309
bles-0.308
Token named
Token ID3706
Feature activation-5.26e+00

Pos logit contributions
 sorts+0.151
 juicy+0.150
 course+0.149
leaf+0.140
 helium+0.131
Neg logit contributions
angers-0.206
ail-0.200
aj-0.177
ails-0.170
ups-0.169
Token Sammy
Token ID44067
Feature activation-2.03e+00

Pos logit contributions
 sorts+0.164
 course+0.160
 juicy+0.139
leaf+0.137
 tiger+0.136
Neg logit contributions
angers-0.168
ail-0.158
aj-0.143
bled-0.142
anks-0.133
Token.
Token ID13
Feature activation-2.24e+00

Pos logit contributions
 course+0.062
 sorts+0.060
 juicy+0.059
 tiger+0.055
leaf+0.053
Neg logit contributions
angers-0.064
ail-0.060
aj-0.056
uing-0.055
bled-0.054
Token Sammy
Token ID44067
Feature activation-1.94e+00

Pos logit contributions
 course+0.062
 sorts+0.059
 juicy+0.056
 tiger+0.054
 animal+0.050
Neg logit contributions
angers-0.084
ail-0.075
aj-0.074
bled-0.073
uing-0.072
Token time
Token ID640
Feature activation-1.85e+00

Pos logit contributions
 course+0.160
 sorts+0.159
 juicy+0.141
 tiger+0.137
 elephant+0.125
Neg logit contributions
angers-0.325
ail-0.304
aj-0.303
uing-0.290
bled-0.289
Token there
Token ID612
Feature activation-2.22e+00

Pos logit contributions
 course+0.029
+0.021
 juicy+0.021
 a+0.021
 sorts+0.020
Neg logit contributions
angers-0.093
immers-0.085
anks-0.084
uing-0.084
ups-0.083
Token was
Token ID373
Feature activation-5.24e+00

Pos logit contributions
 course+0.038
 sorts+0.034
 tiger+0.029
 juicy+0.029
 animal+0.027
Neg logit contributions
angers-0.110
aj-0.100
uing-0.098
immers-0.098
anks-0.097
Token a
Token ID257
Feature activation-7.72e+00

Pos logit contributions
 sorts+0.109
 course+0.101
 tiger+0.094
igator+0.081
 juicy+0.079
Neg logit contributions
angers-0.216
bled-0.204
aj-0.200
ail-0.192
ippers-0.182
Token magical
Token ID10883
Feature activation-4.79e+00

Pos logit contributions
 sorts+0.210
 course+0.210
leaf+0.163
 kinds+0.156
 juicy+0.155
Neg logit contributions
angers-0.283
ail-0.270
aj-0.263
bled-0.244
uing-0.243
Token cater
Token ID20825
Feature activation-9.68e+00

Pos logit contributions
 sorts+0.121
 course+0.119
leaf+0.105
+0.102
 juicy+0.097
Neg logit contributions
ail-0.171
angers-0.170
aj-0.157
 conscience-0.154
tub-0.146
Tokenpillar
Token ID41643
Feature activation-5.70e+00

Pos logit contributions
 sorts+0.202
 juicy+0.187
 course+0.178
 balloon+0.175
 piece+0.168
Neg logit contributions
angers-0.396
ail-0.368
ails-0.323
aj-0.313
line-0.311
Token living
Token ID2877
Feature activation-1.89e+00

Pos logit contributions
 sorts+0.153
 juicy+0.149
 course+0.144
leaf+0.139
 tiger+0.129
Neg logit contributions
angers-0.197
ail-0.192
aj-0.176
ups-0.163
uddled-0.162
Token in
Token ID287
Feature activation-4.57e+00

Pos logit contributions
 course+0.042
 sorts+0.040
 juicy+0.038
 tiger+0.036
+0.032
Neg logit contributions
angers-0.081
ail-0.074
bled-0.072
aj-0.071
uing-0.069
Token a
Token ID257
Feature activation-7.21e+00

Pos logit contributions
 course+0.113
leaf+0.111
igator+0.102
 juicy+0.101
 sorts+0.098
Neg logit contributions
angers-0.124
aby-0.119
bled-0.119
ail-0.117
abies-0.113
Token mysterious
Token ID11428
Feature activation-4.80e+00

Pos logit contributions
 course+0.178
 sorts+0.177
leaf+0.159
 juicy+0.143
igator+0.136
Neg logit contributions
ail-0.261
angers-0.260
aj-0.244
 conscience-0.221
bled-0.220
Token time
Token ID640
Feature activation-1.01e+00

Pos logit contributions
 sorts+0.154
 course+0.154
 tiger+0.139
 juicy+0.138
 elephant+0.134
Neg logit contributions
angers-0.245
aj-0.243
ail-0.235
uing-0.225
immers-0.217
Token,
Token ID11
Feature activation+4.57e-01

Pos logit contributions
 course+0.020
 sorts+0.016
 juicy+0.016
 tiger+0.015
+0.014
Neg logit contributions
angers-0.048
bled-0.043
aj-0.043
uing-0.042
immers-0.042
Token there
Token ID612
Feature activation-6.72e-01

Pos logit contributions
angers+0.017
bled+0.016
ail+0.016
aj+0.015
uing+0.015
Neg logit contributions
 course-0.012
 sorts-0.012
 juicy-0.010
 tiger-0.010
 gir-0.010
Token was
Token ID373
Feature activation-3.87e+00

Pos logit contributions
 course+0.014
 sorts+0.014
 juicy+0.013
 tiger+0.012
 animal+0.011
Neg logit contributions
angers-0.029
ail-0.026
aj-0.026
bled-0.026
uing-0.026
Token a
Token ID257
Feature activation-6.71e+00

Pos logit contributions
 sorts+0.099
 course+0.098
 tiger+0.087
oc+0.086
 gir+0.085
Neg logit contributions
bled-0.119
angers-0.117
ooks-0.102
aj-0.101
 themselves-0.100
Token cater
Token ID20825
Feature activation-9.64e+00

Pos logit contributions
 sorts+0.197
 course+0.193
leaf+0.157
 kinds+0.154
e+0.141
Neg logit contributions
angers-0.222
ail-0.212
aj-0.205
 conscience-0.191
bled-0.191
Tokenpillar
Token ID41643
Feature activation-5.73e+00

Pos logit contributions
 sorts+0.205
 course+0.198
 juicy+0.187
 ribbon+0.182
 balloon+0.178
Neg logit contributions
angers-0.375
ail-0.351
ails-0.308
line-0.306
bles-0.303
Token who
Token ID508
Feature activation-5.32e+00

Pos logit contributions
 juicy+0.138
 sorts+0.137
 course+0.131
leaf+0.126
 helium+0.116
Neg logit contributions
angers-0.209
ail-0.201
aj-0.177
ails-0.175
abies-0.174
Token didn
Token ID1422
Feature activation-1.43e+00

Pos logit contributions
 course+0.172
leaf+0.151
 balloon+0.151
 sorts+0.150
 tiger+0.146
Neg logit contributions
angers-0.141
ail-0.141
bled-0.125
aj-0.121
abies-0.117
Token't
Token ID470
Feature activation-1.14e+00

Pos logit contributions
 course+0.049
 sorts+0.047
 juicy+0.046
 tiger+0.043
 deer+0.042
Neg logit contributions
angers-0.044
ail-0.039
bled-0.038
uing-0.036
anks-0.035
Token like
Token ID588
Feature activation-1.49e+00

Pos logit contributions
 course+0.027
 tiger+0.022
 juicy+0.021
 sorts+0.021
 turkey+0.020
Neg logit contributions
angers-0.045
ail-0.038
anks-0.037
 conscience-0.037
uing-0.037
Token,
Token ID11
Feature activation+3.06e-01

Pos logit contributions
 course+0.024
 sorts+0.021
 juicy+0.020
 tiger+0.019
+0.018
Neg logit contributions
angers-0.059
bled-0.053
aj-0.052
uing-0.052
immers-0.052
Token there
Token ID612
Feature activation-9.06e-01

Pos logit contributions
angers+0.011
bled+0.010
ail+0.010
aj+0.010
uing+0.009
Neg logit contributions
 course-0.008
 sorts-0.008
 juicy-0.007
 tiger-0.007
leaf-0.007
Token was
Token ID373
Feature activation-4.00e+00

Pos logit contributions
 course+0.020
 sorts+0.020
 juicy+0.018
 tiger+0.017
 deer+0.016
Neg logit contributions
angers-0.038
ail-0.035
bled-0.034
aj-0.034
uing-0.033
Token a
Token ID257
Feature activation-6.88e+00

Pos logit contributions
 course+0.104
 sorts+0.104
 tiger+0.093
oc+0.093
 gir+0.092
Neg logit contributions
bled-0.121
angers-0.120
ooks-0.103
aj-0.103
 themselves-0.101
Token little
Token ID1310
Feature activation-7.01e+00

Pos logit contributions
 sorts+0.201
 course+0.197
leaf+0.158
 kinds+0.157
e+0.146
Neg logit contributions
angers-0.231
ail-0.221
aj-0.214
bled-0.199
 conscience-0.198
Token cater
Token ID20825
Feature activation-9.60e+00

Pos logit contributions
 course+0.234
 sorts+0.234
leaf+0.208
e+0.199
+0.196
Neg logit contributions
angers-0.185
ail-0.171
ippers-0.153
aj-0.152
 conscience-0.150
Tokenpillar
Token ID41643
Feature activation-5.82e+00

Pos logit contributions
 sorts+0.197
 course+0.193
 juicy+0.182
 ribbon+0.176
 balloon+0.174
Neg logit contributions
angers-0.385
ail-0.362
ails-0.315
line-0.315
ups-0.311
Token.
Token ID13
Feature activation-2.25e+00

Pos logit contributions
 sorts+0.141
 juicy+0.140
 course+0.138
leaf+0.128
 helium+0.118
Neg logit contributions
angers-0.213
ail-0.207
aj-0.183
abies-0.178
uddled-0.177
Token She
Token ID1375
Feature activation-2.41e+00

Pos logit contributions
 course+0.078
 sorts+0.070
leaf+0.069
 deer+0.067
 juicy+0.067
Neg logit contributions
angers-0.063
anks-0.051
ail-0.049
 conscience-0.047
unes-0.047
Token was
Token ID373
Feature activation-2.65e+00

Pos logit contributions
 course+0.074
 sorts+0.073
 juicy+0.066
 tiger+0.064
leaf+0.062
Neg logit contributions
angers-0.074
ail-0.071
bled-0.069
aj-0.064
uddled-0.062
Token very
Token ID845
Feature activation-3.27e+00

Pos logit contributions
 course+0.080
 sorts+0.071
oc+0.060
 tiger+0.060
leaf+0.060
Neg logit contributions
angers-0.093
ail-0.086
bled-0.084
aj-0.076
bles-0.074
Token time
Token ID640
Feature activation-9.83e-01

Pos logit contributions
 sorts+0.155
 course+0.154
 tiger+0.140
 juicy+0.138
 elephant+0.134
Neg logit contributions
angers-0.262
aj-0.257
ail-0.251
uing-0.240
immers-0.232
Token there
Token ID612
Feature activation-6.04e-01

Pos logit contributions
 course+0.021
 sorts+0.018
 juicy+0.017
 tiger+0.016
+0.015
Neg logit contributions
angers-0.045
bled-0.040
aj-0.040
uing-0.040
ail-0.039
Token was
Token ID373
Feature activation-3.94e+00

Pos logit contributions
 course+0.016
 sorts+0.015
 juicy+0.015
 tiger+0.014
 gir+0.013
Neg logit contributions
angers-0.021
ail-0.020
bled-0.020
aj-0.019
uing-0.019
Token a
Token ID257
Feature activation-6.80e+00

Pos logit contributions
 course+0.097
 sorts+0.089
 tiger+0.086
igator+0.082
 gir+0.081
Neg logit contributions
angers-0.131
bled-0.128
aj-0.119
ail-0.112
ooks-0.111
Token wide
Token ID3094
Feature activation-5.69e+00

Pos logit contributions
 course+0.201
 sorts+0.199
leaf+0.162
 kinds+0.156
e+0.150
Neg logit contributions
angers-0.221
ail-0.216
aj-0.210
uing-0.187
 conscience-0.187
Token cater
Token ID20825
Feature activation-9.59e+00

Pos logit contributions
 sorts+0.160
 course+0.156
leaf+0.154
e+0.135
vous+0.125
Neg logit contributions
angers-0.174
ail-0.171
aj-0.159
 spine-0.158
 conscience-0.157
Tokenpillar
Token ID41643
Feature activation-5.57e+00

Pos logit contributions
 sorts+0.211
 course+0.201
 juicy+0.184
 ribbon+0.174
 piece+0.174
Neg logit contributions
angers-0.370
ail-0.348
line-0.308
ails-0.303
aj-0.297
Token.
Token ID13
Feature activation-2.18e+00

Pos logit contributions
 sorts+0.177
 course+0.174
 juicy+0.174
leaf+0.166
 helium+0.155
Neg logit contributions
angers-0.159
ail-0.154
aj-0.135
ails-0.129
uddled-0.126
Token He
Token ID679
Feature activation-1.72e+00

Pos logit contributions
 course+0.077
 sorts+0.069
leaf+0.068
 juicy+0.066
 deer+0.066
Neg logit contributions
angers-0.059
anks-0.045
ail-0.044
omm-0.044
aj-0.043
Token was
Token ID373
Feature activation-2.71e+00

Pos logit contributions
 sorts+0.053
 course+0.053
leaf+0.048
 juicy+0.046
 helium+0.044
Neg logit contributions
angers-0.049
ail-0.048
bled-0.045
aj-0.043
uddled-0.042
Token alone
Token ID3436
Feature activation-1.24e+00

Pos logit contributions
 course+0.086
 sorts+0.074
 ribbon+0.067
leaf+0.065
Run+0.064
Neg logit contributions
angers-0.089
bled-0.082
ail-0.081
balls-0.073
aj-0.072
Token time
Token ID640
Feature activation-1.03e+00

Pos logit contributions
 sorts+0.161
 course+0.159
 tiger+0.145
 juicy+0.144
 elephant+0.143
Neg logit contributions
aj-0.234
angers-0.231
ail-0.226
uing-0.214
immers-0.207
Token,
Token ID11
Feature activation+4.50e-01

Pos logit contributions
 course+0.020
 sorts+0.017
 juicy+0.016
 tiger+0.016
+0.015
Neg logit contributions
angers-0.048
bled-0.044
aj-0.043
uing-0.043
immers-0.043
Token there
Token ID612
Feature activation-6.67e-01

Pos logit contributions
angers+0.017
bled+0.016
ail+0.016
aj+0.015
uing+0.015
Neg logit contributions
 course-0.012
 sorts-0.012
 juicy-0.010
 tiger-0.010
leaf-0.010
Token was
Token ID373
Feature activation-3.92e+00

Pos logit contributions
 course+0.015
 sorts+0.014
 juicy+0.013
 tiger+0.013
 animal+0.011
Neg logit contributions
angers-0.028
ail-0.026
bled-0.025
aj-0.025
uing-0.025
Token a
Token ID257
Feature activation-6.66e+00

Pos logit contributions
 sorts+0.101
 course+0.099
 tiger+0.089
igator+0.089
oc+0.089
Neg logit contributions
bled-0.122
angers-0.120
aj-0.104
ooks-0.103
 themselves-0.102
Token cater
Token ID20825
Feature activation-9.58e+00

Pos logit contributions
 sorts+0.190
 course+0.189
leaf+0.150
 kinds+0.148
e+0.141
Neg logit contributions
angers-0.226
ail-0.215
aj-0.209
 conscience-0.194
uing-0.192
Tokenpillar
Token ID41643
Feature activation-5.80e+00

Pos logit contributions
 sorts+0.202
 course+0.198
 juicy+0.185
 ribbon+0.183
 balloon+0.179
Neg logit contributions
angers-0.370
ail-0.348
line-0.309
ails-0.303
or-0.301
Token who
Token ID508
Feature activation-5.39e+00

Pos logit contributions
 juicy+0.141
 sorts+0.138
 course+0.134
leaf+0.126
 helium+0.120
Neg logit contributions
angers-0.211
ail-0.202
aj-0.178
ails-0.177
uddled-0.175
Token was
Token ID373
Feature activation-2.69e+00

Pos logit contributions
 course+0.168
leaf+0.148
 balloon+0.148
 sorts+0.147
 tiger+0.142
Neg logit contributions
ail-0.151
angers-0.150
bled-0.136
aj-0.130
 conscience-0.126
Token very
Token ID845
Feature activation-3.13e+00

Pos logit contributions
 course+0.078
 sorts+0.068
 tiger+0.058
 ribbon+0.058
leaf+0.057
Neg logit contributions
angers-0.099
ail-0.093
bled-0.088
aj-0.085
 conscience-0.080
Token obedient
Token ID41652
Feature activation-3.47e+00

Pos logit contributions
 course+0.073
 sorts+0.070
 juicy+0.065
 tiger+0.062
 animal+0.057
Neg logit contributions
angers-0.130
ail-0.118
aj-0.116
bled-0.116
uing-0.114
Token a
Token ID257
Feature activation-6.59e+00

Pos logit contributions
 course+0.056
 sorts+0.055
 tiger+0.048
 elephant+0.048
igator+0.048
Neg logit contributions
angers-0.083
bled-0.079
aj-0.078
ail-0.076
iece-0.076
Token time
Token ID640
Feature activation-1.01e+00

Pos logit contributions
 sorts+0.159
 course+0.157
 tiger+0.144
 juicy+0.141
 elephant+0.140
Neg logit contributions
aj-0.238
angers-0.237
ail-0.230
uing-0.218
immers-0.211
Token there
Token ID612
Feature activation-5.83e-01

Pos logit contributions
 course+0.020
 sorts+0.017
 juicy+0.016
 tiger+0.015
+0.015
Neg logit contributions
angers-0.048
bled-0.043
aj-0.042
uing-0.042
immers-0.042
Token was
Token ID373
Feature activation-3.97e+00

Pos logit contributions
 course+0.014
 sorts+0.013
 juicy+0.013
 tiger+0.012
 deer+0.011
Neg logit contributions
angers-0.023
ail-0.021
bled-0.021
aj-0.021
uing-0.020
Token a
Token ID257
Feature activation-6.62e+00

Pos logit contributions
 course+0.095
 sorts+0.095
 tiger+0.088
igator+0.085
 gir+0.083
Neg logit contributions
bled-0.130
angers-0.130
aj-0.117
ooks-0.113
ail-0.112
Token cater
Token ID20825
Feature activation-9.56e+00

Pos logit contributions
 sorts+0.188
 course+0.188
leaf+0.150
 kinds+0.145
e+0.137
Neg logit contributions
angers-0.226
ail-0.218
aj-0.212
bled-0.193
 conscience-0.193
Tokenpillar
Token ID41643
Feature activation-5.67e+00

Pos logit contributions
 sorts+0.207
 course+0.201
 juicy+0.188
 balloon+0.182
 ribbon+0.181
Neg logit contributions
angers-0.366
ail-0.345
line-0.305
ails-0.299
or-0.296
Token.
Token ID13
Feature activation-2.35e+00

Pos logit contributions
 sorts+0.153
 juicy+0.153
 course+0.152
leaf+0.142
 helium+0.132
Neg logit contributions
angers-0.189
ail-0.182
aj-0.162
ails-0.154
abies-0.154
Token It
Token ID632
Feature activation-1.10e+00

Pos logit contributions
 course+0.077
 sorts+0.071
 juicy+0.067
leaf+0.066
 deer+0.066
Neg logit contributions
angers-0.073
ail-0.058
anks-0.057
aj-0.057
 conscience-0.056
Token lived
Token ID5615
Feature activation-1.20e+00

Pos logit contributions
 course+0.030
 sorts+0.029
 juicy+0.026
 tiger+0.026
leaf+0.025
Neg logit contributions
angers-0.038
ail-0.036
bled-0.034
aj-0.033
uddled-0.031
Token outside
Token ID2354
Feature activation-6.95e-01

Pos logit contributions
 course+0.028
 sorts+0.027
 tiger+0.024
 juicy+0.023
 elephant+0.021
Neg logit contributions
angers-0.050
bled-0.046
ail-0.045
aj-0.044
uing-0.042
Token,
Token ID11
Feature activation-5.22e-01

Pos logit contributions
 course+0.028
 juicy+0.021
+0.021
 sorts+0.021
 tiger+0.020
Neg logit contributions
angers-0.092
anks-0.083
immers-0.082
uing-0.082
ups-0.082
Token there
Token ID612
Feature activation-2.11e+00

Pos logit contributions
 course+0.011
 sorts+0.011
 juicy+0.010
 tiger+0.009
 animal+0.008
Neg logit contributions
angers-0.023
ail-0.021
bled-0.021
aj-0.021
uing-0.020
Token was
Token ID373
Feature activation-4.86e+00

Pos logit contributions
 course+0.043
 sorts+0.041
 juicy+0.037
 tiger+0.035
 animal+0.033
Neg logit contributions
angers-0.096
aj-0.086
ail-0.086
bled-0.085
uing-0.085
Token an
Token ID281
Feature activation-6.20e+00

Pos logit contributions
 sorts+0.111
 course+0.104
 tiger+0.094
igator+0.086
 gir+0.085
Neg logit contributions
angers-0.181
bled-0.178
aj-0.163
ail-0.161
ooks-0.153
Token enormous
Token ID9812
Feature activation-7.59e+00

Pos logit contributions
 course+0.177
 sorts+0.163
 bite+0.143
 ribbon+0.142
leaf+0.139
Neg logit contributions
angers-0.206
ail-0.184
bled-0.172
aj-0.172
omm-0.170
Token cater
Token ID20825
Feature activation-9.55e+00

Pos logit contributions
 sorts+0.201
leaf+0.179
 course+0.174
+0.168
e+0.166
Neg logit contributions
angers-0.254
ail-0.246
 conscience-0.230
aj-0.229
uddle-0.217
Tokenpillar
Token ID41643
Feature activation-5.59e+00

Pos logit contributions
 sorts+0.199
 juicy+0.190
 course+0.188
 balloon+0.176
 helium+0.170
Neg logit contributions
angers-0.386
ail-0.360
ails-0.311
line-0.305
bles-0.302
Token.
Token ID13
Feature activation-2.95e+00

Pos logit contributions
 juicy+0.163
 sorts+0.160
 course+0.155
leaf+0.152
 helium+0.144
Neg logit contributions
angers-0.177
ail-0.171
aj-0.148
ails-0.143
ups-0.141
Token He
Token ID679
Feature activation-2.15e+00

Pos logit contributions
 course+0.102
 sorts+0.091
leaf+0.090
 juicy+0.087
 deer+0.086
Neg logit contributions
angers-0.086
omm-0.068
anks-0.067
ail-0.067
aj-0.065
Token was
Token ID373
Feature activation-2.87e+00

Pos logit contributions
 sorts+0.070
 course+0.070
leaf+0.063
 juicy+0.062
 balloon+0.061
Neg logit contributions
ail-0.058
angers-0.057
bled-0.054
aj-0.050
uddled-0.048
Token looking
Token ID2045
Feature activation-2.50e-01

Pos logit contributions
 course+0.090
 sorts+0.078
 ribbon+0.072
leaf+0.067
 balloon+0.066
Neg logit contributions
angers-0.094
ail-0.086
bled-0.086
balls-0.076
omm-0.076
Token time
Token ID640
Feature activation-1.09e+00

Pos logit contributions
 course+0.134
 sorts+0.130
 juicy+0.117
 tiger+0.114
 elephant+0.104
Neg logit contributions
angers-0.282
aj-0.263
ail-0.263
uing-0.254
bled-0.254
Token,
Token ID11
Feature activation+3.47e-01

Pos logit contributions
 course+0.021
 sorts+0.017
 juicy+0.016
 tiger+0.016
+0.015
Neg logit contributions
angers-0.052
bled-0.047
uing-0.046
aj-0.046
immers-0.046
Token there
Token ID612
Feature activation-7.18e-01

Pos logit contributions
angers+0.014
ail+0.013
bled+0.013
aj+0.013
uing+0.012
Neg logit contributions
 course-0.008
 sorts-0.008
 juicy-0.007
 tiger-0.007
 gir-0.006
Token was
Token ID373
Feature activation-3.92e+00

Pos logit contributions
 course+0.015
 sorts+0.014
 juicy+0.013
 tiger+0.013
 animal+0.011
Neg logit contributions
angers-0.032
ail-0.029
aj-0.029
bled-0.028
uing-0.028
Token a
Token ID257
Feature activation-6.68e+00

Pos logit contributions
 sorts+0.096
 course+0.094
 spe+0.080
leaf+0.080
 gir+0.080
Neg logit contributions
angers-0.128
bled-0.127
aj-0.112
ooks-0.110
ail-0.107
Token cater
Token ID20825
Feature activation-9.51e+00

Pos logit contributions
 course+0.187
 sorts+0.187
leaf+0.145
 kinds+0.142
+0.134
Neg logit contributions
angers-0.234
ail-0.221
aj-0.216
bled-0.202
 conscience-0.199
Tokenpillar
Token ID41643
Feature activation-5.76e+00

Pos logit contributions
 sorts+0.200
 course+0.194
 juicy+0.178
 ribbon+0.171
 balloon+0.167
Neg logit contributions
angers-0.380
ail-0.353
line-0.313
ails-0.308
bles-0.306
Token named
Token ID3706
Feature activation-5.42e+00

Pos logit contributions
 sorts+0.145
 juicy+0.142
 course+0.140
leaf+0.131
 helium+0.121
Neg logit contributions
angers-0.205
ail-0.197
aj-0.175
abies-0.170
ails-0.169
Token Cindy
Token ID39062
Feature activation-1.95e+00

Pos logit contributions
 sorts+0.174
 course+0.171
 juicy+0.146
leaf+0.145
 balloon+0.145
Neg logit contributions
angers-0.173
ail-0.160
aj-0.148
bled-0.142
anks-0.135
Token.
Token ID13
Feature activation-2.12e+00

Pos logit contributions
 course+0.058
 sorts+0.054
 juicy+0.053
 tiger+0.049
 turkey+0.046
Neg logit contributions
angers-0.067
ail-0.061
bled-0.057
aj-0.057
uing-0.056
Token She
Token ID1375
Feature activation-2.16e+00

Pos logit contributions
 course+0.062
 sorts+0.059
 juicy+0.056
 tiger+0.054
 animal+0.051
Neg logit contributions
angers-0.076
ail-0.068
aj-0.067
bled-0.066
uing-0.065
Token time
Token ID640
Feature activation-1.92e+00

Pos logit contributions
 sorts+0.173
 course+0.169
 juicy+0.149
 tiger+0.148
 deer+0.139
Neg logit contributions
angers-0.308
aj-0.296
ail-0.294
uing-0.277
bled-0.273
Token,
Token ID11
Feature activation-6.33e-01

Pos logit contributions
 course+0.031
 juicy+0.023
+0.023
 sorts+0.022
 tiger+0.022
Neg logit contributions
angers-0.096
immers-0.087
anks-0.087
bled-0.086
uing-0.086
Token there
Token ID612
Feature activation-2.19e+00

Pos logit contributions
 course+0.013
 sorts+0.012
 juicy+0.011
 tiger+0.011
 animal+0.010
Neg logit contributions
angers-0.028
ail-0.026
bled-0.025
aj-0.025
uing-0.025
Token was
Token ID373
Feature activation-5.23e+00

Pos logit contributions
 course+0.043
 sorts+0.040
 juicy+0.035
 tiger+0.034
 animal+0.032
Neg logit contributions
angers-0.102
aj-0.092
ail-0.091
bled-0.090
uing-0.090
Token an
Token ID281
Feature activation-6.30e+00

Pos logit contributions
 sorts+0.118
 course+0.113
 tiger+0.101
igator+0.093
oc+0.089
Neg logit contributions
angers-0.201
bled-0.196
aj-0.184
ail-0.177
icker-0.168
Token elderly
Token ID13830
Feature activation-9.48e+00

Pos logit contributions
 course+0.182
 sorts+0.168
 bite+0.147
+0.145
 juicy+0.142
Neg logit contributions
angers-0.214
ail-0.189
aj-0.178
omm-0.175
bled-0.174
Token cat
Token ID3797
Feature activation-6.96e+00

Pos logit contributions
 sorts+0.278
 course+0.275
 juicy+0.241
+0.224
 snowball+0.218
Neg logit contributions
angers-0.326
ail-0.296
aj-0.272
line-0.255
ippers-0.255
Token named
Token ID3706
Feature activation-6.08e+00

Pos logit contributions
 juicy+0.172
 sorts+0.166
 course+0.161
leaf+0.157
 helium+0.147
Neg logit contributions
angers-0.254
ail-0.242
aj-0.221
ooks-0.213
ails-0.212
Token Tom
Token ID4186
Feature activation-1.22e+00

Pos logit contributions
 sorts+0.188
 course+0.187
 juicy+0.163
 tiger+0.157
leaf+0.151
Neg logit contributions
angers-0.208
ail-0.191
aj-0.183
bled-0.169
uing-0.164
Token.
Token ID13
Feature activation-3.34e+00

Pos logit contributions
 course+0.037
 sorts+0.036
 juicy+0.035
 tiger+0.033
leaf+0.032
Neg logit contributions
angers-0.038
ail-0.036
aj-0.035
bled-0.033
uing-0.033
Token Tom
Token ID4186
Feature activation-1.44e+00

Pos logit contributions
 course+0.114
 sorts+0.108
leaf+0.102
 deer+0.100
 juicy+0.100
Neg logit contributions
angers-0.094
aj-0.083
anks-0.077
ail-0.072
ooks-0.071
Token in
Token ID287
Feature activation-3.30e+00

Pos logit contributions
 sorts+0.026
 course+0.025
 juicy+0.025
leaf+0.022
 tiger+0.021
Neg logit contributions
angers-0.027
ail-0.024
bled-0.022
aj-0.022
anks-0.022
Token the
Token ID262
Feature activation+6.67e-02

Pos logit contributions
leaf+0.087
 juicy+0.084
 course+0.082
 sorts+0.082
pillar+0.075
Neg logit contributions
angers-0.100
ail-0.094
bled-0.089
 injuries-0.088
 parents-0.083
Token garden
Token ID11376
Feature activation-1.81e+00

Pos logit contributions
angers+0.002
ail+0.002
aj+0.002
bled+0.002
uing+0.002
Neg logit contributions
 course-0.002
 sorts-0.002
 juicy-0.002
 tiger-0.002
leaf-0.002
Token.
Token ID13
Feature activation-8.10e-01

Pos logit contributions
 course+0.051
 sorts+0.048
 juicy+0.047
 tiger+0.046
 deer+0.042
Neg logit contributions
angers-0.065
ail-0.059
aj-0.057
bled-0.056
uing-0.055
Token A
Token ID317
Feature activation-5.35e+00

Pos logit contributions
 course+0.023
 sorts+0.022
 juicy+0.020
 tiger+0.020
 deer+0.019
Neg logit contributions
angers-0.029
ail-0.026
aj-0.025
bled-0.025
uing-0.024
Token cater
Token ID20825
Feature activation-9.48e+00

Pos logit contributions
 course+0.133
 sorts+0.128
 juicy+0.102
e+0.102
leaf+0.099
Neg logit contributions
angers-0.203
ail-0.196
aj-0.181
 conscience-0.178
uing-0.177
Tokenpillar
Token ID41643
Feature activation-5.70e+00

Pos logit contributions
 sorts+0.235
 juicy+0.213
 balloon+0.209
 chocolate+0.207
 piece+0.203
Neg logit contributions
angers-0.315
ail-0.297
ying-0.265
line-0.262
ails-0.262
Token was
Token ID373
Feature activation-2.21e+00

Pos logit contributions
 sorts+0.170
 juicy+0.159
leaf+0.157
 helium+0.153
 maple+0.143
Neg logit contributions
ail-0.171
angers-0.163
uddled-0.154
ups-0.146
aj-0.141
Token eating
Token ID6600
Feature activation-1.84e+00

Pos logit contributions
 course+0.065
 sorts+0.063
 juicy+0.053
 tiger+0.051
leaf+0.049
Neg logit contributions
angers-0.076
bled-0.070
ail-0.070
aj-0.065
balls-0.062
Token all
Token ID477
Feature activation-1.15e-01

Pos logit contributions
 sorts+0.044
leaf+0.039
 course+0.037
 tiger+0.035
 jugg+0.032
Neg logit contributions
angers-0.066
bled-0.064
ail-0.059
aj-0.058
 conscience-0.057
Token the
Token ID262
Feature activation+3.36e+00

Pos logit contributions
 gir+0.002
 tiger+0.002
 arrow+0.002
 ribbon+0.002
 spe+0.002
Neg logit contributions
angers-0.004
ail-0.004
ups-0.004
ying-0.004
bled-0.004
Token,
Token ID11
Feature activation+1.60e-01

Pos logit contributions
 course+0.026
 sorts+0.023
 juicy+0.021
 tiger+0.021
+0.020
Neg logit contributions
angers-0.063
bled-0.056
uing-0.056
aj-0.056
immers-0.055
Token there
Token ID612
Feature activation-9.66e-01

Pos logit contributions
angers+0.006
bled+0.006
ail+0.005
aj+0.005
uing+0.005
Neg logit contributions
 course-0.004
 sorts-0.004
 juicy-0.004
 tiger-0.004
leaf-0.004
Token was
Token ID373
Feature activation-4.07e+00

Pos logit contributions
 course+0.021
 sorts+0.020
 juicy+0.019
 tiger+0.018
 animal+0.016
Neg logit contributions
angers-0.041
ail-0.037
aj-0.037
bled-0.037
uing-0.036
Token a
Token ID257
Feature activation-6.92e+00

Pos logit contributions
 course+0.108
 sorts+0.108
 tiger+0.097
oc+0.096
igator+0.095
Neg logit contributions
bled-0.121
angers-0.118
aj-0.104
ooks-0.103
 themselves-0.101
Token fat
Token ID3735
Feature activation-7.99e+00

Pos logit contributions
 sorts+0.203
 course+0.198
leaf+0.160
 kinds+0.159
e+0.146
Neg logit contributions
angers-0.232
ail-0.223
aj-0.216
 conscience-0.200
bled-0.199
Token cater
Token ID20825
Feature activation-9.47e+00

Pos logit contributions
 sorts+0.214
 course+0.189
leaf+0.172
+0.162
 kinds+0.154
Neg logit contributions
angers-0.293
ail-0.277
 conscience-0.255
aj-0.255
omm-0.246
Tokenpillar
Token ID41643
Feature activation-5.52e+00

Pos logit contributions
 sorts+0.204
 course+0.200
 juicy+0.185
 ribbon+0.180
 balloon+0.175
Neg logit contributions
angers-0.361
ail-0.334
line-0.296
ails-0.293
bles-0.288
Token called
Token ID1444
Feature activation-4.18e+00

Pos logit contributions
 juicy+0.145
 sorts+0.140
 course+0.139
leaf+0.131
 helium+0.125
Neg logit contributions
angers-0.191
ail-0.182
aj-0.159
ails-0.157
abies-0.156
Token Tom
Token ID4186
Feature activation+8.52e-02

Pos logit contributions
 sorts+0.133
 course+0.129
 juicy+0.117
 tiger+0.110
 piece+0.110
Neg logit contributions
angers-0.133
ail-0.120
aj-0.111
bled-0.106
anks-0.105
Token.
Token ID13
Feature activation-1.93e+00

Pos logit contributions
angers+0.003
ail+0.002
aj+0.002
uing+0.002
bled+0.002
Neg logit contributions
 course-0.003
 juicy-0.003
 sorts-0.003
 tiger-0.002
 spe-0.002
Token Tom
Token ID4186
Feature activation-5.11e-01

Pos logit contributions
 course+0.058
 sorts+0.056
 juicy+0.052
 deer+0.051
 tiger+0.050
Neg logit contributions
angers-0.063
aj-0.056
bled-0.054
ail-0.053
anks-0.053
Token time
Token ID640
Feature activation-2.36e+00

Pos logit contributions
 course+0.162
 sorts+0.155
 juicy+0.140
 tiger+0.134
 animal+0.120
Neg logit contributions
angers-0.374
ail-0.344
aj-0.340
bled-0.336
uing-0.332
Token,
Token ID11
Feature activation-8.85e-01

Pos logit contributions
 course+0.040
 juicy+0.030
 sorts+0.030
 tiger+0.029
 a+0.029
Neg logit contributions
angers-0.116
uing-0.106
immers-0.105
anks-0.104
aj-0.103
Token there
Token ID612
Feature activation-2.69e+00

Pos logit contributions
 course+0.021
 sorts+0.020
 juicy+0.018
 tiger+0.017
 animal+0.016
Neg logit contributions
angers-0.037
bled-0.034
ail-0.034
aj-0.033
uing-0.032
Token was
Token ID373
Feature activation-5.11e+00

Pos logit contributions
 course+0.053
 sorts+0.050
 juicy+0.044
 tiger+0.043
 animal+0.040
Neg logit contributions
angers-0.125
aj-0.113
ail-0.112
uing-0.111
bled-0.111
Token an
Token ID281
Feature activation-6.47e+00

Pos logit contributions
 sorts+0.126
 course+0.117
 tiger+0.107
oc+0.103
igator+0.101
Neg logit contributions
angers-0.175
bled-0.169
aj-0.159
ail-0.153
ooks-0.146
Token elderly
Token ID13830
Feature activation-9.41e+00

Pos logit contributions
 course+0.188
 sorts+0.175
 bite+0.151
leaf+0.150
 ribbon+0.150
Neg logit contributions
angers-0.212
ail-0.189
aj-0.177
bled-0.175
omm-0.174
Token man
Token ID582
Feature activation-3.71e+00

Pos logit contributions
 sorts+0.282
 course+0.277
 juicy+0.245
+0.229
 snowball+0.222
Neg logit contributions
angers-0.317
ail-0.288
aj-0.261
line-0.247
ippers-0.246
Token who
Token ID508
Feature activation-5.93e+00

Pos logit contributions
 course+0.104
 juicy+0.100
 sorts+0.094
 ribbon+0.090
 butterfly+0.088
Neg logit contributions
angers-0.121
ail-0.112
ails-0.105
ooks-0.103
aj-0.102
Token loved
Token ID6151
Feature activation-3.94e+00

Pos logit contributions
 course+0.186
 juicy+0.162
 butterfly+0.160
 sorts+0.157
 turkey+0.157
Neg logit contributions
angers-0.186
ail-0.172
bled-0.164
aj-0.160
uing-0.155
Token rockets
Token ID20293
Feature activation-2.68e+00

Pos logit contributions
 course+0.139
 sorts+0.128
+0.121
 juicy+0.119
e+0.117
Neg logit contributions
angers-0.114
aj-0.092
ail-0.088
iked-0.088
ups-0.087
Token.
Token ID13
Feature activation-2.22e+00

Pos logit contributions
 course+0.091
 juicy+0.090
 sorts+0.084
leaf+0.084
Run+0.083
Neg logit contributions
angers-0.070
ail-0.060
bled-0.056
anks-0.055
uing-0.054
Token<|endoftext|>
Token ID50256
Feature activation-2.39e+00

Pos logit contributions
angers+0.036
ail+0.032
aj+0.031
bled+0.031
uing+0.030
Neg logit contributions
 course-0.029
 sorts-0.028
 juicy-0.027
 tiger-0.026
 deer-0.024
TokenOnce
Token ID7454
Feature activation+2.60e+00

Pos logit contributions
 course+0.071
 sorts+0.069
 juicy+0.066
 tiger+0.063
 elephant+0.060
Neg logit contributions
angers-0.082
ail-0.073
aj-0.071
bled-0.071
uing-0.069
Token there
Token ID612
Feature activation+9.27e-02

Pos logit contributions
angers+0.089
immers+0.075
anks+0.074
bled+0.074
uing+0.072
Neg logit contributions
 course-0.083
 sorts-0.081
 juicy-0.074
 piece-0.073
 tiger-0.071
Token was
Token ID373
Feature activation-3.48e+00

Pos logit contributions
angers+0.004
aj+0.004
ail+0.004
bled+0.004
uing+0.004
Neg logit contributions
 course-0.002
 sorts-0.002
 juicy-0.002
 tiger-0.002
 animal-0.001
Token a
Token ID257
Feature activation-6.28e+00

Pos logit contributions
 course+0.075
 sorts+0.073
 tiger+0.069
 bit+0.067
 gir+0.066
Neg logit contributions
angers-0.114
bled-0.112
aj-0.104
ooks-0.102
ail-0.100
Token cater
Token ID20825
Feature activation-9.41e+00

Pos logit contributions
 course+0.191
 sorts+0.185
leaf+0.156
 kinds+0.145
igator+0.144
Neg logit contributions
angers-0.195
ail-0.188
aj-0.186
uing-0.170
 conscience-0.169
Tokenpillar
Token ID41643
Feature activation-5.56e+00

Pos logit contributions
 sorts+0.201
 course+0.190
 juicy+0.188
 ribbon+0.187
 piece+0.179
Neg logit contributions
angers-0.357
ail-0.328
ails-0.305
or-0.296
line-0.295
Token in
Token ID287
Feature activation-4.20e+00

Pos logit contributions
 juicy+0.173
 sorts+0.171
 course+0.165
leaf+0.162
 helium+0.154
Neg logit contributions
angers-0.160
ail-0.154
aj-0.136
ails-0.131
uddled-0.130
Token a
Token ID257
Feature activation-6.63e+00

Pos logit contributions
leaf+0.108
 sorts+0.103
 juicy+0.096
 course+0.092
ris+0.091
Neg logit contributions
angers-0.119
ail-0.112
bled-0.109
 themselves-0.107
iece-0.105
Token garden
Token ID11376
Feature activation-3.44e+00

Pos logit contributions
 course+0.154
 sorts+0.150
leaf+0.135
 juicy+0.129
 tiger+0.124
Neg logit contributions
angers-0.251
ail-0.245
aj-0.232
uing-0.217
bled-0.216
Token who
Token ID508
Feature activation-4.92e+00

Pos logit contributions
 course+0.096
 sorts+0.094
 juicy+0.090
 tiger+0.087
leaf+0.080
Neg logit contributions
angers-0.121
ail-0.110
aj-0.105
bled-0.105
uing-0.102
Token a
Token ID257
Feature activation-3.42e+00

Pos logit contributions
 course+0.045
 sorts+0.043
 tiger+0.039
 juicy+0.039
igator+0.037
Neg logit contributions
angers-0.085
bled-0.083
ail-0.080
uing-0.078
iece-0.076
Token spoon
Token ID24556
Feature activation-1.93e+00

Pos logit contributions
 course+0.084
 sorts+0.081
 kinds+0.065
 tiger+0.064
e+0.061
Neg logit contributions
ail-0.130
angers-0.121
aj-0.116
uing-0.114
 spine-0.111
Token and
Token ID290
Feature activation-3.49e+00

Pos logit contributions
 course+0.049
 sorts+0.042
 juicy+0.042
 tiger+0.042
 spe+0.037
Neg logit contributions
angers-0.078
ail-0.073
bled-0.069
uing-0.068
line-0.066
Token scoop
Token ID23529
Feature activation-5.23e-02

Pos logit contributions
 course+0.106
 sorts+0.099
 tiger+0.095
igator+0.086
 deer+0.085
Neg logit contributions
bled-0.110
angers-0.105
ail-0.099
aj-0.094
uddled-0.094
Tokened
Token ID276
Feature activation+2.03e+00

Pos logit contributions
 course+0.002
 sorts+0.002
 juicy+0.002
 tiger+0.002
 animal+0.001
Neg logit contributions
angers-0.002
ail-0.001
aj-0.001
bled-0.001
uing-0.001
Token out
Token ID503
Feature activation+4.58e+00

Pos logit contributions
angers+0.071
ail+0.068
bled+0.067
uing+0.065
ups+0.063
Neg logit contributions
 course-0.054
 sorts-0.049
 tiger-0.045
igator-0.043
 juicy-0.041
Token the
Token ID262
Feature activation+3.93e+00

Pos logit contributions
angers+0.162
bled+0.159
ail+0.155
uing+0.144
ups+0.142
Neg logit contributions
 course-0.114
 sorts-0.102
 tiger-0.097
 deer-0.092
igator-0.091
Token inside
Token ID2641
Feature activation+3.07e+00

Pos logit contributions
angers+0.161
ail+0.155
bled+0.152
aj+0.147
uing+0.142
Neg logit contributions
 course-0.082
 sorts-0.080
 tiger-0.069
 deer-0.065
igator-0.062
Token.
Token ID13
Feature activation+2.29e-01

Pos logit contributions
angers+0.091
bled+0.079
ail+0.079
uing+0.077
iece+0.075
Neg logit contributions
 course-0.099
 tiger-0.092
 deer-0.090
 juicy-0.090
 sorts-0.089
Token It
Token ID632
Feature activation-1.38e-01

Pos logit contributions
angers+0.008
ail+0.007
aj+0.007
bled+0.007
uing+0.007
Neg logit contributions
 course-0.007
 sorts-0.006
 juicy-0.006
 tiger-0.006
 animal-0.006
Token was
Token ID373
Feature activation-1.26e+00

Pos logit contributions
 course+0.004
 sorts+0.004
 tiger+0.004
leaf+0.003
 juicy+0.003
Neg logit contributions
ail-0.004
bled-0.004
angers-0.004
uing-0.004
aj-0.004
Token Tim
Token ID5045
Feature activation+8.02e-01

Pos logit contributions
angers+0.044
ail+0.039
aj+0.039
bled+0.038
uing+0.038
Neg logit contributions
 course-0.031
 sorts-0.030
 juicy-0.028
 tiger-0.027
 elephant-0.025
Tokenmy
Token ID1820
Feature activation+4.15e-01

Pos logit contributions
ail+0.026
angers+0.026
aj+0.024
bled+0.023
uing+0.023
Neg logit contributions
 course-0.023
 sorts-0.023
 juicy-0.023
 tiger-0.021
 spe-0.021
Token felt
Token ID2936
Feature activation-2.05e+00

Pos logit contributions
ail+0.013
angers+0.013
aj+0.012
bled+0.012
uing+0.012
Neg logit contributions
 course-0.012
 sorts-0.012
 juicy-0.011
 tiger-0.011
leaf-0.010
Token happy
Token ID3772
Feature activation+1.80e-01

Pos logit contributions
 course+0.053
 sorts+0.051
 tiger+0.048
 elephant+0.045
 juicy+0.045
Neg logit contributions
angers-0.073
bled-0.070
ail-0.067
uing-0.066
aj-0.065
Token again
Token ID757
Feature activation+4.22e+00

Pos logit contributions
angers+0.008
ail+0.007
bled+0.007
aj+0.007
uing+0.007
Neg logit contributions
 course-0.004
 sorts-0.004
 juicy-0.003
 tiger-0.003
 elephant-0.003
Token,
Token ID11
Feature activation+5.04e+00

Pos logit contributions
angers+0.167
ail+0.154
aj+0.150
uing+0.149
bled+0.147
Neg logit contributions
 course-0.096
 sorts-0.094
 juicy-0.087
igator-0.082
 tiger-0.082
Token and
Token ID290
Feature activation-2.18e+00

Pos logit contributions
angers+0.154
bled+0.139
aj+0.132
 conscience+0.130
ail+0.129
Neg logit contributions
 sorts-0.154
 course-0.153
igator-0.136
leaf-0.133
 tiger-0.132
Token the
Token ID262
Feature activation+2.23e+00

Pos logit contributions
 course+0.060
 sorts+0.057
 juicy+0.054
 tiger+0.052
 animal+0.049
Neg logit contributions
angers-0.082
ail-0.073
aj-0.073
bled-0.072
uing-0.071
Token bigger
Token ID5749
Feature activation-1.07e+00

Pos logit contributions
angers+0.080
ail+0.075
bled+0.074
aj+0.073
immers+0.069
Neg logit contributions
 course-0.058
 sorts-0.056
 juicy-0.048
 tiger-0.047
 spe-0.046
Token boy
Token ID2933
Feature activation-1.34e+00

Pos logit contributions
 course+0.029
 sorts+0.028
 juicy+0.026
 tiger+0.024
 spe+0.023
Neg logit contributions
angers-0.040
ail-0.036
aj-0.035
bled-0.034
uing-0.034
Token and
Token ID290
Feature activation-2.74e+00

Pos logit contributions
 sorts+0.036
 course+0.036
 juicy+0.034
 tiger+0.032
 turkey+0.030
Neg logit contributions
angers-0.047
ail-0.045
bled-0.042
aj-0.042
uing-0.041
Token.
Token ID13
Feature activation-8.96e-01

Pos logit contributions
 course+0.022
 sorts+0.021
 juicy+0.020
 tiger+0.020
leaf+0.019
Neg logit contributions
angers-0.021
ail-0.019
aj-0.017
uing-0.017
ups-0.016
Token He
Token ID679
Feature activation-8.81e-01

Pos logit contributions
 course+0.025
 sorts+0.024
 juicy+0.023
 tiger+0.022
 elephant+0.020
Neg logit contributions
angers-0.033
ail-0.030
bled-0.030
aj-0.029
uing-0.029
Token would
Token ID561
Feature activation-1.93e+00

Pos logit contributions
 course+0.024
 sorts+0.024
 tiger+0.021
 juicy+0.020
leaf+0.020
Neg logit contributions
angers-0.031
ail-0.030
bled-0.028
aj-0.027
uddled-0.026
Token always
Token ID1464
Feature activation+1.50e+00

Pos logit contributions
 sorts+0.056
 tiger+0.055
 course+0.054
 snowball+0.052
pillar+0.050
Neg logit contributions
angers-0.053
uing-0.049
ail-0.048
 conscience-0.048
bled-0.043
Token ask
Token ID1265
Feature activation+4.17e+00

Pos logit contributions
angers+0.043
uing+0.043
ail+0.041
aj+0.040
 conscience+0.039
Neg logit contributions
 sorts-0.041
 tiger-0.041
 course-0.040
 snowball-0.036
 animal-0.036
Token his
Token ID465
Feature activation+5.25e+00

Pos logit contributions
angers+0.169
aj+0.154
ail+0.154
bled+0.151
uing+0.147
Neg logit contributions
 course-0.103
 sorts-0.097
 juicy-0.093
 tiger-0.090
 animal-0.084
Token friends
Token ID2460
Feature activation-1.37e+00

Pos logit contributions
angers+0.148
ail+0.130
aj+0.127
bled+0.122
uing+0.122
Neg logit contributions
 course-0.192
 sorts-0.186
 juicy-0.173
 tiger-0.166
 piece-0.159
Token to
Token ID284
Feature activation-4.13e-01

Pos logit contributions
 course+0.039
 sorts+0.038
 juicy+0.036
 tiger+0.034
 animal+0.032
Neg logit contributions
angers-0.049
ail-0.044
uing-0.043
aj-0.043
bled-0.043
Token come
Token ID1282
Feature activation+4.80e+00

Pos logit contributions
 sorts+0.012
 course+0.011
 tiger+0.011
 snowball+0.010
 juicy+0.010
Neg logit contributions
angers-0.013
ail-0.012
uing-0.012
bled-0.012
 conscience-0.011
Token along
Token ID1863
Feature activation+2.07e+00

Pos logit contributions
angers+0.195
ail+0.177
aj+0.172
uing+0.171
bled+0.170
Neg logit contributions
 course-0.118
 sorts-0.109
 juicy-0.099
 tiger-0.097
 piece-0.087
Token and
Token ID290
Feature activation-1.54e+00

Pos logit contributions
angers+0.066
uing+0.061
 nicely+0.059
ail+0.057
 conscience+0.057
Neg logit contributions
 sorts-0.053
 course-0.053
leaf-0.050
 tiger-0.050
 juicy-0.050
Token who
Token ID508
Feature activation-3.45e+00

Pos logit contributions
angers+0.120
ail+0.109
aj+0.107
uing+0.104
bled+0.103
Neg logit contributions
 sorts-0.080
 course-0.078
 juicy-0.073
 tiger-0.067
 piece-0.065
Token warned
Token ID7728
Feature activation+2.07e+00

Pos logit contributions
 juicy+0.099
 course+0.093
 maple+0.091
 turkey+0.090
 snowball+0.090
Neg logit contributions
angers-0.093
ail-0.091
bled-0.083
ups-0.082
uddled-0.082
Token him
Token ID683
Feature activation+6.29e+00

Pos logit contributions
angers+0.080
aj+0.072
ail+0.070
bled+0.069
uing+0.068
Neg logit contributions
 course-0.057
 sorts-0.052
 juicy-0.050
 tiger-0.049
 animal-0.047
Token to
Token ID284
Feature activation-2.70e-01

Pos logit contributions
angers+0.240
ail+0.215
aj+0.213
bled+0.212
uing+0.208
Neg logit contributions
 course-0.167
 sorts-0.160
 juicy-0.151
 tiger-0.145
 animal-0.135
Token stay
Token ID2652
Feature activation+3.60e+00

Pos logit contributions
 sorts+0.008
 course+0.008
 juicy+0.008
 tiger+0.008
 turkey+0.007
Neg logit contributions
angers-0.008
ail-0.008
uing-0.007
aj-0.007
bled-0.007
Token away
Token ID1497
Feature activation+6.29e+00

Pos logit contributions
angers+0.143
aj+0.131
ail+0.131
bled+0.129
uing+0.127
Neg logit contributions
 course-0.090
 sorts-0.085
 juicy-0.079
 tiger-0.077
 elephant-0.070
Token from
Token ID422
Feature activation+1.32e+00

Pos logit contributions
angers+0.243
ail+0.220
aj+0.216
bled+0.214
uing+0.214
Neg logit contributions
 course-0.166
 sorts-0.153
 juicy-0.144
 tiger-0.138
 elephant-0.127
Token the
Token ID262
Feature activation+2.96e+00

Pos logit contributions
angers+0.053
bled+0.048
ail+0.047
aj+0.045
immers+0.045
Neg logit contributions
 sorts-0.030
 course-0.029
 juicy-0.027
 tiger-0.024
leaf-0.024
Token hole
Token ID7604
Feature activation+1.39e+00

Pos logit contributions
angers+0.094
ail+0.084
 injuries+0.083
 conscience+0.082
 spine+0.082
Neg logit contributions
 sorts-0.084
 course-0.083
leaf-0.070
e-0.070
 juicy-0.067
Token.
Token ID13
Feature activation+6.73e-01

Pos logit contributions
angers+0.049
ail+0.045
aj+0.043
bled+0.043
uing+0.043
Neg logit contributions
 course-0.039
 sorts-0.038
 juicy-0.036
 tiger-0.035
 deer-0.032
Token She
Token ID1375
Feature activation-8.48e-01

Pos logit contributions
angers+0.026
bled+0.025
ail+0.024
uing+0.024
immers+0.023
Neg logit contributions
 course-0.017
 sorts-0.016
 tiger-0.015
 juicy-0.015
 animal-0.014
Token to
Token ID284
Feature activation+1.63e+00

Pos logit contributions
angers+0.103
ail+0.091
bled+0.089
aj+0.089
uing+0.088
Neg logit contributions
 course-0.077
 sorts-0.073
 juicy-0.069
 tiger-0.066
 deer-0.062
Token shoot
Token ID2686
Feature activation+1.82e+00

Pos logit contributions
angers+0.054
uing+0.051
ail+0.050
aj+0.048
bled+0.048
Neg logit contributions
 sorts-0.044
 course-0.042
 juicy-0.039
 turkey-0.039
 tiger-0.038
Token their
Token ID511
Feature activation+6.71e+00

Pos logit contributions
angers+0.063
uing+0.059
bled+0.058
ail+0.057
iece+0.056
Neg logit contributions
 sorts-0.046
 course-0.046
 juicy-0.040
leaf-0.039
 tiger-0.038
Token cars
Token ID5006
Feature activation-1.61e-03

Pos logit contributions
angers+0.234
aj+0.219
ail+0.215
bled+0.204
uing+0.204
Neg logit contributions
 sorts-0.192
 course-0.191
 juicy-0.167
leaf-0.152
igator-0.151
Token over
Token ID625
Feature activation+3.51e+00

Pos logit contributions
 sorts+0.000
 course+0.000
 juicy+0.000
 tiger+0.000
 deer+0.000
Neg logit contributions
angers-0.000
uing-0.000
ail-0.000
bled-0.000
iece-0.000
Token the
Token ID262
Feature activation+4.71e+00

Pos logit contributions
angers+0.124
ail+0.111
bled+0.110
ups+0.105
uing+0.105
Neg logit contributions
 sorts-0.088
 course-0.088
leaf-0.085
 juicy-0.084
 tiger-0.079
Token cone
Token ID27763
Feature activation+1.19e+00

Pos logit contributions
angers+0.159
aj+0.147
ail+0.147
immers+0.135
 spine+0.135
Neg logit contributions
 sorts-0.137
 course-0.127
 juicy-0.114
leaf-0.109
 deer-0.101
Token.
Token ID13
Feature activation+6.63e-01

Pos logit contributions
angers+0.038
ail+0.034
uing+0.032
anks+0.031
bled+0.031
Neg logit contributions
 course-0.038
 sorts-0.037
 juicy-0.037
leaf-0.034
 deer-0.033
Token They
Token ID1119
Feature activation-2.16e+00

Pos logit contributions
angers+0.025
ail+0.023
bled+0.023
uing+0.023
aj+0.022
Neg logit contributions
 course-0.017
 sorts-0.017
 juicy-0.016
 tiger-0.015
 animal-0.014
Token see
Token ID766
Feature activation+1.42e+00

Pos logit contributions
 sorts+0.062
 course+0.060
 juicy+0.057
 turkey+0.057
 animal+0.054
Neg logit contributions
uing-0.062
angers-0.062
ail-0.058
bles-0.057
immers-0.056
Token how
Token ID703
Feature activation+9.99e-01

Pos logit contributions
angers+0.056
bled+0.052
iece+0.050
ail+0.049
uing+0.049
Neg logit contributions
 sorts-0.031
 course-0.030
 juicy-0.027
leaf-0.024
 tiger-0.024
Token she
Token ID673
Feature activation+2.16e+00

Pos logit contributions
angers+0.082
ail+0.075
bled+0.072
uing+0.069
aj+0.069
Neg logit contributions
 course-0.086
 sorts-0.085
 tiger-0.082
 juicy-0.080
 snowball-0.078
Token created
Token ID2727
Feature activation+1.49e+00

Pos logit contributions
angers+0.071
bled+0.071
ail+0.069
uing+0.064
aj+0.064
Neg logit contributions
 sorts-0.057
 course-0.056
 tiger-0.053
 juicy-0.052
 snowball-0.052
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
angers+0.056
ail+0.050
bled+0.049
uing+0.049
aj+0.047
Neg logit contributions
 course-0.037
 tiger-0.037
 juicy-0.037
 sorts-0.035
 deer-0.034
Token
Token ID198
Feature activation+1.79e+00

Pos logit contributions
angers+0.042
uing+0.038
aj+0.038
bled+0.038
immers+0.038
Neg logit contributions
 course-0.025
 sorts-0.024
 juicy-0.022
 tiger-0.020
-0.019
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
angers+0.079
aj+0.071
immers+0.071
uing+0.070
bled+0.070
Neg logit contributions
 course-0.039
 sorts-0.036
 juicy-0.032
-0.030
 tiger-0.030
TokenWhen
Token ID2215
Feature activation+2.60e-01

Pos logit contributions
angers+0.040
ail+0.036
bled+0.036
aj+0.036
uing+0.035
Neg logit contributions
 course-0.029
 sorts-0.028
 juicy-0.027
 tiger-0.026
 animal-0.024
Token she
Token ID673
Feature activation+6.57e-01

Pos logit contributions
angers+0.010
ail+0.009
bled+0.009
aj+0.008
uing+0.008
Neg logit contributions
 course-0.007
 sorts-0.007
 tiger-0.006
 juicy-0.006
 elephant-0.006
Token was
Token ID373
Feature activation-1.08e+00

Pos logit contributions
ail+0.021
angers+0.020
bled+0.019
aj+0.019
uing+0.019
Neg logit contributions
 tiger-0.019
 juicy-0.019
 sorts-0.018
 course-0.018
 deer-0.018
Token done
Token ID1760
Feature activation+2.30e+00

Pos logit contributions
 course+0.036
 sorts+0.035
 juicy+0.033
 tiger+0.031
 piece+0.030
Neg logit contributions
angers-0.034
ail-0.030
aj-0.029
bled-0.029
uing-0.029
Token,
Token ID11
Feature activation+3.58e+00

Pos logit contributions
angers+0.095
aj+0.087
ail+0.087
bled+0.086
uing+0.084
Neg logit contributions
 course-0.053
 sorts-0.050
 juicy-0.047
 tiger-0.044
 piece-0.041
Token the
Token ID262
Feature activation+1.49e+00

Pos logit contributions
angers+0.124
ail+0.113
bled+0.113
aj+0.106
uing+0.106
Neg logit contributions
 course-0.102
 sorts-0.099
 tiger-0.093
 juicy-0.090
 elephant-0.085
Token to
Token ID284
Feature activation-5.42e-01

Pos logit contributions
 course+0.030
 sorts+0.029
 juicy+0.027
 tiger+0.026
 animal+0.024
Neg logit contributions
angers-0.052
ail-0.047
aj-0.047
bled-0.046
uing-0.046
Token hear
Token ID3285
Feature activation-1.90e-01

Pos logit contributions
 course+0.013
 sorts+0.011
 juicy+0.011
 tiger+0.010
 animal+0.010
Neg logit contributions
angers-0.023
aj-0.021
ail-0.021
bled-0.021
uing-0.020
Token from
Token ID422
Feature activation+9.68e-02

Pos logit contributions
 sorts+0.005
 course+0.005
 juicy+0.005
 tiger+0.005
 deer+0.005
Neg logit contributions
angers-0.007
ail-0.006
aj-0.006
bled-0.006
uing-0.006
Token Lily
Token ID20037
Feature activation+1.02e+00

Pos logit contributions
angers+0.004
ail+0.004
bled+0.004
aj+0.003
uing+0.003
Neg logit contributions
 course-0.002
 sorts-0.002
 juicy-0.002
 tiger-0.002
 piece-0.002
Token and
Token ID290
Feature activation-3.94e+00

Pos logit contributions
angers+0.038
ail+0.036
aj+0.035
uing+0.034
anks+0.033
Neg logit contributions
 course-0.028
 sorts-0.026
 juicy-0.025
 tiger-0.024
 spe-0.022
Token Ben
Token ID3932
Feature activation+1.62e+00

Pos logit contributions
 course+0.124
 sorts+0.119
 juicy+0.111
 tiger+0.109
 animal+0.102
Neg logit contributions
angers-0.133
aj-0.118
ail-0.117
bled-0.116
uing-0.110
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
angers+0.058
ail+0.053
aj+0.052
uing+0.052
bled+0.051
Neg logit contributions
 course-0.046
 sorts-0.044
 juicy-0.042
 tiger-0.041
 deer-0.037
Token She
Token ID1375
Feature activation-1.35e+00

Pos logit contributions
bled+0.013
angers+0.013
ail+0.013
immers+0.013
uing+0.012
Neg logit contributions
 sorts-0.006
 course-0.006
 juicy-0.006
-0.005
 tiger-0.005
Token loved
Token ID6151
Feature activation-2.89e+00

Pos logit contributions
 course+0.040
 sorts+0.038
 tiger+0.033
 juicy+0.032
 animal+0.031
Neg logit contributions
aj-0.042
angers-0.042
ail-0.042
uddled-0.039
bled-0.038
Token them
Token ID606
Feature activation+4.42e+00

Pos logit contributions
 course+0.092
 sorts+0.091
 juicy+0.083
 tiger+0.082
 piece+0.079
Neg logit contributions
angers-0.092
ail-0.079
aj-0.078
bled-0.076
uing-0.073
Token very
Token ID845
Feature activation-9.86e-01

Pos logit contributions
angers+0.142
ail+0.128
uing+0.127
aj+0.126
 conscience+0.125
Neg logit contributions
 sorts-0.123
 course-0.122
 spe-0.112
leaf-0.108
 juicy-0.106
Token leave
Token ID2666
Feature activation+2.43e+00

Pos logit contributions
angers+0.011
ail+0.010
aj+0.010
bled+0.010
uing+0.010
Neg logit contributions
 course-0.008
 sorts-0.008
 juicy-0.008
 tiger-0.007
 animal-0.007
Token his
Token ID465
Feature activation+6.21e+00

Pos logit contributions
angers+0.108
ail+0.099
aj+0.098
bled+0.097
uing+0.097
Neg logit contributions
 course-0.052
 sorts-0.047
 juicy-0.045
 tiger-0.043
 animal-0.040
Token t
Token ID256
Feature activation+1.02e+00

Pos logit contributions
angers+0.274
ail+0.249
bled+0.248
uing+0.245
aj+0.244
Neg logit contributions
 course-0.129
 sorts-0.121
 juicy-0.115
 tiger-0.112
 animal-0.102
Tokeneddy
Token ID21874
Feature activation+8.32e-01

Pos logit contributions
angers+0.038
bled+0.034
uing+0.034
aj+0.033
ail+0.033
Neg logit contributions
 course-0.025
 sorts-0.025
 tiger-0.024
 animal-0.023
 juicy-0.022
Token bear
Token ID6842
Feature activation+7.37e-01

Pos logit contributions
angers+0.035
ail+0.033
aj+0.032
bled+0.031
uing+0.030
Neg logit contributions
 sorts-0.018
 course-0.017
 juicy-0.016
leaf-0.014
 tiger-0.013
Token alone
Token ID3436
Feature activation+1.47e+00

Pos logit contributions
angers+0.022
ail+0.021
aj+0.020
uing+0.019
anks+0.018
Neg logit contributions
 sorts-0.025
 course-0.024
 juicy-0.023
leaf-0.022
 spe-0.021
Token.
Token ID13
Feature activation+5.76e-01

Pos logit contributions
angers+0.057
ail+0.051
aj+0.050
bled+0.050
uing+0.050
Neg logit contributions
 course-0.038
 sorts-0.037
 juicy-0.035
 tiger-0.033
 deer-0.030
Token He
Token ID679
Feature activation-1.54e-01

Pos logit contributions
angers+0.024
ail+0.022
bled+0.022
uing+0.022
immers+0.021
Neg logit contributions
 course-0.014
 tiger-0.014
 sorts-0.013
 juicy-0.013
 animal-0.012
Token said
Token ID531
Feature activation+3.09e+00

Pos logit contributions
 course+0.004
 sorts+0.004
 juicy+0.004
 tiger+0.003
 turkey+0.003
Neg logit contributions
angers-0.006
ail-0.005
aj-0.005
bled-0.005
uing-0.005
Token,
Token ID11
Feature activation+4.82e+00

Pos logit contributions
angers+0.169
immers+0.151
aj+0.151
ail+0.144
ippers+0.144
Neg logit contributions
 a-0.036
 juicy-0.035
 course-0.035
 tiger-0.033
 turkey-0.030
Token "
Token ID366
Feature activation-5.49e-01

Pos logit contributions
angers+0.198
immers+0.188
ail+0.184
aj+0.183
uing+0.175
Neg logit contributions
 tiger-0.107
 course-0.107
 juicy-0.105
 a-0.099
 elephant-0.097
Token tried
Token ID3088
Feature activation+1.72e+00

Pos logit contributions
angers+0.050
ail+0.047
aj+0.047
bled+0.046
uddled+0.045
Neg logit contributions
 course-0.041
 sorts-0.040
 juicy-0.037
 tiger-0.036
igator-0.034
Token to
Token ID284
Feature activation+1.35e+00

Pos logit contributions
angers+0.071
ail+0.064
aj+0.064
bled+0.063
uing+0.062
Neg logit contributions
 course-0.041
 sorts-0.039
 juicy-0.037
 tiger-0.036
 piece-0.033
Token play
Token ID711
Feature activation-8.80e-01

Pos logit contributions
angers+0.044
uing+0.044
ail+0.042
bled+0.042
aj+0.041
Neg logit contributions
 sorts-0.038
 course-0.036
 juicy-0.034
 tiger-0.033
 turkey-0.032
Token,
Token ID11
Feature activation+5.04e+00

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.015
 tiger+0.015
 animal+0.013
Neg logit contributions
angers-0.039
ail-0.036
bled-0.035
aj-0.035
uing-0.035
Token but
Token ID475
Feature activation+1.43e-01

Pos logit contributions
angers+0.158
uing+0.133
ail+0.132
aj+0.132
 spine+0.128
Neg logit contributions
 sorts-0.161
 course-0.156
 juicy-0.140
 tiger-0.140
 animal-0.134
Token it
Token ID340
Feature activation+3.04e+00

Pos logit contributions
angers+0.006
aj+0.006
ail+0.006
uing+0.006
immers+0.005
Neg logit contributions
 course-0.003
 sorts-0.003
 juicy-0.003
 tiger-0.003
 piece-0.002
Token sounded
Token ID14846
Feature activation+1.51e+00

Pos logit contributions
angers+0.113
ail+0.106
bled+0.105
aj+0.099
uing+0.099
Neg logit contributions
 course-0.080
 sorts-0.078
 juicy-0.072
 tiger-0.067
 turkey-0.065
Token loud
Token ID7812
Feature activation-3.97e+00

Pos logit contributions
angers+0.069
ail+0.063
aj+0.062
bled+0.062
uing+0.061
Neg logit contributions
 course-0.029
 sorts-0.027
 juicy-0.026
 tiger-0.024
 animal-0.021
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
 course+0.084
 sorts+0.083
 juicy+0.076
 tiger+0.070
 deer+0.066
Neg logit contributions
angers-0.168
bled-0.152
aj-0.151
ail-0.151
uing-0.150
Token noisy
Token ID31210
Feature activation-2.78e+00

Pos logit contributions
 course+0.053
 sorts+0.051
 juicy+0.046
 tiger+0.045
 animal+0.041
Neg logit contributions
angers-0.094
ail-0.085
bled-0.085
aj-0.085
uing-0.083
Token.
Token ID13
Feature activation+9.49e-01

Pos logit contributions
 course+0.068
 sorts+0.065
 juicy+0.061
 tiger+0.059
 animal+0.054
Neg logit contributions
angers-0.112
ail-0.101
aj-0.100
bled-0.099
uing-0.098
Token floor
Token ID4314
Feature activation+1.82e-01

Pos logit contributions
angers+0.109
ail+0.097
bled+0.095
aj+0.094
uing+0.092
Neg logit contributions
 course-0.105
 sorts-0.102
 juicy-0.094
 tiger-0.093
 deer-0.087
Token.
Token ID13
Feature activation+8.24e-01

Pos logit contributions
angers+0.007
ail+0.007
aj+0.007
bled+0.007
uing+0.007
Neg logit contributions
 course-0.004
 sorts-0.004
 juicy-0.004
 tiger-0.004
 animal-0.003
Token She
Token ID1375
Feature activation-8.10e-01

Pos logit contributions
angers+0.033
ail+0.033
immers+0.033
bled+0.032
uing+0.032
Neg logit contributions
 course-0.017
 juicy-0.017
 sorts-0.016
 a-0.014
 apple-0.014
Token didn
Token ID1422
Feature activation-8.22e-01

Pos logit contributions
 course+0.024
 sorts+0.024
 tiger+0.022
 juicy+0.021
 deer+0.021
Neg logit contributions
angers-0.027
ail-0.026
aj-0.025
bled-0.025
uddled-0.024
Token't
Token ID470
Feature activation-3.96e-01

Pos logit contributions
 course+0.027
 sorts+0.026
 juicy+0.025
 tiger+0.024
 deer+0.023
Neg logit contributions
angers-0.027
ail-0.024
bled-0.024
uing-0.023
aj-0.023
Token notice
Token ID4003
Feature activation+1.89e+00

Pos logit contributions
 course+0.010
 sorts+0.009
 tiger+0.009
 juicy+0.009
 deer+0.008
Neg logit contributions
angers-0.015
uing-0.014
ail-0.014
aj-0.013
bled-0.013
Token.
Token ID13
Feature activation+9.16e-01

Pos logit contributions
angers+0.077
ail+0.069
aj+0.068
bled+0.068
uing+0.067
Neg logit contributions
 sorts-0.044
 course-0.043
 tiger-0.040
 juicy-0.040
 deer-0.036
Token She
Token ID1375
Feature activation-7.24e-01

Pos logit contributions
immers+0.041
angers+0.040
uing+0.040
bled+0.040
ail+0.039
Neg logit contributions
 course-0.016
 sorts-0.015
 juicy-0.015
 a-0.014
-0.014
Token put
Token ID1234
Feature activation-1.16e+00

Pos logit contributions
 sorts+0.022
 course+0.022
 tiger+0.020
 juicy+0.019
 elephant+0.018
Neg logit contributions
angers-0.024
ail-0.023
bled-0.022
aj-0.022
uddled-0.021
Token the
Token ID262
Feature activation+3.51e+00

Pos logit contributions
 sorts+0.020
 course+0.020
 tiger+0.018
 juicy+0.017
 deer+0.016
Neg logit contributions
angers-0.054
bled-0.050
ail-0.049
aj-0.048
uing-0.048
Token pan
Token ID3425
Feature activation+1.70e+00

Pos logit contributions
angers+0.127
ail+0.117
bled+0.115
aj+0.113
uing+0.109
Neg logit contributions
 course-0.099
 sorts-0.098
 tiger-0.088
 juicy-0.086
 deer-0.081
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
angers+0.113
ail+0.101
aj+0.100
bled+0.099
uing+0.098
Neg logit contributions
 course-0.076
 sorts-0.072
 juicy-0.069
 tiger-0.067
 deer-0.062
Token<|endoftext|>
Token ID50256
Feature activation-2.42e+00

Pos logit contributions
angers+0.044
ail+0.039
aj+0.038
bled+0.038
uing+0.037
Neg logit contributions
 course-0.036
 sorts-0.034
 juicy-0.032
 tiger-0.031
 animal-0.029
TokenOnce
Token ID7454
Feature activation+2.55e+00

Pos logit contributions
 course+0.079
 sorts+0.077
 juicy+0.074
 tiger+0.071
 elephant+0.067
Neg logit contributions
angers-0.076
ail-0.068
aj-0.065
bled-0.065
uing-0.063
Token upon
Token ID2402
Feature activation-2.18e+00

Pos logit contributions
angers+0.085
immers+0.073
anks+0.073
bled+0.072
uing+0.070
Neg logit contributions
 course-0.082
 sorts-0.081
 juicy-0.073
 tiger-0.071
 piece-0.071
Token a
Token ID257
Feature activation-6.28e+00

Pos logit contributions
 course+0.049
 sorts+0.048
 elephant+0.042
 tiger+0.042
 gir+0.042
Neg logit contributions
angers-0.076
bled-0.074
aj-0.072
ail-0.071
iece-0.070
Token time
Token ID640
Feature activation-8.28e-01

Pos logit contributions
 sorts+0.153
 course+0.151
 tiger+0.139
 juicy+0.137
 elephant+0.135
Neg logit contributions
aj-0.225
angers-0.223
ail-0.219
uing-0.208
immers-0.200
Token,
Token ID11
Feature activation+7.34e-01

Pos logit contributions
 course+0.017
 sorts+0.015
 juicy+0.014
 tiger+0.013
+0.012
Neg logit contributions
angers-0.038
bled-0.034
aj-0.034
uing-0.034
immers-0.034
Token there
Token ID612
Feature activation-4.96e-01

Pos logit contributions
angers+0.027
bled+0.025
ail+0.025
aj+0.024
uing+0.024
Neg logit contributions
 course-0.019
 sorts-0.019
 juicy-0.017
 tiger-0.016
leaf-0.016
Token was
Token ID373
Feature activation-3.78e+00

Pos logit contributions
 course+0.011
 sorts+0.010
 juicy+0.010
 tiger+0.009
 animal+0.008
Neg logit contributions
angers-0.021
ail-0.019
aj-0.019
bled-0.019
uing-0.019
Token a
Token ID257
Feature activation-6.57e+00

Pos logit contributions
 sorts+0.096
 course+0.094
 tiger+0.085
igator+0.084
oc+0.081
Neg logit contributions
angers-0.118
bled-0.117
aj-0.102
ooks-0.101
 themselves-0.100
Token little
Token ID1310
Feature activation-6.69e+00

Pos logit contributions
 sorts+0.193
 course+0.191
leaf+0.156
 kinds+0.152
e+0.143
Neg logit contributions
angers-0.216
ail-0.208
aj-0.202
 conscience-0.184
uing-0.183
Token.
Token ID13
Feature activation-3.08e-03

Pos logit contributions
angers+0.094
ail+0.085
bled+0.083
uing+0.082
aj+0.082
Neg logit contributions
 course-0.074
 sorts-0.070
 juicy-0.070
 tiger-0.064
 turkey-0.061
Token Lily
Token ID20037
Feature activation-3.24e-01

Pos logit contributions
 course+0.000
 sorts+0.000
 juicy+0.000
 tiger+0.000
 piece+0.000
Neg logit contributions
angers-0.000
ail-0.000
aj-0.000
bled-0.000
uing-0.000
Token was
Token ID373
Feature activation-1.21e+00

Pos logit contributions
 course+0.008
 sorts+0.008
 juicy+0.007
 tiger+0.007
 turkey+0.006
Neg logit contributions
angers-0.013
ail-0.012
aj-0.012
bled-0.011
uing-0.011
Token scared
Token ID12008
Feature activation-3.35e+00

Pos logit contributions
 course+0.029
 sorts+0.026
 juicy+0.024
 tiger+0.022
 piece+0.021
Neg logit contributions
angers-0.050
bled-0.046
ail-0.046
aj-0.045
uing-0.043
Token,
Token ID11
Feature activation+3.38e+00

Pos logit contributions
 course+0.074
 sorts+0.073
 juicy+0.066
 tiger+0.063
 piece+0.058
Neg logit contributions
angers-0.140
ail-0.128
aj-0.125
uing-0.123
bled-0.123
Token but
Token ID475
Feature activation-8.50e-01

Pos logit contributions
angers+0.108
ail+0.094
bled+0.094
uing+0.089
aj+0.088
Neg logit contributions
 sorts-0.105
 course-0.102
 juicy-0.090
 tiger-0.089
leaf-0.088
Token her
Token ID607
Feature activation+3.29e+00

Pos logit contributions
 course+0.023
 sorts+0.023
 juicy+0.021
 tiger+0.020
 piece+0.019
Neg logit contributions
angers-0.031
bled-0.029
ail-0.028
aj-0.027
uing-0.027
Token mom
Token ID1995
Feature activation+9.94e-02

Pos logit contributions
angers+0.086
ail+0.072
bled+0.071
aj+0.071
uing+0.069
Neg logit contributions
 course-0.128
 sorts-0.124
 juicy-0.120
 tiger-0.118
 animal-0.112
Tokenmy
Token ID1820
Feature activation+1.69e-01

Pos logit contributions
ail+0.003
angers+0.003
uing+0.003
aj+0.003
bled+0.003
Neg logit contributions
 sorts-0.003
 course-0.003
 juicy-0.002
 tiger-0.002
 turkey-0.002
Token told
Token ID1297
Feature activation+8.63e-01

Pos logit contributions
ail+0.006
angers+0.006
uing+0.006
bled+0.006
aj+0.005
Neg logit contributions
 sorts-0.004
 course-0.004
 juicy-0.004
 tiger-0.004
 turkey-0.004
Token her
Token ID607
Feature activation+4.45e+00

Pos logit contributions
angers+0.035
aj+0.032
ail+0.032
bled+0.031
uing+0.031
Neg logit contributions
 course-0.022
 sorts-0.020
 juicy-0.019
 tiger-0.018
 animal-0.017
Tokeninky
Token ID29246
Feature activation-1.45e+00

Pos logit contributions
 sorts+0.025
 course+0.025
 tiger+0.025
 juicy+0.024
 animal+0.024
Neg logit contributions
angers-0.025
bled-0.023
iece-0.022
uing-0.022
immers-0.021
Token,
Token ID11
Feature activation+3.86e+00

Pos logit contributions
 course+0.027
 sorts+0.026
 animal+0.025
 elephant+0.024
 tiger+0.024
Neg logit contributions
angers-0.067
bled-0.061
aj-0.060
uddled-0.058
immers-0.058
Token "
Token ID366
Feature activation-1.14e+00

Pos logit contributions
angers+0.117
ail+0.102
aj+0.100
bled+0.100
uing+0.098
Neg logit contributions
 course-0.133
 sorts-0.129
 juicy-0.123
 tiger-0.120
 animal-0.113
TokenWhat
Token ID2061
Feature activation-1.13e+00

Pos logit contributions
 course+0.031
 sorts+0.031
 juicy+0.028
 tiger+0.027
 animal+0.025
Neg logit contributions
angers-0.042
ail-0.038
bled-0.037
aj-0.037
uing-0.036
Token happened
Token ID3022
Feature activation+1.87e+00

Pos logit contributions
 course+0.034
 sorts+0.032
 juicy+0.030
 tiger+0.029
 deer+0.028
Neg logit contributions
angers-0.036
ail-0.034
aj-0.033
uing-0.032
bled-0.032
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
angers+0.067
ail+0.061
aj+0.060
bled+0.059
uing+0.058
Neg logit contributions
 course-0.053
 sorts-0.052
 juicy-0.047
 tiger-0.045
 gir-0.042
Token your
Token ID534
Feature activation+4.82e+00

Pos logit contributions
 course+0.022
 sorts+0.022
 juicy+0.020
 tiger+0.019
 piece+0.017
Neg logit contributions
angers-0.046
ail-0.042
aj-0.041
bled-0.041
uing-0.041
Token knee
Token ID10329
Feature activation+1.13e+00

Pos logit contributions
angers+0.140
ail+0.123
aj+0.122
bled+0.118
uing+0.115
Neg logit contributions
 course-0.174
 sorts-0.169
 juicy-0.160
 tiger-0.154
 deer-0.146
Token?"
Token ID1701
Feature activation-4.23e-01

Pos logit contributions
angers+0.052
bled+0.047
ail+0.047
uing+0.046
aj+0.046
Neg logit contributions
 course-0.022
 sorts-0.020
 juicy-0.019
 tiger-0.018
 piece-0.017
Token B
Token ID347
Feature activation-1.49e+00

Pos logit contributions
 course+0.009
 sorts+0.008
 juicy+0.008
 tiger+0.008
 animal+0.007
Neg logit contributions
angers-0.019
bled-0.017
uing-0.017
immers-0.017
aj-0.017
Tokeninky
Token ID29246
Feature activation-1.94e+00

Pos logit contributions
 course+0.054
 sorts+0.053
 juicy+0.051
 tiger+0.051
 animal+0.048
Neg logit contributions
angers-0.040
bled-0.035
uing-0.034
ail-0.033
aj-0.033
Token.
Token ID13
Feature activation+9.20e-01

Pos logit contributions
 course+0.057
 sorts+0.055
 juicy+0.051
 tiger+0.048
 piece+0.045
Neg logit contributions
angers-0.095
ail-0.086
aj-0.085
bled-0.085
uing-0.084
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
immers+0.040
angers+0.039
uing+0.039
ail+0.038
bled+0.038
Neg logit contributions
 juicy-0.017
 sorts-0.016
 apple-0.015
 balloon-0.015
 chocolate-0.015
Token
Token ID198
Feature activation+7.99e-01

Pos logit contributions
angers+0.070
bled+0.064
immers+0.063
aj+0.063
ail+0.062
Neg logit contributions
 course-0.033
 sorts-0.032
 juicy-0.028
 tiger-0.027
-0.027
TokenBut
Token ID1537
Feature activation+2.20e+00

Pos logit contributions
angers+0.032
ail+0.029
aj+0.028
bled+0.028
uing+0.028
Neg logit contributions
 course-0.020
 sorts-0.019
 juicy-0.019
 tiger-0.017
 balloon-0.016
Token she
Token ID673
Feature activation-6.53e-02

Pos logit contributions
angers+0.097
ail+0.088
aj+0.087
uing+0.085
immers+0.085
Neg logit contributions
 course-0.047
 sorts-0.043
 juicy-0.042
 tiger-0.039
 animal-0.037
Token was
Token ID373
Feature activation-1.33e+00

Pos logit contributions
 course+0.002
 sorts+0.002
 juicy+0.002
 tiger+0.002
 deer+0.001
Neg logit contributions
angers-0.002
ail-0.002
bled-0.002
aj-0.002
uing-0.002
Token too
Token ID1165
Feature activation-3.84e-01

Pos logit contributions
 course+0.038
 sorts+0.037
 juicy+0.034
 tiger+0.033
 deer+0.031
Neg logit contributions
angers-0.049
ail-0.043
bled-0.043
aj-0.043
uing-0.042
Token small
Token ID1402
Feature activation-2.21e+00

Pos logit contributions
 course+0.009
 sorts+0.008
 juicy+0.008
 tiger+0.007
 animal+0.007
Neg logit contributions
angers-0.016
ail-0.015
aj-0.014
bled-0.014
uing-0.014
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
 course+0.070
 sorts+0.066
 juicy+0.065
 tiger+0.063
 deer+0.061
Neg logit contributions
angers-0.073
ail-0.063
aj-0.062
anks-0.060
uing-0.059
Token She
Token ID1375
Feature activation-1.01e+00

Pos logit contributions
 juicy+0.000
 apple+0.000
 course+0.000
 sorts+0.000
 tiger+0.000
Neg logit contributions
angers-0.000
ail-0.000
uing-0.000
bled-0.000
immers-0.000
Token could
Token ID714
Feature activation-1.73e+00

Pos logit contributions
 course+0.029
 sorts+0.029
 juicy+0.025
 tiger+0.025
 deer+0.024
Neg logit contributions
angers-0.035
ail-0.033
bled-0.032
aj-0.032
uing-0.030
Token was
Token ID373
Feature activation-1.63e+00

Pos logit contributions
 course+0.026
 sorts+0.025
 tiger+0.023
 juicy+0.023
leaf+0.022
Neg logit contributions
ail-0.029
angers-0.028
aj-0.028
uddled-0.025
ups-0.025
Token happy
Token ID3772
Feature activation-8.29e-01

Pos logit contributions
 course+0.051
 sorts+0.049
 juicy+0.045
 tiger+0.044
 deer+0.041
Neg logit contributions
angers-0.055
bled-0.049
ail-0.049
aj-0.049
uing-0.046
Token to
Token ID284
Feature activation-2.16e-01

Pos logit contributions
 course+0.018
 sorts+0.017
 juicy+0.015
 tiger+0.015
 deer+0.013
Neg logit contributions
angers-0.036
ail-0.033
aj-0.033
bled-0.032
uing-0.032
Token be
Token ID307
Feature activation+2.08e+00

Pos logit contributions
 course+0.004
 sorts+0.003
 juicy+0.003
 tiger+0.003
 piece+0.003
Neg logit contributions
angers-0.011
aj-0.010
bled-0.009
ail-0.009
uing-0.009
Token inside
Token ID2641
Feature activation+2.14e+00

Pos logit contributions
angers+0.087
ail+0.079
aj+0.078
bled+0.077
uing+0.077
Neg logit contributions
 course-0.048
 sorts-0.046
 juicy-0.044
 tiger-0.041
 animal-0.038
Token with
Token ID351
Feature activation-9.71e-01

Pos logit contributions
angers+0.078
ail+0.072
aj+0.070
uing+0.070
bled+0.069
Neg logit contributions
 course-0.054
 sorts-0.052
 tiger-0.052
 juicy-0.048
 deer-0.048
Token her
Token ID607
Feature activation+4.82e+00

Pos logit contributions
 course+0.028
 sorts+0.028
 tiger+0.026
 juicy+0.026
 deer+0.024
Neg logit contributions
angers-0.033
ail-0.030
bled-0.030
aj-0.030
uing-0.028
Token mom
Token ID1995
Feature activation+1.24e+00

Pos logit contributions
angers+0.128
aj+0.127
ail+0.120
bled+0.108
uing+0.106
Neg logit contributions
 sorts-0.177
 course-0.175
 juicy-0.156
leaf-0.151
 tiger-0.149
Tokenmy
Token ID1820
Feature activation+1.51e+00

Pos logit contributions
angers+0.036
ail+0.036
aj+0.035
uing+0.033
icking+0.032
Neg logit contributions
 sorts-0.038
 course-0.037
 tiger-0.037
leaf-0.036
 juicy-0.035
Token,
Token ID11
Feature activation+2.85e+00

Pos logit contributions
angers+0.049
ail+0.048
aj+0.046
uing+0.045
bled+0.043
Neg logit contributions
 sorts-0.044
 course-0.043
 juicy-0.040
leaf-0.040
 tiger-0.039
Token safe
Token ID3338
Feature activation+1.31e+00

Pos logit contributions
angers+0.099
aj+0.093
ail+0.088
bled+0.086
 conscience+0.085
Neg logit contributions
 course-0.072
 sorts-0.072
 tiger-0.063
igator-0.060
leaf-0.060
Token says
Token ID1139
Feature activation+2.91e+00

Pos logit contributions
 course+0.020
 sorts+0.020
 juicy+0.019
 tiger+0.018
 deer+0.017
Neg logit contributions
angers-0.021
ail-0.019
aj-0.019
uing-0.018
bled-0.018
Token to
Token ID284
Feature activation+4.81e-02

Pos logit contributions
angers+0.119
ail+0.107
aj+0.106
bled+0.105
uing+0.103
Neg logit contributions
 course-0.071
 sorts-0.066
 juicy-0.064
 tiger-0.061
 piece-0.057
Token Sam
Token ID3409
Feature activation+8.53e-01

Pos logit contributions
angers+0.002
aj+0.002
ail+0.002
bled+0.002
uing+0.002
Neg logit contributions
 course-0.001
 sorts-0.001
 juicy-0.001
 tiger-0.001
 animal-0.001
Token,
Token ID11
Feature activation+3.52e+00

Pos logit contributions
angers+0.034
ail+0.031
aj+0.031
bled+0.031
uing+0.030
Neg logit contributions
 course-0.021
 sorts-0.020
 juicy-0.019
 tiger-0.018
 animal-0.017
Token "
Token ID366
Feature activation-1.19e+00

Pos logit contributions
angers+0.109
ail+0.096
aj+0.094
bled+0.093
uing+0.091
Neg logit contributions
 course-0.119
 sorts-0.115
 juicy-0.110
 tiger-0.108
 animal-0.101
TokenI
Token ID40
Feature activation-5.87e+00

Pos logit contributions
 course+0.031
 juicy+0.030
 sorts+0.030
 tiger+0.029
 deer+0.028
Neg logit contributions
angers-0.043
iece-0.037
uing-0.036
bled-0.036
ups-0.036
Token am
Token ID716
Feature activation-1.96e-01

Pos logit contributions
 course+0.167
 tiger+0.151
 sorts+0.145
 juicy+0.145
 deer+0.143
Neg logit contributions
angers-0.203
uing-0.189
ail-0.185
aj-0.180
ippers-0.176
Token the
Token ID262
Feature activation+9.29e-01

Pos logit contributions
 course+0.005
 sorts+0.004
 tiger+0.004
 deer+0.004
pillar+0.003
Neg logit contributions
angers-0.008
bled-0.007
ail-0.007
aj-0.007
anks-0.007
Token boss
Token ID6478
Feature activation-2.22e+00

Pos logit contributions
angers+0.029
ail+0.025
bled+0.024
anks+0.024
aj+0.024
Neg logit contributions
 sorts-0.028
 course-0.028
 juicy-0.025
leaf-0.025
 tiger-0.024
Token of
Token ID286
Feature activation-2.59e+00

Pos logit contributions
 juicy+0.055
 course+0.053
 spe+0.050
 sorts+0.047
 gob+0.046
Neg logit contributions
angers-0.078
ail-0.066
line-0.066
ups-0.065
bles-0.065
Token the
Token ID262
Feature activation+2.14e+00

Pos logit contributions
 sorts+0.068
 course+0.064
 juicy+0.061
 tiger+0.060
 deer+0.058
Neg logit contributions
angers-0.093
bled-0.082
ail-0.082
uing-0.079
aj-0.077
Token played
Token ID2826
Feature activation-2.29e+00

Pos logit contributions
angers+0.002
ail+0.002
aj+0.002
uddled+0.002
iked+0.001
Neg logit contributions
 sorts-0.002
 course-0.002
 juicy-0.002
igator-0.002
 turkey-0.002
Token,
Token ID11
Feature activation+3.17e+00

Pos logit contributions
 course+0.049
 sorts+0.047
 juicy+0.043
 tiger+0.041
 animal+0.037
Neg logit contributions
angers-0.100
ail-0.091
bled-0.089
aj-0.089
uing-0.088
Token she
Token ID673
Feature activation+6.24e-01

Pos logit contributions
angers+0.107
ail+0.093
bled+0.092
iece+0.082
 conscience+0.082
Neg logit contributions
 sorts-0.095
 course-0.093
 tiger-0.083
 juicy-0.082
leaf-0.079
Token saw
Token ID2497
Feature activation+3.02e-01

Pos logit contributions
angers+0.023
ail+0.021
aj+0.021
bled+0.021
uing+0.020
Neg logit contributions
 course-0.017
 sorts-0.016
 juicy-0.015
 tiger-0.015
 animal-0.013
Token a
Token ID257
Feature activation-4.70e+00

Pos logit contributions
angers+0.014
bled+0.013
ail+0.012
iece+0.012
ups+0.012
Neg logit contributions
 sorts-0.005
 course-0.005
 juicy-0.004
 spe-0.004
 tiger-0.004
Token shiny
Token ID22441
Feature activation-6.50e+00

Pos logit contributions
 course+0.131
 sorts+0.128
e+0.106
leaf+0.100
+0.098
Neg logit contributions
angers-0.159
ail-0.152
aj-0.146
 conscience-0.141
uing-0.137
Token glass
Token ID5405
Feature activation-4.93e+00

Pos logit contributions
 sorts+0.178
+0.171
 course+0.163
leaf+0.148
e+0.135
Neg logit contributions
angers-0.222
 conscience-0.204
ail-0.200
ippers-0.194
rier-0.193
Token on
Token ID319
Feature activation-3.69e+00

Pos logit contributions
 sorts+0.122
 course+0.116
leaf+0.109
 tiger+0.102
e+0.099
Neg logit contributions
angers-0.174
ail-0.153
tub-0.153
bled-0.151
balls-0.148
Token the
Token ID262
Feature activation+1.90e+00

Pos logit contributions
 sorts+0.111
leaf+0.105
vous+0.094
 juicy+0.091
 course+0.089
Neg logit contributions
angers-0.096
bled-0.092
iece-0.087
 conscience-0.087
 themselves-0.085
Token ground
Token ID2323
Feature activation+1.04e-01

Pos logit contributions
angers+0.054
bled+0.048
ail+0.047
aj+0.044
 spine+0.043
Neg logit contributions
 sorts-0.068
 course-0.065
 juicy-0.058
 tiger-0.055
 spe-0.054
Token.
Token ID13
Feature activation-1.72e-01

Pos logit contributions
angers+0.003
ail+0.003
bled+0.003
iece+0.003
aj+0.002
Neg logit contributions
 course-0.003
 sorts-0.003
 tiger-0.003
 juicy-0.003
leaf-0.003
Token in
Token ID287
Feature activation-6.37e-01

Pos logit contributions
 course+0.031
 sorts+0.030
 juicy+0.027
 tiger+0.027
 elephant+0.025
Neg logit contributions
angers-0.054
bled-0.049
ail-0.049
aj-0.048
uing-0.048
Token it
Token ID340
Feature activation+4.45e+00

Pos logit contributions
 sorts+0.014
 tiger+0.014
 gir+0.014
 course+0.013
 juicy+0.013
Neg logit contributions
angers-0.023
ail-0.021
aj-0.021
bled-0.021
uing-0.020
Token.
Token ID13
Feature activation-7.42e-01

Pos logit contributions
angers+0.145
ail+0.133
aj+0.130
uing+0.129
bled+0.125
Neg logit contributions
 course-0.130
 sorts-0.127
 juicy-0.121
 tiger-0.120
leaf-0.119
Token Suddenly
Token ID24975
Feature activation+6.25e-02

Pos logit contributions
 course+0.023
 sorts+0.022
 juicy+0.021
 tiger+0.021
 piece+0.020
Neg logit contributions
angers-0.025
ail-0.022
aj-0.022
bled-0.021
uing-0.021
Token,
Token ID11
Feature activation+2.09e+00

Pos logit contributions
angers+0.002
ail+0.002
bled+0.002
aj+0.002
uing+0.002
Neg logit contributions
 course-0.002
 sorts-0.002
 juicy-0.001
 tiger-0.001
 animal-0.001
Token a
Token ID257
Feature activation-6.17e+00

Pos logit contributions
angers+0.076
ail+0.069
bled+0.068
aj+0.064
uing+0.062
Neg logit contributions
 sorts-0.057
 course-0.056
 juicy-0.051
 tiger-0.048
leaf-0.046
Token nos
Token ID43630
Feature activation-6.50e+00

Pos logit contributions
 sorts+0.156
 course+0.154
e+0.126
leaf+0.118
 kinds+0.116
Neg logit contributions
ail-0.216
angers-0.216
aj-0.199
 conscience-0.197
bled-0.195
Tokeny
Token ID88
Feature activation-3.46e+00

Pos logit contributions
 course+0.231
 juicy+0.226
 y+0.206
 ribbon+0.204
 sorts+0.202
Neg logit contributions
angers-0.166
ail-0.144
ying-0.136
line-0.131
iece-0.130
Token bird
Token ID6512
Feature activation-3.75e+00

Pos logit contributions
 sorts+0.082
 course+0.080
 juicy+0.064
leaf+0.062
 kinds+0.057
Neg logit contributions
angers-0.131
ail-0.130
 conscience-0.117
bled-0.117
aj-0.116
Token flew
Token ID13112
Feature activation-1.56e+00

Pos logit contributions
 sorts+0.115
 juicy+0.113
 course+0.106
 tiger+0.102
leaf+0.101
Neg logit contributions
ail-0.107
angers-0.106
bled-0.095
aj-0.094
leys-0.094
Token over
Token ID625
Feature activation+1.67e+00

Pos logit contributions
 course+0.054
 sorts+0.053
 juicy+0.048
 tiger+0.047
 piece+0.046
Neg logit contributions
angers-0.044
bled-0.041
ail-0.040
aj-0.036
uing-0.036
Token a
Token ID257
Feature activation-6.88e+00

Pos logit contributions
 sorts+0.101
 course+0.095
 tiger+0.084
oc+0.081
igator+0.078
Neg logit contributions
bled-0.144
angers-0.141
aj-0.125
ail-0.122
ooks-0.121
Token large
Token ID1588
Feature activation-7.68e+00

Pos logit contributions
 sorts+0.207
 course+0.203
leaf+0.164
 kinds+0.161
e+0.147
Neg logit contributions
angers-0.225
ail-0.216
aj-0.208
bled-0.194
 conscience-0.193
Token tray
Token ID26473
Feature activation-6.21e+00

Pos logit contributions
 sorts+0.202
leaf+0.193
 course+0.176
+0.169
e+0.156
Neg logit contributions
angers-0.252
ail-0.241
 conscience-0.232
aj-0.222
tub-0.215
Token.
Token ID13
Feature activation-2.49e+00

Pos logit contributions
 sorts+0.171
 juicy+0.168
 course+0.161
 snowball+0.157
leaf+0.153
Neg logit contributions
angers-0.195
ail-0.178
bled-0.173
tub-0.166
ider-0.165
Token The
Token ID383
Feature activation-1.43e+00

Pos logit contributions
 course+0.090
 sorts+0.079
leaf+0.074
 juicy+0.074
 deer+0.073
Neg logit contributions
angers-0.069
abies-0.056
ooks-0.054
aj-0.054
iked-0.054
Token tray
Token ID26473
Feature activation-5.57e+00

Pos logit contributions
 sorts+0.042
 course+0.041
+0.037
 spe+0.036
 tiger+0.035
Neg logit contributions
angers-0.047
ail-0.042
bled-0.040
abies-0.040
aj-0.040
Token was
Token ID373
Feature activation-2.44e+00

Pos logit contributions
 sorts+0.167
 course+0.163
 juicy+0.161
 snowball+0.155
leaf+0.153
Neg logit contributions
ail-0.161
angers-0.161
bled-0.147
uddled-0.143
aj-0.134
Token made
Token ID925
Feature activation-8.53e-01

Pos logit contributions
 course+0.075
 sorts+0.061
 tiger+0.056
pillar+0.054
leaf+0.053
Neg logit contributions
angers-0.090
bled-0.083
ail-0.080
aj-0.079
balls-0.072
Token of
Token ID286
Feature activation-2.73e+00

Pos logit contributions
 course+0.016
 tiger+0.013
 sorts+0.013
 juicy+0.012
 deer+0.011
Neg logit contributions
angers-0.041
ail-0.038
bled-0.037
uing-0.036
aj-0.036
Token wood
Token ID4898
Feature activation-4.07e-01

Pos logit contributions
 course+0.080
+0.068
leaf+0.064
igator+0.064
ah+0.063
Neg logit contributions
angers-0.089
aj-0.075
 parents-0.072
 wounds-0.072
ooks-0.072
Token,
Token ID11
Feature activation+2.96e+00

Pos logit contributions
 course+0.012
 sorts+0.010
 tiger+0.010
 juicy+0.009
leaf+0.009
Neg logit contributions
angers-0.015
ail-0.014
uing-0.013
anks-0.013
aj-0.013
Token.
Token ID13
Feature activation-5.40e-01

Pos logit contributions
angers+0.070
ail+0.064
aj+0.063
bled+0.063
uing+0.062
Neg logit contributions
 course-0.043
 sorts-0.041
 juicy-0.039
 tiger-0.038
 animal-0.035
Token Within
Token ID12511
Feature activation-2.45e+00

Pos logit contributions
 course+0.017
 sorts+0.017
 juicy+0.016
 tiger+0.015
 animal+0.015
Neg logit contributions
angers-0.018
ail-0.015
aj-0.015
bled-0.015
uing-0.015
Token minutes
Token ID2431
Feature activation-5.42e-01

Pos logit contributions
 tiger+0.064
 sorts+0.062
 juicy+0.061
 deer+0.060
 elephant+0.059
Neg logit contributions
angers-0.079
ail-0.077
bled-0.076
uing-0.075
aj-0.073
Token,
Token ID11
Feature activation+2.69e+00

Pos logit contributions
 course+0.013
 sorts+0.013
 juicy+0.012
 tiger+0.011
 piece+0.010
Neg logit contributions
angers-0.022
aj-0.020
ail-0.020
bled-0.019
uing-0.019
Token a
Token ID257
Feature activation-5.88e+00

Pos logit contributions
angers+0.104
ail+0.095
bled+0.094
aj+0.091
uing+0.090
Neg logit contributions
 course-0.066
 sorts-0.065
 juicy-0.059
 tiger-0.058
 elephant-0.053
Token delicious
Token ID12625
Feature activation-6.28e+00

Pos logit contributions
 sorts+0.147
 course+0.139
e+0.114
leaf+0.111
 kinds+0.111
Neg logit contributions
ail-0.205
angers-0.201
aj-0.194
 conscience-0.190
uing-0.187
Token chocolate
Token ID11311
Feature activation-3.85e+00

Pos logit contributions
 sorts+0.159
leaf+0.147
 course+0.142
+0.124
 arrow+0.123
Neg logit contributions
ail-0.196
 conscience-0.186
angers-0.185
uing-0.174
omm-0.174
Token cake
Token ID12187
Feature activation-2.08e-01

Pos logit contributions
 sorts+0.098
 course+0.088
leaf+0.080
 juicy+0.080
 deer+0.075
Neg logit contributions
angers-0.140
ail-0.133
bled-0.127
balls-0.125
aj-0.123
Token was
Token ID373
Feature activation-4.50e-01

Pos logit contributions
 course+0.004
 sorts+0.004
 tiger+0.004
 juicy+0.004
 deer+0.004
Neg logit contributions
angers-0.009
ail-0.008
bled-0.008
aj-0.008
uing-0.008
Token done
Token ID1760
Feature activation+3.51e+00

Pos logit contributions
 course+0.011
 sorts+0.011
 tiger+0.011
 deer+0.010
 animal+0.009
Neg logit contributions
angers-0.017
bled-0.016
ail-0.016
aj-0.015
uing-0.015
Token.
Token ID13
Feature activation+7.47e-02

Pos logit contributions
angers+0.142
ail+0.130
bled+0.128
uing+0.127
aj+0.126
Neg logit contributions
 course-0.084
 sorts-0.078
 tiger-0.075
 juicy-0.074
 deer-0.069