TOP ACTIVATIONS
MAX = 0.179

H oor ay ! I found a
and cheered , " H oor ay ! The fairy has
. " H oor ay , h oor ay
mom and dad , h oor ay ! They
H oor ay , h oor ay , h oor ay
everyone cheered . " H oor ay for Blue and his
" H oor ay !" said Tommy ,
time to go . H oor ay !
it felt wonderful . H oor ay ! <|endoftext|> Once upon
too spicy . " H oor ay !" said Mom my
. " H oor ay ! We did it
. " H oor ay , we found the
! " H oor ay !" shouted Ted as
Alice said , " H oor ay ! Let 's throw
We did it ! H oor ay !" he said .
Elsa smiled . " H oor ay , we took a
flew away . " H oor ay !" Jane shouted with
. They say " H oor ay ! We are the
special polish he couldn 't contain his happiness . He began
excited - she could hardly contain herself . She started to

MIN ACTIVATIONS
MIN = -0.196

the herb . It is lav ender . " That is
source . It was their ham ster cage . Their ham
ham ster cage . Their ham ster , Fl uffy ,
. He likes cheese and ham and lettuce too . He
because I like cheese and ham and yellow and red .
herb . It is lav ender . " That is not
cheeks . That is a ham ster . A rabbit has
cheese and ol ives and ham . They see mom 's
. It had cheese and ham and bread . He also
and the cheese and the ham . They put them on
out some cheese and some ham . She put them on
. It has cheese and ham and lettuce . It looks
Do you like cheese and ham ?" L ila
do not like cheese and ham . They are too salty
my hurts from the bad ham ," Lily said , rubbing
had already put cheese and ham in some of the eggs
. They were cheese and ham and lettuce . They were
. It is cheese and ham . Do you like cheese
watching her eat the pine con es . The squirrel said
and the cheese and the ham . Can you help me

INTERVAL 0.086 - 0.179
CONTAINS 1.447%

light way off in the distance . He ran over to
were ready for the next journey ! <|endoftext|> Sam my and
was living . He was eager to find the creature !
we can fix it ." <|endoftext|> Sam likes to play with
a year and more . <|endoftext|> Anna and Ben love to

INTERVAL -0.008 - 0.086
CONTAINS 58.085%

vendor is happy to see them . He gives them each
asleep with a tum my full of y ummy cookies .
to the theater again . They never missed one show !
to the beach . One day , he saw a big
it wouldn 't bud ge . Then , Bun remembered that

INTERVAL -0.102 - -0.008
CONTAINS 39.593%

and move in circles . Stella followed her mom 's lead
against the fat frog â s shell . The
himself in the mirror . His Mom my thought
She saw the dough on the table . She saw Lily
The people of the city cheered and cl apped

INTERVAL -0.196 - -0.102
CONTAINS 0.876%

messy pile of flour and sugar . " Do you want
. They also got some milk and bread .
cl apped as the cow gently carried the sheep to safety
like the butterfly and she can 't fly away whenever she
skirt is broken . What can I do ?" Her mom
Token
Token ID95
Feature activation-3.93e-02

Pos logit contributions
 Ho+0.064
 Rib+0.062
 H+0.057
 Bub+0.053
 Bun+0.052
Neg logit contributions
eks-0.051
oos-0.050
ays-0.049
cases-0.049
ases-0.049
Token
Token ID26391
Feature activation-8.98e-02

Pos logit contributions
 Ho+0.072
 Rib+0.071
 H+0.065
 Bub+0.059
 Bun+0.059
Neg logit contributions
eks-0.057
oos-0.057
ays-0.056
cases-0.056
ases-0.055
Token
Token ID129
Feature activation-3.91e-02

Pos logit contributions
 Ho+0.152
 Rib+0.148
 H+0.134
 Bun+0.122
 Bub+0.122
Neg logit contributions
eks-0.144
oos-0.143
 elevator-0.140
ays-0.139
ases-0.139
Token
Token ID241
Feature activation+5.11e-02

Pos logit contributions
 Ho+0.081
 Rib+0.079
 H+0.073
 Bub+0.068
 Bun+0.068
Neg logit contributions
eks-0.048
oos-0.048
ays-0.047
cases-0.046
 elevator-0.046
TokenH
Token ID39
Feature activation-1.93e-02

Pos logit contributions
he+0.077
oos+0.073
ases+0.073
hed+0.072
 elevator+0.072
Neg logit contributions
 Ho-0.092
 Rib-0.080
 Bun-0.075
 Ros-0.075
 Bub-0.073
Tokenoor
Token ID2675
Feature activation+1.71e-01

Pos logit contributions
 Ho+0.041
 Rib+0.041
 H+0.038
 Bub+0.035
 Bun+0.035
Neg logit contributions
eks-0.022
oos-0.022
cases-0.022
 elevator-0.021
ays-0.021
Tokenay
Token ID323
Feature activation+7.10e-02

Pos logit contributions
eks+0.133
oos+0.118
ases+0.117
 elevator+0.110
cks+0.108
Neg logit contributions
 Ho-0.437
 Rib-0.427
 H-0.413
 Bun-0.387
 Lucky-0.383
Token!
Token ID0
Feature activation+3.73e-02

Pos logit contributions
oos+0.100
eks+0.099
ays+0.097
cases+0.097
agged+0.097
Neg logit contributions
 Ho-0.134
 Rib-0.132
 H-0.121
 Bun-0.112
 Bub-0.111
Token I
Token ID314
Feature activation-3.11e-02

Pos logit contributions
ays+0.044
ases+0.042
he+0.040
ay+0.040
 are+0.038
Neg logit contributions
 Ho-0.065
 accidentally-0.065
 Rib-0.063
onna-0.060
please-0.060
Token found
Token ID1043
Feature activation+1.21e-02

Pos logit contributions
 Ho+0.049
 Rib+0.048
 H+0.043
 Bub+0.040
 Bun+0.039
Neg logit contributions
oos-0.053
eks-0.053
ays-0.052
cases-0.052
 elevator-0.052
Token a
Token ID257
Feature activation-1.29e-02

Pos logit contributions
eks+0.017
 elevator+0.016
ays+0.016
oos+0.016
ases+0.016
Neg logit contributions
 Rib-0.022
 Ho-0.022
 H-0.020
 accidentally-0.019
 Bun-0.019
Token and
Token ID290
Feature activation+1.47e-02

Pos logit contributions
eks+0.061
oos+0.059
ays+0.059
ases+0.058
 elevator+0.058
Neg logit contributions
 Ho-0.069
 Rib-0.067
 H-0.061
 Bub-0.057
 Bun-0.056
Token cheered
Token ID34767
Feature activation+4.23e-02

Pos logit contributions
eks+0.020
led+0.019
hed+0.019
cases+0.019
oos+0.019
Neg logit contributions
 Rib-0.027
 Ho-0.027
 H-0.024
 Butter-0.023
 Bub-0.022
Token,
Token ID11
Feature activation-2.78e-03

Pos logit contributions
oos+0.063
eks+0.062
cases+0.060
ays+0.060
ases+0.060
Neg logit contributions
 Ho-0.077
 Rib-0.075
 H-0.067
 Bub-0.063
 Bun-0.062
Token "
Token ID366
Feature activation+4.83e-03

Pos logit contributions
 Ho+0.005
 Rib+0.005
 H+0.004
 Bub+0.004
 Bun+0.004
Neg logit contributions
cases-0.004
eks-0.004
hed-0.004
 elevator-0.004
oos-0.004
TokenH
Token ID39
Feature activation-2.19e-02

Pos logit contributions
hed+0.007
he+0.007
oos+0.006
ases+0.006
eks+0.006
Neg logit contributions
 Ho-0.009
 Rib-0.009
 H-0.008
 accidentally-0.008
onna-0.008
Tokenoor
Token ID2675
Feature activation+1.70e-01

Pos logit contributions
 Ho+0.046
 Rib+0.046
 H+0.044
 Bub+0.041
 Bun+0.040
Neg logit contributions
cases-0.026
 elevator-0.025
eks-0.025
ays-0.024
oos-0.023
Tokenay
Token ID323
Feature activation+6.85e-02

Pos logit contributions
eks+0.122
oos+0.108
ases+0.107
 elevator+0.107
cases+0.098
Neg logit contributions
 Ho-0.448
 Rib-0.438
 H-0.420
 Bun-0.400
 Bub-0.393
Token!
Token ID0
Feature activation+3.92e-02

Pos logit contributions
cases+0.104
ays+0.102
roads+0.102
 elevator+0.101
oos+0.101
Neg logit contributions
 Ho-0.124
 Rib-0.121
 H-0.109
 Bun-0.103
 Tw-0.101
Token The
Token ID383
Feature activation-7.38e-03

Pos logit contributions
ays+0.047
ases+0.045
he+0.044
hed+0.044
oos+0.042
Neg logit contributions
 Ho-0.074
 Rib-0.071
 accidentally-0.067
onna-0.062
please-0.061
Token fairy
Token ID25607
Feature activation-1.04e-01

Pos logit contributions
 Rib+0.013
 Ho+0.013
 H+0.012
 Stri+0.011
 Butter+0.011
Neg logit contributions
 elevator-0.011
eks-0.011
oos-0.010
he-0.010
ases-0.010
Token has
Token ID468
Feature activation-2.87e-02

Pos logit contributions
 Ho+0.194
 Rib+0.190
 H+0.172
 Bub+0.160
 Bun+0.160
Neg logit contributions
oos-0.149
eks-0.147
ays-0.144
cases-0.143
 elevator-0.143
Token.
Token ID13
Feature activation-9.95e-03

Pos logit contributions
oos+0.056
cases+0.054
eks+0.053
 elevator+0.053
ays+0.053
Neg logit contributions
 Ho-0.084
 Rib-0.084
 H-0.074
 Bub-0.070
 Butter-0.070
Token
Token ID198
Feature activation-2.43e-02

Pos logit contributions
 Ho+0.020
 Rib+0.019
 H+0.017
 Bun+0.017
 accidentally+0.016
Neg logit contributions
oos-0.012
agged-0.012
ays-0.012
ases-0.012
ags-0.012
Token
Token ID198
Feature activation-2.42e-02

Pos logit contributions
 Ho+0.032
 Rib+0.032
 H+0.026
 Butter+0.024
 accidentally+0.023
Neg logit contributions
he-0.047
ases-0.046
eks-0.046
oos-0.046
ays-0.045
Token"
Token ID1
Feature activation+4.47e-02

Pos logit contributions
 Ho+0.036
 Rib+0.035
 H+0.031
 Bub+0.029
 Bun+0.029
Neg logit contributions
eks-0.044
oos-0.044
ays-0.043
cases-0.043
 elevator-0.043
TokenH
Token ID39
Feature activation-2.33e-02

Pos logit contributions
agged+0.060
ases+0.059
oos+0.059
hed+0.058
he+0.058
Neg logit contributions
 Ho-0.086
 Rib-0.079
 H-0.075
 Bun-0.070
 accidentally-0.069
Tokenoor
Token ID2675
Feature activation+1.70e-01

Pos logit contributions
 Rib+0.038
 Ho+0.037
 H+0.035
 Bub+0.034
 Fro+0.032
Neg logit contributions
eks-0.038
cases-0.036
 elevator-0.036
ps-0.035
 bags-0.035
Tokenay
Token ID323
Feature activation+7.08e-02

Pos logit contributions
eks+0.181
cks+0.172
ps+0.167
ases+0.159
oos+0.155
Neg logit contributions
 Ho-0.377
 Rib-0.364
 H-0.362
 Bun-0.338
 Lucky-0.331
Token,
Token ID11
Feature activation-5.37e-03

Pos logit contributions
ays+0.120
agged+0.119
oos+0.118
cases+0.118
eks+0.118
Neg logit contributions
 Ho-0.114
 Rib-0.112
 H-0.103
 Bun-0.094
 Bub-0.091
Token h
Token ID289
Feature activation-3.43e-02

Pos logit contributions
 Ho+0.008
 Rib+0.008
 H+0.007
 Bun+0.006
 accidentally+0.006
Neg logit contributions
 elevator-0.010
eks-0.010
oos-0.009
cases-0.009
ases-0.009
Tokenoor
Token ID2675
Feature activation+1.69e-01

Pos logit contributions
 Rib+0.061
 Ho+0.059
 H+0.055
 Bub+0.053
 Stri+0.051
Neg logit contributions
eks-0.052
led-0.049
aks-0.049
roads-0.049
igators-0.048
Tokenay
Token ID323
Feature activation+7.05e-02

Pos logit contributions
eks+0.176
cks+0.156
ases+0.153
ps+0.150
oos+0.148
Neg logit contributions
 Ho-0.388
 Rib-0.377
 H-0.372
 Bun-0.352
 Lucky-0.340
Token mom
Token ID1995
Feature activation+6.17e-02

Pos logit contributions
 Ho+0.012
 Rib+0.012
 H+0.011
 Bun+0.010
 Bub+0.010
Neg logit contributions
eks-0.012
 elevator-0.012
ays-0.012
oos-0.012
cases-0.011
Token and
Token ID290
Feature activation+9.52e-03

Pos logit contributions
eks+0.088
oos+0.087
ays+0.085
 elevator+0.085
cases+0.084
Neg logit contributions
 Ho-0.116
 Rib-0.114
 H-0.103
 Bub-0.096
 Bun-0.095
Token dad
Token ID9955
Feature activation+1.05e-01

Pos logit contributions
eks+0.015
oos+0.015
ays+0.015
cases+0.015
 elevator+0.015
Neg logit contributions
 Ho-0.016
 Rib-0.016
 H-0.014
 Bub-0.013
 Bun-0.013
Token,
Token ID11
Feature activation-6.19e-03

Pos logit contributions
oos+0.170
ays+0.163
agged+0.163
eks+0.163
cases+0.160
Neg logit contributions
 Ho-0.181
 Rib-0.174
 H-0.160
 Bub-0.148
 accidentally-0.147
Token h
Token ID289
Feature activation-3.63e-02

Pos logit contributions
 Ho+0.011
 Rib+0.011
 H+0.010
 Bub+0.009
 Bun+0.009
Neg logit contributions
eks-0.009
oos-0.009
 elevator-0.009
ases-0.009
ays-0.009
Tokenoor
Token ID2675
Feature activation+1.69e-01

Pos logit contributions
 Rib+0.065
 Ho+0.063
 H+0.057
 Tw+0.053
 Bub+0.053
Neg logit contributions
eks-0.050
roads-0.050
igators-0.050
aks-0.047
 elevator-0.047
Tokenay
Token ID323
Feature activation+7.06e-02

Pos logit contributions
eks+0.183
cks+0.175
ases+0.169
oos+0.168
ps+0.161
Neg logit contributions
 Ho-0.358
 H-0.339
 Rib-0.339
 Lucky-0.311
 Bun-0.310
Token!
Token ID0
Feature activation+3.25e-02

Pos logit contributions
eks+0.106
agged+0.102
oos+0.101
roads+0.101
ays+0.101
Neg logit contributions
 Ho-0.130
 Rib-0.128
 H-0.115
 Tw-0.106
 Bun-0.105
Token
Token ID198
Feature activation-2.59e-02

Pos logit contributions
ays+0.058
ases+0.055
he+0.055
cases+0.054
agged+0.054
Neg logit contributions
 Ho-0.047
 Rib-0.046
 H-0.041
 Bun-0.039
 Bub-0.039
Token
Token ID198
Feature activation-2.62e-02

Pos logit contributions
 Ho+0.039
 Rib+0.038
 H+0.033
 Bub+0.031
 accidentally+0.030
Neg logit contributions
he-0.047
eks-0.045
ays-0.044
ases-0.044
 elevator-0.044
TokenThey
Token ID2990
Feature activation+7.00e-02

Pos logit contributions
 Ho+0.044
 Rib+0.043
 H+0.039
 Bub+0.036
 Bun+0.035
Neg logit contributions
eks-0.042
he-0.042
oos-0.041
ays-0.041
ases-0.041
TokenH
Token ID39
Feature activation-2.33e-02

Pos logit contributions
agged+0.060
ases+0.059
oos+0.059
hed+0.058
he+0.058
Neg logit contributions
 Ho-0.086
 Rib-0.079
 H-0.075
 Bun-0.070
 accidentally-0.069
Tokenoor
Token ID2675
Feature activation+1.70e-01

Pos logit contributions
 Rib+0.038
 Ho+0.037
 H+0.035
 Bub+0.034
 Fro+0.032
Neg logit contributions
eks-0.038
cases-0.036
 elevator-0.036
ps-0.035
 bags-0.035
Tokenay
Token ID323
Feature activation+7.08e-02

Pos logit contributions
eks+0.181
cks+0.172
ps+0.167
ases+0.159
oos+0.155
Neg logit contributions
 Ho-0.377
 Rib-0.364
 H-0.362
 Bun-0.338
 Lucky-0.331
Token,
Token ID11
Feature activation-5.37e-03

Pos logit contributions
ays+0.120
agged+0.119
oos+0.118
cases+0.118
eks+0.118
Neg logit contributions
 Ho-0.114
 Rib-0.112
 H-0.103
 Bun-0.094
 Bub-0.091
Token h
Token ID289
Feature activation-3.43e-02

Pos logit contributions
 Ho+0.008
 Rib+0.008
 H+0.007
 Bun+0.006
 accidentally+0.006
Neg logit contributions
 elevator-0.010
eks-0.010
oos-0.009
cases-0.009
ases-0.009
Tokenoor
Token ID2675
Feature activation+1.69e-01

Pos logit contributions
 Rib+0.061
 Ho+0.059
 H+0.055
 Bub+0.053
 Stri+0.051
Neg logit contributions
eks-0.052
led-0.049
aks-0.049
roads-0.049
igators-0.048
Tokenay
Token ID323
Feature activation+7.05e-02

Pos logit contributions
eks+0.176
cks+0.156
ases+0.153
ps+0.150
oos+0.148
Neg logit contributions
 Ho-0.388
 Rib-0.377
 H-0.372
 Bun-0.352
 Lucky-0.340
Token,
Token ID11
Feature activation-5.60e-03

Pos logit contributions
ays+0.113
roads+0.113
eks+0.111
cases+0.110
agged+0.110
Neg logit contributions
 Ho-0.119
 Rib-0.118
 H-0.109
 Bun-0.100
 Bub-0.097
Token h
Token ID289
Feature activation-3.43e-02

Pos logit contributions
 Ho+0.009
 Rib+0.009
 H+0.008
 Bun+0.007
 accidentally+0.007
Neg logit contributions
 elevator-0.009
eks-0.009
cases-0.009
oos-0.009
he-0.009
Tokenoor
Token ID2675
Feature activation+1.69e-01

Pos logit contributions
 Rib+0.061
 Ho+0.059
 H+0.055
 Bub+0.053
 Stri+0.051
Neg logit contributions
eks-0.052
roads-0.049
led-0.048
aks-0.048
igators-0.048
Tokenay
Token ID323
Feature activation+7.05e-02

Pos logit contributions
eks+0.174
ases+0.152
cks+0.152
oos+0.147
ps+0.145
Neg logit contributions
 Ho-0.390
 Rib-0.380
 H-0.375
 Bun-0.357
 Lucky-0.342
Token everyone
Token ID2506
Feature activation+6.32e-02

Pos logit contributions
eks+0.025
cases+0.025
 elevator+0.024
oos+0.024
led+0.024
Neg logit contributions
 Rib-0.025
 Ho-0.025
 H-0.022
 Bub-0.020
 Po-0.019
Token cheered
Token ID34767
Feature activation+4.26e-02

Pos logit contributions
eks+0.103
oos+0.103
ays+0.100
 elevator+0.100
cases+0.100
Neg logit contributions
 Ho-0.105
 Rib-0.103
 H-0.092
 Bub-0.084
 Bun-0.083
Token.
Token ID13
Feature activation-3.90e-03

Pos logit contributions
eks+0.062
oos+0.061
ays+0.060
 elevator+0.059
cases+0.059
Neg logit contributions
 Ho-0.080
 Rib-0.078
 H-0.071
 Bub-0.066
 Bun-0.066
Token "
Token ID366
Feature activation+5.00e-03

Pos logit contributions
 Rib+0.005
 Ho+0.005
 H+0.004
 accidentally+0.004
 Fro+0.004
Neg logit contributions
cases-0.007
agged-0.007
hed-0.007
ays-0.007
oos-0.007
TokenH
Token ID39
Feature activation-2.28e-02

Pos logit contributions
hed+0.007
he+0.007
eks+0.007
agged+0.007
oos+0.006
Neg logit contributions
 Ho-0.010
 Rib-0.009
 H-0.008
onna-0.008
 Fro-0.008
Tokenoor
Token ID2675
Feature activation+1.68e-01

Pos logit contributions
 Ho+0.045
 Rib+0.044
 H+0.043
 Bun+0.041
 Bub+0.040
Neg logit contributions
 elevator-0.030
ays-0.030
eks-0.030
oos-0.029
cases-0.029
Tokenay
Token ID323
Feature activation+6.77e-02

Pos logit contributions
eks+0.163
cks+0.148
ases+0.144
 elevator+0.144
ps+0.144
Neg logit contributions
 Ho-0.402
 Rib-0.388
 H-0.382
 Bun-0.367
 Bub-0.351
Token for
Token ID329
Feature activation+2.88e-02

Pos logit contributions
cases+0.106
ays+0.104
oos+0.103
 elevator+0.102
roads+0.100
Neg logit contributions
 Ho-0.121
 Rib-0.117
 H-0.109
 Bun-0.103
 Bub-0.098
Token Blue
Token ID4518
Feature activation-7.49e-02

Pos logit contributions
eks+0.045
oos+0.044
ases+0.043
 elevator+0.043
ays+0.042
Neg logit contributions
 Ho-0.050
 Rib-0.050
 H-0.044
 Bub-0.041
 Bun-0.040
Token and
Token ID290
Feature activation+1.51e-02

Pos logit contributions
 Ho+0.145
 Rib+0.142
 H+0.129
 Bun+0.121
 Bub+0.120
Neg logit contributions
eks-0.103
oos-0.103
ays-0.100
 elevator-0.100
cases-0.099
Token his
Token ID465
Feature activation+2.39e-02

Pos logit contributions
eks+0.023
 elevator+0.023
oos+0.022
ases+0.022
led+0.022
Neg logit contributions
 Rib-0.025
 Ho-0.025
 H-0.022
 Stri-0.020
 Tw-0.020
Token
Token ID220
Feature activation+1.68e-02

Pos logit contributions
 Ho+0.006
 Rib+0.006
 H+0.005
 Bun+0.005
 Tw+0.005
Neg logit contributions
cases-0.005
ays-0.005
 elevator-0.005
oos-0.005
agged-0.005
Token
Token ID198
Feature activation-1.59e-02

Pos logit contributions
ays+0.032
cases+0.031
he+0.031
oos+0.031
hed+0.031
Neg logit contributions
 Rib-0.024
 Ho-0.023
 H-0.019
 Bub-0.018
 Po-0.017
Token
Token ID198
Feature activation-1.64e-02

Pos logit contributions
 Ho+0.024
 Rib+0.024
 H+0.020
 Po+0.019
 Bub+0.018
Neg logit contributions
he-0.030
cases-0.028
hed-0.027
irens-0.026
agged-0.026
Token"
Token ID1
Feature activation+5.02e-02

Pos logit contributions
 Ho+0.028
 Rib+0.027
 H+0.024
 Bub+0.022
 Bun+0.022
Neg logit contributions
oos-0.027
eks-0.026
cases-0.026
 elevator-0.026
ays-0.026
TokenH
Token ID39
Feature activation-2.31e-02

Pos logit contributions
eks+0.076
he+0.075
oos+0.075
ays+0.073
ases+0.073
Neg logit contributions
 Ho-0.090
 Rib-0.086
 H-0.078
 Bub-0.073
 Bun-0.073
Tokenoor
Token ID2675
Feature activation+1.67e-01

Pos logit contributions
 Rib+0.048
 Ho+0.047
 H+0.046
onna+0.042
 accidentally+0.041
Neg logit contributions
eks-0.027
cases-0.025
 elevator-0.024
led-0.024
roads-0.023
Tokenay
Token ID323
Feature activation+6.81e-02

Pos logit contributions
eks+0.171
cks+0.152
ases+0.151
ps+0.146
oos+0.146
Neg logit contributions
 Ho-0.381
 H-0.368
 Rib-0.368
 Bun-0.346
 Lucky-0.333
Token!"
Token ID2474
Feature activation+2.56e-02

Pos logit contributions
ays+0.108
roads+0.107
oos+0.107
ags+0.107
agged+0.107
Neg logit contributions
 Ho-0.112
 Rib-0.110
 H-0.101
 Bun-0.094
 Bub-0.091
Token said
Token ID531
Feature activation-1.51e-02

Pos logit contributions
cases+0.042
 elevator+0.041
he+0.041
eks+0.040
oos+0.040
Neg logit contributions
 Ho-0.041
 Rib-0.041
 H-0.035
 Bun-0.033
 Bub-0.032
Token Tommy
Token ID19919
Feature activation+3.04e-02

Pos logit contributions
 Ho+0.027
 Rib+0.026
 H+0.023
 Bun+0.022
 Butter+0.021
Neg logit contributions
 elevator-0.021
oos-0.021
he-0.021
cases-0.021
ays-0.020
Token,
Token ID11
Feature activation-4.75e-03

Pos logit contributions
cases+0.033
hed+0.030
he+0.029
led+0.028
ow+0.027
Neg logit contributions
 Ho-0.068
 Rib-0.067
 H-0.058
 Bub-0.058
 Butter-0.058
Token time
Token ID640
Feature activation-8.24e-03

Pos logit contributions
 elevator+0.015
eks+0.015
ags+0.015
agged+0.014
oos+0.014
Neg logit contributions
 Rib-0.028
 Ho-0.026
 H-0.023
 Bub-0.022
 Stri-0.022
Token to
Token ID284
Feature activation-1.51e-02

Pos logit contributions
 Ho+0.012
 Rib+0.011
 H+0.010
 Bub+0.009
 Bun+0.009
Neg logit contributions
oos-0.016
eks-0.016
ays-0.015
ases-0.015
agged-0.015
Token go
Token ID467
Feature activation+2.58e-02

Pos logit contributions
 Ho+0.031
 Rib+0.030
 H+0.028
 Bub+0.026
 Bun+0.026
Neg logit contributions
oos-0.019
eks-0.019
ays-0.019
cases-0.018
agged-0.018
Token.
Token ID13
Feature activation-4.35e-03

Pos logit contributions
oos+0.043
agged+0.042
eks+0.042
ays+0.042
ases+0.042
Neg logit contributions
 Ho-0.043
 Rib-0.040
 H-0.039
 Bun-0.035
 Bub-0.035
Token H
Token ID367
Feature activation-5.32e-02

Pos logit contributions
 Ho+0.006
 Rib+0.006
 H+0.005
 Bun+0.005
 Tooth+0.005
Neg logit contributions
ays-0.007
oos-0.007
ases-0.007
eks-0.007
hed-0.007
Tokenoor
Token ID2675
Feature activation+1.66e-01

Pos logit contributions
 Ho+0.085
 Rib+0.082
 H+0.073
 Bub+0.067
 Bun+0.067
Neg logit contributions
oos-0.092
eks-0.091
ays-0.090
ases-0.089
cases-0.088
Tokenay
Token ID323
Feature activation+6.70e-02

Pos logit contributions
eks+0.158
ases+0.145
cks+0.144
oos+0.139
 elevator+0.130
Neg logit contributions
 Ho-0.390
 Rib-0.377
 H-0.376
 Bun-0.352
 Lucky-0.341
Token!
Token ID0
Feature activation+3.57e-02

Pos logit contributions
oos+0.094
eks+0.094
cases+0.092
 elevator+0.090
ays+0.090
Neg logit contributions
 Ho-0.126
 Rib-0.124
 H-0.112
 Bub-0.104
 Butter-0.103
Token
Token ID220
Feature activation+1.59e-02

Pos logit contributions
ays+0.055
oos+0.052
ases+0.051
he+0.051
agged+0.049
Neg logit contributions
 Ho-0.056
 Rib-0.055
 accidentally-0.050
please-0.049
 Bun-0.047
Token
Token ID198
Feature activation-1.84e-02

Pos logit contributions
ays+0.026
he+0.026
oos+0.025
cases+0.024
ases+0.024
Neg logit contributions
 Rib-0.026
 Ho-0.025
 fle-0.021
 H-0.020
 accidentally-0.020
Token
Token ID198
Feature activation-1.83e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.023
 accidentally+0.022
 Butter+0.022
Neg logit contributions
he-0.034
eks-0.031
oos-0.030
ases-0.030
hed-0.030
Token it
Token ID340
Feature activation+1.17e-02

Pos logit contributions
eks+0.013
cases+0.013
 elevator+0.013
led+0.013
oos+0.013
Neg logit contributions
 Ho-0.013
 Rib-0.013
 H-0.012
 Butter-0.011
 Tw-0.010
Token felt
Token ID2936
Feature activation+1.22e-02

Pos logit contributions
eks+0.021
oos+0.021
cases+0.020
 elevator+0.020
ays+0.020
Neg logit contributions
 Ho-0.018
 Rib-0.017
 H-0.015
 Bub-0.014
 Bun-0.014
Token wonderful
Token ID7932
Feature activation-3.61e-04

Pos logit contributions
eks+0.020
oos+0.020
ays+0.019
 elevator+0.019
cases+0.019
Neg logit contributions
 Ho-0.020
 Rib-0.020
 H-0.018
 Bub-0.016
 Bun-0.016
Token.
Token ID13
Feature activation-9.41e-03

Pos logit contributions
 Ho+0.001
 Rib+0.001
 H+0.001
 Bub+0.001
 Bun+0.001
Neg logit contributions
eks-0.001
oos-0.001
ays-0.001
 elevator-0.001
ases-0.001
Token H
Token ID367
Feature activation-5.56e-02

Pos logit contributions
 Rib+0.016
 Ho+0.015
 accidentally+0.014
 H+0.013
Ros+0.013
Neg logit contributions
hed-0.014
he-0.014
ays-0.014
oos-0.014
agged-0.014
Tokenoor
Token ID2675
Feature activation+1.65e-01

Pos logit contributions
 Ho+0.097
 Rib+0.095
 H+0.092
 Bun+0.086
 Bub+0.083
Neg logit contributions
 elevator-0.085
eks-0.083
oos-0.077
 lobby-0.077
ags-0.077
Tokenay
Token ID323
Feature activation+6.53e-02

Pos logit contributions
eks+0.123
oos+0.117
ases+0.114
 elevator+0.111
ays+0.109
Neg logit contributions
 Ho-0.427
 Rib-0.418
 H-0.396
 Bun-0.376
 Bub-0.374
Token!
Token ID0
Feature activation+3.19e-02

Pos logit contributions
eks+0.075
oos+0.075
cases+0.072
ases+0.071
 elevator+0.071
Neg logit contributions
 Ho-0.139
 Rib-0.137
 H-0.125
 Bub-0.118
 Butter-0.117
Token<|endoftext|>
Token ID50256
Feature activation+1.15e-01

Pos logit contributions
he+0.052
hed+0.049
ays+0.047
agged+0.046
 are+0.045
Neg logit contributions
 Rib-0.049
 accidentally-0.047
 Ho-0.047
please-0.043
onna-0.042
TokenOnce
Token ID7454
Feature activation+1.17e-02

Pos logit contributions
he+0.160
hed+0.148
ays+0.140
oos+0.138
agged+0.130
Neg logit contributions
 Rib-0.227
 Ho-0.224
 H-0.197
 accidentally-0.194
 Butter-0.192
Token upon
Token ID2402
Feature activation+2.40e-02

Pos logit contributions
eks+0.021
oos+0.021
ays+0.021
 elevator+0.021
cases+0.021
Neg logit contributions
 Ho-0.017
 Rib-0.017
 H-0.015
 Bub-0.013
 Bun-0.013
Token too
Token ID1165
Feature activation-3.27e-02

Pos logit contributions
 Ho+0.064
 Rib+0.063
 H+0.056
 Bub+0.053
 Bun+0.052
Neg logit contributions
oos-0.052
eks-0.052
 elevator-0.051
ays-0.051
cases-0.051
Token spicy
Token ID26880
Feature activation-2.01e-02

Pos logit contributions
 Ho+0.056
 Rib+0.054
 H+0.049
 accidentally+0.045
 Bub+0.044
Neg logit contributions
eks-0.053
oos-0.053
ays-0.051
agged-0.051
ases-0.051
Token.
Token ID13
Feature activation-8.17e-03

Pos logit contributions
 Ho+0.034
 Rib+0.032
 H+0.029
 Bub+0.027
 Bun+0.027
Neg logit contributions
eks-0.034
agged-0.032
oos-0.032
ays-0.032
 elevator-0.031
Token "
Token ID366
Feature activation+2.27e-03

Pos logit contributions
 Ho+0.014
 Rib+0.013
 H+0.012
 Bub+0.011
 Bun+0.011
Neg logit contributions
cases-0.013
oos-0.013
ays-0.013
 elevator-0.013
agged-0.012
TokenH
Token ID39
Feature activation-2.57e-02

Pos logit contributions
he+0.003
oos+0.003
eks+0.003
ays+0.003
ases+0.003
Neg logit contributions
 Ho-0.004
 Rib-0.004
 H-0.004
 Bub-0.003
 Bun-0.003
Tokenoor
Token ID2675
Feature activation+1.64e-01

Pos logit contributions
 Rib+0.041
 Ho+0.041
 H+0.037
onna+0.034
 accidentally+0.033
Neg logit contributions
eks-0.043
cases-0.042
 elevator-0.041
roads-0.040
oos-0.040
Tokenay
Token ID323
Feature activation+6.55e-02

Pos logit contributions
eks+0.162
cks+0.147
ases+0.143
ps+0.137
oos+0.136
Neg logit contributions
 Ho-0.384
 Rib-0.367
 H-0.366
 Bun-0.347
 Lucky-0.337
Token!"
Token ID2474
Feature activation+3.42e-02

Pos logit contributions
cases+0.097
ays+0.097
eks+0.097
oos+0.097
agged+0.096
Neg logit contributions
 Ho-0.116
 Rib-0.112
 H-0.105
 Bun-0.097
 Bub-0.093
Token said
Token ID531
Feature activation-1.97e-02

Pos logit contributions
eks+0.064
oos+0.064
ases+0.062
ays+0.062
 elevator+0.062
Neg logit contributions
 Ho-0.050
 Rib-0.048
 H-0.042
 Bub-0.038
 Bun-0.038
Token Mom
Token ID11254
Feature activation+7.46e-02

Pos logit contributions
 Ho+0.032
 Rib+0.032
 H+0.028
 Bub+0.025
 Bun+0.025
Neg logit contributions
 elevator-0.032
oos-0.032
eks-0.031
he-0.031
cases-0.031
Tokenmy
Token ID1820
Feature activation-3.37e-02

Pos logit contributions
 elevator+0.095
cases+0.095
he+0.094
ays+0.093
oos+0.093
Neg logit contributions
 Ho-0.149
 Rib-0.147
 H-0.124
 Butter-0.124
 Bub-0.123
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
eks+0.027
agged+0.026
oos+0.026
ases+0.025
ays+0.025
Neg logit contributions
 Ho-0.023
 Rib-0.023
 H-0.021
 Bun-0.019
 Tw-0.019
Token
Token ID198
Feature activation-3.55e-02

Pos logit contributions
 Ho+0.039
 Rib+0.039
 Bun+0.035
 H+0.035
 accidentally+0.033
Neg logit contributions
ays-0.033
he-0.031
irens-0.030
 elevator-0.030
oos-0.030
Token
Token ID198
Feature activation-3.49e-02

Pos logit contributions
 Rib+0.054
 Ho+0.053
 H+0.044
 Butter+0.042
 accidentally+0.041
Neg logit contributions
he-0.062
ases-0.059
eks-0.058
ays-0.058
 elevator-0.057
Token"
Token ID1
Feature activation+3.86e-02

Pos logit contributions
 Ho+0.060
 Rib+0.059
 H+0.053
 Bub+0.049
 Bun+0.049
Neg logit contributions
eks-0.054
oos-0.054
ases-0.053
 elevator-0.053
cases-0.053
TokenH
Token ID39
Feature activation-3.21e-02

Pos logit contributions
eks+0.063
oos+0.063
ays+0.061
 elevator+0.061
cases+0.061
Neg logit contributions
 Ho-0.065
 Rib-0.063
 H-0.057
 Bub-0.052
 Bun-0.052
Tokenoor
Token ID2675
Feature activation+1.63e-01

Pos logit contributions
 Ho+0.052
 Rib+0.052
 H+0.048
onna+0.043
 Fro+0.043
Neg logit contributions
eks-0.050
 elevator-0.050
cases-0.050
roads-0.048
ags-0.048
Tokenay
Token ID323
Feature activation+6.59e-02

Pos logit contributions
eks+0.177
led+0.170
oos+0.167
cks+0.165
ps+0.160
Neg logit contributions
 Ho-0.356
 Rib-0.336
 H-0.335
 Lucky-0.309
 Bun-0.307
Token!
Token ID0
Feature activation+2.61e-02

Pos logit contributions
roads+0.116
agged+0.115
cases+0.113
ags+0.112
ays+0.111
Neg logit contributions
 Ho-0.103
 Rib-0.100
 H-0.090
 Bun-0.079
 Stri-0.079
Token We
Token ID775
Feature activation+1.82e-02

Pos logit contributions
ays+0.040
ases+0.037
oos+0.037
 elevator+0.037
cases+0.035
Neg logit contributions
 Ho-0.044
 Rib-0.042
 Bun-0.038
 H-0.038
 accidentally-0.037
Token did
Token ID750
Feature activation-3.99e-02

Pos logit contributions
oos+0.032
ays+0.032
agged+0.031
cases+0.030
ags+0.030
Neg logit contributions
 Ho-0.029
 Rib-0.028
 H-0.026
 accidentally-0.025
 Bub-0.025
Token it
Token ID340
Feature activation+4.90e-03

Pos logit contributions
 Ho+0.063
 Rib+0.063
 H+0.053
 Bub+0.051
 Bun+0.049
Neg logit contributions
eks-0.067
 elevator-0.066
oos-0.064
 tickets-0.063
cases-0.063
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
 Ho+0.108
 Rib+0.106
 H+0.093
 Bub+0.085
 Lucky+0.085
Neg logit contributions
eks-0.114
oos-0.111
agged-0.111
ases-0.106
 elevator-0.106
Token
Token ID198
Feature activation-2.96e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.024
 Bun+0.024
 accidentally+0.023
Neg logit contributions
ays-0.017
oos-0.017
ases-0.016
cases-0.016
 tickets-0.016
Token
Token ID198
Feature activation-2.90e-02

Pos logit contributions
 Rib+0.044
 Ho+0.044
 H+0.036
 Butter+0.034
 Bub+0.033
Neg logit contributions
he-0.053
ases-0.050
oos-0.050
ays-0.050
eks-0.049
Token"
Token ID1
Feature activation+4.09e-02

Pos logit contributions
 Ho+0.045
 Rib+0.044
 H+0.039
 Bub+0.035
 Bun+0.035
Neg logit contributions
eks-0.052
oos-0.052
ays-0.050
 elevator-0.050
agged-0.050
TokenH
Token ID39
Feature activation-2.77e-02

Pos logit contributions
eks+0.068
oos+0.068
 elevator+0.066
ases+0.066
ays+0.066
Neg logit contributions
 Ho-0.067
 Rib-0.066
 H-0.059
 Bub-0.054
 Bun-0.054
Tokenoor
Token ID2675
Feature activation+1.62e-01

Pos logit contributions
 Ho+0.054
 Rib+0.052
 H+0.049
 Bub+0.045
 Stri+0.044
Neg logit contributions
eks-0.036
cases-0.036
 elevator-0.036
led-0.036
ays-0.035
Tokenay
Token ID323
Feature activation+6.67e-02

Pos logit contributions
eks+0.166
oos+0.155
cks+0.154
ps+0.154
led+0.153
Neg logit contributions
 Ho-0.362
 Rib-0.341
 H-0.341
 Bun-0.314
 Lucky-0.314
Token,
Token ID11
Feature activation-1.00e-02

Pos logit contributions
roads+0.110
agged+0.110
cases+0.109
ays+0.107
ags+0.106
Neg logit contributions
 Ho-0.112
 Rib-0.108
 H-0.099
 Stri-0.089
 Bun-0.089
Token we
Token ID356
Feature activation+1.49e-02

Pos logit contributions
 Ho+0.016
 Rib+0.016
 H+0.014
 Bun+0.013
 accidentally+0.013
Neg logit contributions
 elevator-0.016
eks-0.016
cases-0.016
oos-0.016
ases-0.015
Token found
Token ID1043
Feature activation+6.79e-03

Pos logit contributions
ays+0.024
oos+0.023
agged+0.023
irens+0.022
cases+0.022
Neg logit contributions
 Ho-0.027
 Rib-0.025
 H-0.024
 accidentally-0.023
 Bub-0.023
Token the
Token ID262
Feature activation-1.69e-02

Pos logit contributions
eks+0.010
oos+0.010
ays+0.010
 elevator+0.010
ases+0.010
Neg logit contributions
 Ho-0.012
 Rib-0.012
 H-0.011
 Bub-0.010
 Bun-0.010
Token!
Token ID0
Feature activation+2.90e-02

Pos logit contributions
 Ho+0.167
 Rib+0.165
 H+0.144
 Bub+0.137
 Butter+0.136
Neg logit contributions
oos-0.110
he-0.108
eks-0.106
ases-0.106
cases-0.105
Token
Token ID198
Feature activation-2.70e-02

Pos logit contributions
he+0.043
oos+0.042
agged+0.042
hed+0.041
ays+0.041
Neg logit contributions
 Rib-0.048
 Ho-0.048
 H-0.041
please-0.038
 Stri-0.038
Token
Token ID198
Feature activation-2.72e-02

Pos logit contributions
 Ho+0.041
 Rib+0.041
 H+0.035
 Butter+0.032
 fle+0.031
Neg logit contributions
he-0.050
oos-0.047
eks-0.046
agged-0.045
hed-0.045
Token"
Token ID1
Feature activation+3.96e-02

Pos logit contributions
 Ho+0.044
 Rib+0.043
 H+0.038
 Bub+0.034
 Butter+0.034
Neg logit contributions
oos-0.047
eks-0.047
he-0.045
ases-0.045
cases-0.045
TokenH
Token ID39
Feature activation-2.84e-02

Pos logit contributions
he+0.055
hed+0.054
hing+0.050
ited+0.050
oos+0.049
Neg logit contributions
 Ho-0.078
 Rib-0.072
 H-0.069
 Bub-0.065
 Fro-0.064
Tokenoor
Token ID2675
Feature activation+1.61e-01

Pos logit contributions
 Ho+0.055
 Rib+0.055
 H+0.051
 Bub+0.048
 Bun+0.047
Neg logit contributions
eks-0.039
cases-0.038
 elevator-0.037
ays-0.036
oos-0.036
Tokenay
Token ID323
Feature activation+6.59e-02

Pos logit contributions
eks+0.142
ases+0.124
oos+0.122
cks+0.121
 elevator+0.120
Neg logit contributions
 Ho-0.396
 Rib-0.385
 H-0.375
 Bun-0.357
 Lucky-0.347
Token!"
Token ID2474
Feature activation+1.76e-02

Pos logit contributions
ays+0.096
cases+0.095
oos+0.095
eks+0.094
agged+0.093
Neg logit contributions
 Ho-0.121
 Rib-0.119
 H-0.109
 Bun-0.101
 Bub-0.100
Token shouted
Token ID17293
Feature activation+2.92e-02

Pos logit contributions
led+0.028
eks+0.028
oos+0.027
cases+0.027
he+0.027
Neg logit contributions
 Rib-0.029
 Ho-0.029
 H-0.025
 Butter-0.023
 Stri-0.022
Token Ted
Token ID11396
Feature activation-1.01e-02

Pos logit contributions
oos+0.049
led+0.048
 elevator+0.046
hed+0.046
ued+0.045
Neg logit contributions
 Rib-0.044
 Ho-0.044
 H-0.038
 Stri-0.035
 Butter-0.034
Token as
Token ID355
Feature activation-2.72e-02

Pos logit contributions
 Ho+0.021
 Rib+0.020
 H+0.018
 Butter+0.018
 Bub+0.017
Neg logit contributions
cases-0.011
hed-0.011
led-0.011
he-0.011
oos-0.011
TokenAlice
Token ID44484
Feature activation+7.25e-03

Pos logit contributions
 Ho+0.038
 Rib+0.038
 H+0.034
 Bun+0.032
 Tw+0.031
Neg logit contributions
oos-0.038
eks-0.037
ays-0.037
ases-0.037
 elevator-0.036
Token said
Token ID531
Feature activation-2.20e-02

Pos logit contributions
oos+0.011
eks+0.011
cases+0.011
led+0.010
hed+0.010
Neg logit contributions
 Ho-0.013
 Rib-0.013
 H-0.011
 Bub-0.011
 Butter-0.011
Token,
Token ID11
Feature activation-9.81e-03

Pos logit contributions
 Ho+0.042
 Rib+0.041
 H+0.037
 Bub+0.035
 Bun+0.035
Neg logit contributions
eks-0.031
oos-0.031
ays-0.030
ases-0.030
 elevator-0.030
Token "
Token ID366
Feature activation-1.41e-03

Pos logit contributions
 Ho+0.015
 Rib+0.014
 H+0.012
 Bub+0.011
 Fro+0.011
Neg logit contributions
cases-0.017
 elevator-0.016
he-0.016
hed-0.016
oos-0.016
TokenH
Token ID39
Feature activation-2.75e-02

Pos logit contributions
 Ho+0.003
 Rib+0.003
 H+0.002
 Bub+0.002
 Fro+0.002
Neg logit contributions
he-0.002
hed-0.002
oos-0.002
agged-0.002
ases-0.002
Tokenoor
Token ID2675
Feature activation+1.60e-01

Pos logit contributions
 Rib+0.055
 Ho+0.054
 H+0.053
 Bub+0.048
 Bun+0.047
Neg logit contributions
eks-0.033
led-0.031
 elevator-0.030
ays-0.030
oos-0.030
Tokenay
Token ID323
Feature activation+6.48e-02

Pos logit contributions
eks+0.139
ases+0.121
cks+0.121
oos+0.117
 elevator+0.114
Neg logit contributions
 Ho-0.393
 Rib-0.384
 H-0.377
 Bun-0.355
 Lucky-0.345
Token!
Token ID0
Feature activation+2.96e-02

Pos logit contributions
eks+0.097
oos+0.096
ays+0.096
agged+0.095
cases+0.094
Neg logit contributions
 Ho-0.115
 Rib-0.113
 H-0.105
 Bun-0.096
 Bub-0.094
Token Let
Token ID3914
Feature activation-3.41e-02

Pos logit contributions
ays+0.037
cases+0.036
 elevator+0.035
ases+0.035
he+0.034
Neg logit contributions
 Ho-0.054
 Rib-0.051
 accidentally-0.048
 Fro-0.045
 H-0.044
Token's
Token ID338
Feature activation-5.02e-02

Pos logit contributions
 Ho+0.055
 Rib+0.054
 H+0.048
 Bun+0.045
 Bub+0.044
Neg logit contributions
eks-0.057
oos-0.057
ases-0.056
ays-0.056
agged-0.056
Token throw
Token ID3714
Feature activation+2.29e-03

Pos logit contributions
 Ho+0.104
 Rib+0.102
 H+0.093
 Bub+0.087
 Bun+0.086
Neg logit contributions
eks-0.062
oos-0.061
 elevator-0.060
ases-0.059
cases-0.058
TokenWe
Token ID1135
Feature activation+2.74e-02

Pos logit contributions
 Ho+0.009
 Rib+0.008
 H+0.007
 Fro+0.007
 Bub+0.007
Neg logit contributions
hed-0.005
he-0.005
ases-0.005
oos-0.005
agged-0.005
Token did
Token ID750
Feature activation-4.40e-02

Pos logit contributions
cases+0.045
oos+0.045
ays+0.044
agged+0.044
 elevator+0.042
Neg logit contributions
 Ho-0.046
 Rib-0.043
 H-0.041
 accidentally-0.039
 Bub-0.038
Token it
Token ID340
Feature activation+2.44e-03

Pos logit contributions
 Ho+0.083
 Rib+0.082
 H+0.071
 Butter+0.067
 Bub+0.066
Neg logit contributions
 elevator-0.061
eks-0.061
oos-0.060
cases-0.058
ases-0.058
Token!
Token ID0
Feature activation+2.64e-02

Pos logit contributions
eks+0.003
oos+0.003
ays+0.003
 elevator+0.003
cases+0.003
Neg logit contributions
 Ho-0.005
 Rib-0.005
 H-0.004
 Bub-0.004
 Bun-0.004
Token H
Token ID367
Feature activation-6.31e-02

Pos logit contributions
ays+0.032
ases+0.031
hed+0.028
oos+0.027
ay+0.027
Neg logit contributions
 Ho-0.051
 Rib-0.048
 accidentally-0.045
onna-0.044
 Fro-0.044
Tokenoor
Token ID2675
Feature activation+1.60e-01

Pos logit contributions
 Ho+0.131
 Rib+0.130
 H+0.119
 Bun+0.112
 Bub+0.111
Neg logit contributions
eks-0.078
 elevator-0.076
oos-0.074
cases-0.073
agged-0.072
Tokenay
Token ID323
Feature activation+6.27e-02

Pos logit contributions
eks+0.118
oos+0.104
ases+0.103
 elevator+0.101
cases+0.095
Neg logit contributions
 Ho-0.411
 Rib-0.404
 H-0.389
 Bun-0.370
 Bub-0.361
Token!"
Token ID2474
Feature activation+2.52e-02

Pos logit contributions
eks+0.089
oos+0.088
ays+0.087
 elevator+0.087
cases+0.086
Neg logit contributions
 Ho-0.116
 Rib-0.115
 H-0.106
 Bun-0.098
 Bub-0.097
Token he
Token ID339
Feature activation-9.08e-03

Pos logit contributions
hed+0.038
he+0.035
cases+0.035
ays+0.034
led+0.034
Neg logit contributions
 Rib-0.035
onna-0.035
please-0.032
 Ho-0.032
Acc-0.030
Token said
Token ID531
Feature activation-2.76e-02

Pos logit contributions
 Ho+0.018
 Rib+0.017
 H+0.016
 Butter+0.016
 Tooth+0.015
Neg logit contributions
led-0.011
cases-0.011
hed-0.010
eks-0.010
 tickets-0.010
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 Ho+0.056
 Rib+0.054
 H+0.049
 Butter+0.046
 Stri+0.046
Neg logit contributions
cases-0.034
oos-0.034
he-0.033
led-0.033
 elevator-0.033
TokenElsa
Token ID49050
Feature activation-9.25e-02

Pos logit contributions
 Ho+0.004
 Rib+0.004
 H+0.004
 Bub+0.003
 Butter+0.003
Neg logit contributions
he-0.003
eks-0.003
oos-0.003
ases-0.003
roads-0.003
Token smiled
Token ID13541
Feature activation+3.03e-03

Pos logit contributions
 Ho+0.151
 Rib+0.147
 H+0.132
 Bub+0.121
 Bun+0.120
Neg logit contributions
oos-0.153
eks-0.153
ays-0.150
 elevator-0.149
cases-0.149
Token.
Token ID13
Feature activation-4.41e-03

Pos logit contributions
oos+0.004
agged+0.003
ays+0.003
led+0.003
cases+0.003
Neg logit contributions
 Ho-0.006
 Rib-0.006
 H-0.006
 Bub-0.005
 Stri-0.005
Token "
Token ID366
Feature activation+1.25e-02

Pos logit contributions
 Rib+0.009
 Ho+0.009
 accidentally+0.009
please+0.008
 Bub+0.008
Neg logit contributions
ays-0.004
 elevator-0.003
he-0.003
oos-0.003
 downtown-0.003
TokenH
Token ID39
Feature activation-2.74e-02

Pos logit contributions
he+0.015
hed+0.014
agged+0.013
ited+0.013
hing+0.013
Neg logit contributions
 Ho-0.027
 Rib-0.024
 Bub-0.023
 Fro-0.023
 accidentally-0.023
Tokenoor
Token ID2675
Feature activation+1.58e-01

Pos logit contributions
 Ho+0.048
 Rib+0.047
 H+0.043
 Bub+0.039
 Bun+0.039
Neg logit contributions
eks-0.043
oos-0.042
cases-0.042
 elevator-0.042
ays-0.041
Tokenay
Token ID323
Feature activation+7.26e-02

Pos logit contributions
eks+0.101
oos+0.093
ases+0.089
 elevator+0.088
cases+0.085
Neg logit contributions
 Ho-0.424
 Rib-0.416
 H-0.397
 Bun-0.376
 Bub-0.370
Token,
Token ID11
Feature activation-8.68e-03

Pos logit contributions
oos+0.101
eks+0.101
ays+0.100
cases+0.100
agged+0.098
Neg logit contributions
 Ho-0.138
 Rib-0.135
 H-0.125
 Bub-0.115
 Bun-0.114
Token we
Token ID356
Feature activation+1.04e-02

Pos logit contributions
 Rib+0.014
 Ho+0.013
 H+0.012
 Bub+0.011
 accidentally+0.011
Neg logit contributions
 elevator-0.014
he-0.013
 are-0.013
eks-0.013
cases-0.012
Token took
Token ID1718
Feature activation+1.15e-02

Pos logit contributions
oos+0.014
ays+0.014
cases+0.014
eks+0.014
agged+0.013
Neg logit contributions
 Ho-0.020
 Rib-0.020
 H-0.018
 Bub-0.017
 Bun-0.017
Token a
Token ID257
Feature activation-1.32e-02

Pos logit contributions
oos+0.016
eks+0.016
ays+0.016
cases+0.016
 elevator+0.016
Neg logit contributions
 Ho-0.022
 Rib-0.021
 H-0.019
 Bub-0.018
 Bun-0.018
Token flew
Token ID13112
Feature activation-2.66e-02

Pos logit contributions
led+0.017
eks+0.016
 elevator+0.015
cases+0.015
oos+0.015
Neg logit contributions
 Ho-0.020
 Rib-0.020
 H-0.018
Ros-0.016
 Tw-0.016
Token away
Token ID1497
Feature activation+3.50e-02

Pos logit contributions
 Ho+0.066
 Rib+0.065
 H+0.061
 accidentally+0.057
 Butter+0.057
Neg logit contributions
oos-0.021
eks-0.021
agged-0.020
led-0.020
out-0.020
Token.
Token ID13
Feature activation-7.46e-03

Pos logit contributions
oos+0.052
eks+0.052
cases+0.050
ays+0.050
 elevator+0.050
Neg logit contributions
 Ho-0.063
 Rib-0.062
 H-0.056
 Bub-0.052
 Bun-0.051
Token "
Token ID366
Feature activation+6.76e-03

Pos logit contributions
 Ho+0.014
 Rib+0.013
Ros+0.012
 needle+0.012
 accidentally+0.012
Neg logit contributions
he-0.008
hed-0.008
cases-0.007
oos-0.007
ays-0.007
TokenH
Token ID39
Feature activation-2.73e-02

Pos logit contributions
he+0.010
eks+0.009
hed+0.009
oos+0.009
agged+0.009
Neg logit contributions
 Ho-0.013
 Rib-0.012
 H-0.011
 Bub-0.011
onna-0.010
Tokenoor
Token ID2675
Feature activation+1.57e-01

Pos logit contributions
 Rib+0.054
 Ho+0.053
 H+0.050
 Bub+0.046
 Butter+0.045
Neg logit contributions
cases-0.036
eks-0.035
ays-0.035
 elevator-0.035
oos-0.034
Tokenay
Token ID323
Feature activation+6.58e-02

Pos logit contributions
eks+0.116
oos+0.106
ases+0.105
 elevator+0.102
cases+0.098
Neg logit contributions
 Ho-0.409
 Rib-0.400
 H-0.384
 Bun-0.365
 Bub-0.358
Token!"
Token ID2474
Feature activation+2.67e-02

Pos logit contributions
ays+0.093
oos+0.092
cases+0.091
eks+0.090
 elevator+0.089
Neg logit contributions
 Ho-0.124
 Rib-0.122
 H-0.112
 Bun-0.104
 Bub-0.103
Token Jane
Token ID12091
Feature activation+2.35e-02

Pos logit contributions
hed+0.039
he+0.038
cases+0.038
 elevator+0.038
led+0.037
Neg logit contributions
 Rib-0.042
 Ho-0.041
 H-0.035
onna-0.035
Ros-0.035
Token shouted
Token ID17293
Feature activation+2.67e-02

Pos logit contributions
led+0.030
hed+0.030
he+0.029
eks+0.027
ered+0.026
Neg logit contributions
 Ho-0.045
 Rib-0.043
 H-0.040
 Butter-0.038
 Bub-0.038
Token with
Token ID351
Feature activation+2.75e-02

Pos logit contributions
oos+0.035
cases+0.034
eks+0.034
 elevator+0.033
he+0.033
Neg logit contributions
 Ho-0.052
 Rib-0.051
 H-0.046
 Bub-0.043
 Stri-0.043
Token.
Token ID13
Feature activation-2.16e-02

Pos logit contributions
ases+0.017
oos+0.017
 elevator+0.017
ays+0.017
cases+0.016
Neg logit contributions
 Ho-0.040
 Rib-0.040
 H-0.036
 Butter-0.035
 Bub-0.035
Token They
Token ID1119
Feature activation+3.26e-02

Pos logit contributions
 Ho+0.042
 Rib+0.041
 H+0.036
 Bun+0.035
 Bub+0.034
Neg logit contributions
oos-0.029
agged-0.029
ases-0.029
ays-0.029
 elevator-0.028
Token say
Token ID910
Feature activation-2.62e-02

Pos logit contributions
oos+0.045
ays+0.044
eks+0.044
cases+0.043
agged+0.043
Neg logit contributions
 Ho-0.064
 Rib-0.062
 H-0.057
 Bub-0.053
 Bun-0.052
Token "
Token ID366
Feature activation-9.90e-03

Pos logit contributions
 Ho+0.038
 Rib+0.037
 H+0.032
 Bun+0.031
 Butter+0.030
Neg logit contributions
 elevator-0.044
 tickets-0.044
agged-0.043
ases-0.043
oos-0.042
TokenH
Token ID39
Feature activation-3.93e-02

Pos logit contributions
 Ho+0.019
 Rib+0.017
 H+0.016
 Bub+0.015
 Po+0.015
Neg logit contributions
he-0.015
ases-0.015
oos-0.015
hed-0.014
eks-0.014
Tokenoor
Token ID2675
Feature activation+1.56e-01

Pos logit contributions
 Rib+0.081
 Ho+0.079
 H+0.077
 Bub+0.071
onna+0.070
Neg logit contributions
eks-0.045
 elevator-0.043
cases-0.043
led-0.042
roads-0.041
Tokenay
Token ID323
Feature activation+6.16e-02

Pos logit contributions
eks+0.165
cks+0.146
led+0.141
ps+0.140
oos+0.138
Neg logit contributions
 Ho-0.346
 Rib-0.337
 H-0.332
 Lucky-0.308
 Bun-0.303
Token!
Token ID0
Feature activation+2.10e-02

Pos logit contributions
eks+0.103
roads+0.101
cases+0.100
agged+0.100
oos+0.099
Neg logit contributions
 Ho-0.100
 Rib-0.100
 H-0.092
 Stri-0.081
 Bun-0.081
Token We
Token ID775
Feature activation+1.32e-02

Pos logit contributions
ays+0.028
ases+0.028
oos+0.025
 elevator+0.024
hed+0.024
Neg logit contributions
 Ho-0.040
 Rib-0.037
 Bun-0.034
 accidentally-0.034
 H-0.034
Token are
Token ID389
Feature activation+4.64e-02

Pos logit contributions
ays+0.021
oos+0.021
cases+0.021
agged+0.020
irens+0.020
Neg logit contributions
 Ho-0.023
 Rib-0.022
 H-0.020
 Bub-0.019
 accidentally-0.019
Token the
Token ID262
Feature activation-1.30e-02

Pos logit contributions
eks+0.066
 elevator+0.065
ases+0.065
ags+0.063
agged+0.062
Neg logit contributions
 Ho-0.086
 Rib-0.085
 H-0.075
 Butter-0.072
 Bun-0.071
Token special
Token ID2041
Feature activation+2.75e-02

Pos logit contributions
 Ho+0.023
 Rib+0.022
 H+0.019
 Bub+0.017
 Bun+0.017
Neg logit contributions
oos-0.028
eks-0.028
 elevator-0.028
ays-0.028
ases-0.027
Token polish
Token ID25245
Feature activation-8.28e-02

Pos logit contributions
 elevator+0.038
oos+0.038
eks+0.036
ays+0.036
ases+0.036
Neg logit contributions
 Ho-0.053
 Rib-0.052
 H-0.047
 Bub-0.043
 Bun-0.043
Token he
Token ID339
Feature activation+1.41e-02

Pos logit contributions
 Ho+0.149
 Rib+0.146
 H+0.131
 Bub+0.122
 Bun+0.121
Neg logit contributions
oos-0.123
eks-0.123
ays-0.120
cases-0.119
 elevator-0.119
Token couldn
Token ID3521
Feature activation-4.42e-02

Pos logit contributions
eks+0.025
oos+0.025
cases+0.024
 elevator+0.024
led+0.024
Neg logit contributions
 Ho-0.021
 Rib-0.021
 H-0.019
 Bub-0.017
 Butter-0.017
Token't
Token ID470
Feature activation-6.19e-03

Pos logit contributions
 Ho+0.072
 Rib+0.071
 H+0.064
 Bub+0.059
 Bun+0.059
Neg logit contributions
eks-0.074
oos-0.073
agged-0.072
ays-0.071
ases-0.071
Token contain
Token ID3994
Feature activation+1.52e-01

Pos logit contributions
 Ho+0.011
 Rib+0.011
 H+0.010
 Bub+0.009
 Bun+0.009
Neg logit contributions
oos-0.010
eks-0.010
ays-0.009
cases-0.009
ases-0.009
Token his
Token ID465
Feature activation+4.72e-02

Pos logit contributions
eks+0.279
oos+0.277
ays+0.276
cases+0.275
agged+0.272
Neg logit contributions
 Ho-0.222
 Rib-0.212
 H-0.190
 Bub-0.176
 Bun-0.173
Token happiness
Token ID12157
Feature activation+2.87e-02

Pos logit contributions
eks+0.068
oos+0.068
 elevator+0.065
cases+0.065
ases+0.065
Neg logit contributions
 Ho-0.088
 Rib-0.087
 H-0.079
 Bub-0.073
 Bun-0.072
Token.
Token ID13
Feature activation-2.91e-04

Pos logit contributions
cases+0.037
oos+0.037
he+0.036
eks+0.036
led+0.036
Neg logit contributions
 Ho-0.057
 Rib-0.056
 H-0.051
 Butter-0.047
 Bub-0.047
Token He
Token ID679
Feature activation+3.11e-02

Pos logit contributions
 Ho+0.001
 Rib+0.001
onna+0.000
 accidentally+0.000
please+0.000
Neg logit contributions
ays-0.000
he-0.000
roads-0.000
oos-0.000
 elevator-0.000
Token began
Token ID2540
Feature activation-8.04e-02

Pos logit contributions
eks+0.051
oos+0.051
 elevator+0.050
cases+0.049
led+0.049
Neg logit contributions
 Ho-0.052
 Rib-0.051
 H-0.046
 Bub-0.042
 Butter-0.041
Token excited
Token ID6568
Feature activation+1.17e-01

Pos logit contributions
eks+0.027
 elevator+0.026
cases+0.026
oos+0.026
led+0.026
Neg logit contributions
 Ho-0.028
 Rib-0.027
 H-0.024
 Bun-0.022
 Bub-0.022
Token -
Token ID532
Feature activation+2.13e-02

Pos logit contributions
eks+0.185
oos+0.185
ays+0.180
 elevator+0.179
cases+0.179
Neg logit contributions
 Ho-0.202
 Rib-0.197
 H-0.177
 Bub-0.164
 Bun-0.162
Token she
Token ID673
Feature activation-3.09e-02

Pos logit contributions
 elevator+0.034
cases+0.033
oos+0.032
eks+0.032
 tickets+0.031
Neg logit contributions
 Ho-0.035
 Rib-0.035
 H-0.030
 Bub-0.028
 Butter-0.027
Token could
Token ID714
Feature activation-1.27e-01

Pos logit contributions
 Ho+0.050
 Rib+0.050
 H+0.044
 Butter+0.040
 Bub+0.040
Neg logit contributions
eks-0.052
oos-0.051
 elevator-0.051
cases-0.050
led-0.049
Token hardly
Token ID8941
Feature activation+2.30e-02

Pos logit contributions
 Ho+0.192
 Rib+0.187
 H+0.167
 accidentally+0.158
 Bun+0.157
Neg logit contributions
ays-0.226
agged-0.225
oos-0.224
ases-0.215
led-0.215
Token contain
Token ID3994
Feature activation+1.51e-01

Pos logit contributions
eks+0.022
he+0.021
oos+0.021
 elevator+0.021
cases+0.021
Neg logit contributions
 Ho-0.054
 Rib-0.053
 H-0.049
 Bun-0.046
 Bub-0.045
Token herself
Token ID5223
Feature activation+1.81e-04

Pos logit contributions
cases+0.287
ays+0.286
eks+0.282
oos+0.282
agged+0.279
Neg logit contributions
 Ho-0.210
 Rib-0.200
 H-0.182
 Bun-0.166
 Bub-0.164
Token.
Token ID13
Feature activation+6.90e-03

Pos logit contributions
eks+0.000
oos+0.000
ases+0.000
agged+0.000
ays+0.000
Neg logit contributions
 Ho-0.000
 Rib-0.000
 H-0.000
 Bun-0.000
 Bub-0.000
Token She
Token ID1375
Feature activation-5.32e-03

Pos logit contributions
he+0.009
oos+0.008
ays+0.008
 downtown+0.008
roads+0.008
Neg logit contributions
 Rib-0.013
 Ho-0.012
onna-0.011
 Stri-0.010
 accidentally-0.010
Token started
Token ID2067
Feature activation-7.43e-02

Pos logit contributions
 Ho+0.009
 Rib+0.008
 H+0.008
 Bub+0.007
 Bun+0.007
Neg logit contributions
eks-0.009
oos-0.009
 elevator-0.009
cases-0.009
ays-0.009
Token to
Token ID284
Feature activation-1.70e-02

Pos logit contributions
 Ho+0.108
 Rib+0.105
 H+0.093
 Bub+0.084
 Bun+0.083
Neg logit contributions
eks-0.136
oos-0.136
ays-0.133
cases-0.133
agged-0.132
Token the
Token ID262
Feature activation-1.83e-02

Pos logit contributions
 Rib+0.048
 Ho+0.047
 H+0.042
 Bub+0.040
 accidentally+0.039
Neg logit contributions
oos-0.046
 elevator-0.046
ays-0.046
eks-0.045
ases-0.045
Token herb
Token ID21047
Feature activation-1.01e-01

Pos logit contributions
 Rib+0.035
 Ho+0.034
 H+0.031
 Bun+0.030
 Bub+0.030
Neg logit contributions
 elevator-0.026
 are-0.024
eks-0.023
ps-0.023
oos-0.023
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
 Ho+0.189
 Rib+0.186
 H+0.169
 Bub+0.157
 Bun+0.156
Neg logit contributions
oos-0.143
eks-0.142
 elevator-0.140
ays-0.140
cases-0.139
Token It
Token ID632
Feature activation-3.83e-03

Pos logit contributions
 Rib+0.043
 Ho+0.043
 Bun+0.038
 accidentally+0.037
 Bub+0.037
Neg logit contributions
he-0.026
ays-0.025
ases-0.023
 elevator-0.022
otion-0.022
Token is
Token ID318
Feature activation+1.33e-02

Pos logit contributions
 Ho+0.008
 Rib+0.008
 H+0.008
 Bub+0.007
 Butter+0.007
Neg logit contributions
oos-0.004
eks-0.004
cases-0.004
agged-0.004
ays-0.004
Token lav
Token ID21606
Feature activation-1.96e-01

Pos logit contributions
ps+0.017
 elevator+0.016
ags+0.015
cks+0.015
led+0.015
Neg logit contributions
 Rib-0.026
 Ho-0.025
 H-0.024
 Bun-0.023
 Bub-0.022
Tokenender
Token ID2194
Feature activation-1.84e-01

Pos logit contributions
 Ho+0.248
 Rib+0.243
 H+0.217
 Bub+0.193
 Bun+0.192
Neg logit contributions
ays-0.400
oos-0.398
eks-0.389
ases-0.384
agged-0.384
Token.
Token ID13
Feature activation-2.25e-02

Pos logit contributions
 Ho+0.319
 Rib+0.309
 H+0.275
 Butter+0.256
 Bub+0.254
Neg logit contributions
eks-0.296
oos-0.287
agged-0.282
cases-0.280
ases-0.278
Token "
Token ID366
Feature activation-5.65e-03

Pos logit contributions
 Ho+0.044
 Rib+0.044
 Bun+0.040
 accidentally+0.039
 Bub+0.039
Neg logit contributions
ays-0.025
he-0.024
ases-0.022
otion-0.022
 are-0.021
TokenThat
Token ID2504
Feature activation+6.33e-02

Pos logit contributions
 Ho+0.010
 Rib+0.009
 H+0.008
 Bun+0.008
 Bub+0.008
Neg logit contributions
ases-0.009
eks-0.009
ays-0.009
he-0.009
oos-0.008
Token is
Token ID318
Feature activation+1.37e-02

Pos logit contributions
oos+0.063
 elevator+0.063
ays+0.063
eks+0.063
ases+0.059
Neg logit contributions
 Ho-0.143
 Rib-0.141
 H-0.130
 Bub-0.124
 Bun-0.124
Token source
Token ID2723
Feature activation-2.18e-02

Pos logit contributions
 Rib+0.034
 Ho+0.034
 H+0.031
 Bub+0.029
 Bun+0.029
Neg logit contributions
 elevator-0.023
eks-0.021
oos-0.021
 tickets-0.020
he-0.020
Token.
Token ID13
Feature activation-1.79e-02

Pos logit contributions
 Ho+0.040
 Rib+0.039
 H+0.036
 Bun+0.034
 Lucky+0.034
Neg logit contributions
eks-0.032
oos-0.030
agged-0.030
ases-0.029
ags-0.029
Token It
Token ID632
Feature activation-2.86e-03

Pos logit contributions
 Rib+0.033
 Ho+0.032
please+0.031
 H+0.030
 Cle+0.029
Neg logit contributions
agged-0.020
ays-0.019
ags-0.018
he-0.018
oos-0.017
Token was
Token ID373
Feature activation+5.51e-03

Pos logit contributions
 Ho+0.005
 Rib+0.005
 H+0.004
 Bub+0.004
 Bun+0.004
Neg logit contributions
eks-0.005
oos-0.005
 elevator-0.005
led-0.005
cases-0.004
Token their
Token ID511
Feature activation+1.97e-02

Pos logit contributions
 elevator+0.007
ps+0.006
ags+0.006
eks+0.006
ases+0.006
Neg logit contributions
 Rib-0.011
 Ho-0.011
 H-0.010
 Bun-0.010
 Bub-0.009
Token ham
Token ID8891
Feature activation-1.85e-01

Pos logit contributions
 elevator+0.029
oos+0.028
eks+0.028
ases+0.028
ays+0.027
Neg logit contributions
 Ho-0.036
 Rib-0.036
 H-0.033
 Bun-0.031
 Bub-0.030
Tokenster
Token ID1706
Feature activation-5.39e-02

Pos logit contributions
 Ho+0.333
 Rib+0.331
 H+0.306
 Bub+0.284
 Bun+0.281
Neg logit contributions
oos-0.267
eks-0.265
ays-0.261
cases-0.260
ases-0.259
Token cage
Token ID17186
Feature activation+1.10e-02

Pos logit contributions
 Ho+0.099
 Rib+0.098
 H+0.089
 Bub+0.083
 Bun+0.081
Neg logit contributions
eks-0.078
oos-0.077
 elevator-0.075
cases-0.075
ays-0.075
Token.
Token ID13
Feature activation-1.83e-02

Pos logit contributions
eks+0.020
ases+0.019
agged+0.019
ays+0.019
oos+0.019
Neg logit contributions
 Ho-0.016
 Rib-0.015
 H-0.014
 Bun-0.013
 Lucky-0.013
Token Their
Token ID5334
Feature activation-4.07e-02

Pos logit contributions
 Rib+0.030
 Ho+0.030
please+0.030
 Bun+0.028
 H+0.028
Neg logit contributions
ays-0.023
agged-0.022
he-0.022
ases-0.021
ags-0.021
Token ham
Token ID8891
Feature activation-1.85e-01

Pos logit contributions
 Rib+0.082
 Ho+0.082
 H+0.077
 Bun+0.073
 Bub+0.072
Neg logit contributions
oos-0.050
eks-0.050
 elevator-0.049
ases-0.048
 tickets-0.047
Token ham
Token ID8891
Feature activation-1.85e-01

Pos logit contributions
 elevator+0.029
oos+0.028
eks+0.028
ases+0.028
ays+0.027
Neg logit contributions
 Ho-0.036
 Rib-0.036
 H-0.033
 Bun-0.031
 Bub-0.030
Tokenster
Token ID1706
Feature activation-5.39e-02

Pos logit contributions
 Ho+0.333
 Rib+0.331
 H+0.306
 Bub+0.284
 Bun+0.281
Neg logit contributions
oos-0.267
eks-0.265
ays-0.261
cases-0.260
ases-0.259
Token cage
Token ID17186
Feature activation+1.10e-02

Pos logit contributions
 Ho+0.099
 Rib+0.098
 H+0.089
 Bub+0.083
 Bun+0.081
Neg logit contributions
eks-0.078
oos-0.077
 elevator-0.075
cases-0.075
ays-0.075
Token.
Token ID13
Feature activation-1.83e-02

Pos logit contributions
eks+0.020
ases+0.019
agged+0.019
ays+0.019
oos+0.019
Neg logit contributions
 Ho-0.016
 Rib-0.015
 H-0.014
 Bun-0.013
 Lucky-0.013
Token Their
Token ID5334
Feature activation-4.07e-02

Pos logit contributions
 Rib+0.030
 Ho+0.030
please+0.030
 Bun+0.028
 H+0.028
Neg logit contributions
ays-0.023
agged-0.022
he-0.022
ases-0.021
ags-0.021
Token ham
Token ID8891
Feature activation-1.85e-01

Pos logit contributions
 Rib+0.082
 Ho+0.082
 H+0.077
 Bun+0.073
 Bub+0.072
Neg logit contributions
oos-0.050
eks-0.050
 elevator-0.049
ases-0.048
 tickets-0.047
Tokenster
Token ID1706
Feature activation-5.41e-02

Pos logit contributions
 Ho+0.322
 Rib+0.317
 H+0.292
 Bub+0.267
 Bun+0.267
Neg logit contributions
eks-0.282
oos-0.281
ays-0.275
ases-0.273
cases-0.272
Token,
Token ID11
Feature activation-1.33e-02

Pos logit contributions
 Ho+0.088
 Rib+0.087
 H+0.080
 Bub+0.071
 Bun+0.071
Neg logit contributions
eks-0.089
oos-0.087
cases-0.087
 elevator-0.086
led-0.086
Token Fl
Token ID1610
Feature activation-9.69e-02

Pos logit contributions
 Rib+0.022
 Ho+0.022
 H+0.020
 Bub+0.018
 Bun+0.018
Neg logit contributions
eks-0.021
 elevator-0.020
oos-0.020
ases-0.020
ays-0.020
Tokenuffy
Token ID15352
Feature activation-4.76e-02

Pos logit contributions
 Ho+0.166
 Rib+0.163
 H+0.147
 Bub+0.137
 Bun+0.136
Neg logit contributions
oos-0.154
eks-0.153
ays-0.150
ases-0.149
 elevator-0.147
Token,
Token ID11
Feature activation-1.26e-02

Pos logit contributions
 Rib+0.091
 Ho+0.091
 H+0.084
 Bub+0.078
 Bun+0.076
Neg logit contributions
oos-0.062
eks-0.060
 elevator-0.060
cases-0.060
led-0.059
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
 Ho+0.170
 Rib+0.166
 H+0.151
 Bub+0.140
 Bun+0.139
Neg logit contributions
oos-0.136
eks-0.136
ays-0.132
 elevator-0.131
cases-0.131
Token He
Token ID679
Feature activation+1.52e-02

Pos logit contributions
 Ho+0.049
 Rib+0.049
 accidentally+0.047
Ros+0.047
 Bun+0.046
Neg logit contributions
ags-0.021
agged-0.021
ases-0.020
he-0.020
ays-0.020
Token likes
Token ID7832
Feature activation+2.31e-02

Pos logit contributions
eks+0.017
oos+0.017
ays+0.016
cases+0.016
 elevator+0.016
Neg logit contributions
 Ho-0.033
 Rib-0.033
 H-0.030
 Bub-0.028
 Bun-0.028
Token cheese
Token ID9891
Feature activation-1.02e-01

Pos logit contributions
ases+0.030
 elevator+0.030
oos+0.029
 tickets+0.028
out+0.028
Neg logit contributions
 Ho-0.042
 Bun-0.042
 H-0.041
 Rib-0.040
Ros-0.038
Token and
Token ID290
Feature activation-3.13e-03

Pos logit contributions
 Ho+0.199
 Rib+0.196
 H+0.184
 Bun+0.171
 Bub+0.169
Neg logit contributions
ases-0.129
oos-0.128
ays-0.125
eks-0.125
he-0.125
Token ham
Token ID8891
Feature activation-1.85e-01

Pos logit contributions
 Ho+0.006
 H+0.006
 Rib+0.006
 Bun+0.005
 Bub+0.005
Neg logit contributions
ases-0.004
 elevator-0.004
eks-0.004
oos-0.004
 are-0.004
Token and
Token ID290
Feature activation-1.98e-03

Pos logit contributions
 Ho+0.360
 Rib+0.353
 H+0.335
 Bun+0.318
 Bub+0.312
Neg logit contributions
ases-0.239
ays-0.238
oos-0.237
eks-0.233
agged-0.230
Token lettuce
Token ID39406
Feature activation-9.98e-02

Pos logit contributions
 Ho+0.003
 Rib+0.003
 H+0.003
 Bun+0.003
 Bub+0.003
Neg logit contributions
ases-0.003
 elevator-0.003
eks-0.003
oos-0.003
led-0.003
Token too
Token ID1165
Feature activation-3.70e-02

Pos logit contributions
 Ho+0.190
 Rib+0.187
 H+0.172
 Bun+0.160
 Bub+0.160
Neg logit contributions
oos-0.134
eks-0.134
ays-0.132
ases-0.132
cases-0.131
Token.
Token ID13
Feature activation-2.22e-02

Pos logit contributions
 Ho+0.051
 Rib+0.048
 H+0.044
 accidentally+0.039
 Lucky+0.038
Neg logit contributions
eks-0.074
oos-0.072
ays-0.071
agged-0.068
ases-0.068
Token He
Token ID679
Feature activation+1.63e-02

Pos logit contributions
 Rib+0.044
 Ho+0.044
 accidentally+0.043
Ros+0.043
 Bun+0.042
Neg logit contributions
ays-0.020
ases-0.019
ags-0.019
agged-0.019
 are-0.018
Token because
Token ID780
Feature activation+4.25e-02

Pos logit contributions
oos+0.030
eks+0.030
ays+0.029
 elevator+0.029
cases+0.029
Neg logit contributions
 Ho-0.037
 Rib-0.036
 H-0.032
 Bub-0.030
 Bun-0.030
Token I
Token ID314
Feature activation-3.74e-02

Pos logit contributions
 elevator+0.068
ays+0.063
ases+0.063
cases+0.062
oos+0.062
Neg logit contributions
 Ho-0.073
 Rib-0.072
 H-0.062
 Bun-0.059
 Fro-0.059
Token like
Token ID588
Feature activation-5.46e-03

Pos logit contributions
 Ho+0.066
 Rib+0.065
 H+0.059
 Bub+0.054
 Bun+0.054
Neg logit contributions
oos-0.057
eks-0.057
ays-0.055
 elevator-0.055
cases-0.055
Token cheese
Token ID9891
Feature activation-1.01e-01

Pos logit contributions
 Ho+0.010
 Rib+0.010
 H+0.009
 Bun+0.009
Ros+0.009
Neg logit contributions
 elevator-0.007
ases-0.007
 tickets-0.007
oos-0.007
ays-0.007
Token and
Token ID290
Feature activation+4.98e-04

Pos logit contributions
 Ho+0.183
 Rib+0.179
 H+0.161
 Bub+0.150
 Bun+0.149
Neg logit contributions
eks-0.151
oos-0.150
ays-0.146
 elevator-0.145
cases-0.145
Token ham
Token ID8891
Feature activation-1.84e-01

Pos logit contributions
 elevator+0.001
ases+0.001
 bags+0.001
oos+0.001
 tickets+0.001
Neg logit contributions
 Ho-0.001
 Rib-0.001
 H-0.001
 Bun-0.001
 Bub-0.001
Token and
Token ID290
Feature activation+1.39e-03

Pos logit contributions
 Ho+0.337
 Rib+0.330
 H+0.300
 Bub+0.278
 Bun+0.277
Neg logit contributions
oos-0.269
eks-0.269
ays-0.262
ases-0.261
cases-0.260
Token yellow
Token ID7872
Feature activation+2.67e-03

Pos logit contributions
 elevator+0.002
ases+0.002
 bags+0.002
 are+0.002
eks+0.002
Neg logit contributions
 Rib-0.002
 Ho-0.002
 H-0.002
 Bun-0.002
 Bub-0.002
Token and
Token ID290
Feature activation+2.15e-03

Pos logit contributions
oos+0.004
eks+0.004
ays+0.004
 elevator+0.004
cases+0.004
Neg logit contributions
 Ho-0.005
 Rib-0.005
 H-0.004
 Bub-0.004
 Bun-0.004
Token red
Token ID2266
Feature activation+3.50e-02

Pos logit contributions
 elevator+0.003
 are+0.003
 bags+0.003
ases+0.003
eks+0.003
Neg logit contributions
 Ho-0.004
 Rib-0.003
 H-0.003
 Bun-0.003
 Bub-0.003
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
eks+0.053
oos+0.051
cases+0.051
 elevator+0.050
ays+0.050
Neg logit contributions
 Ho-0.064
 Rib-0.062
 H-0.056
 Bub-0.052
 Bun-0.051
Token herb
Token ID21047
Feature activation-1.01e-01

Pos logit contributions
 Rib+0.035
 Ho+0.034
 H+0.031
 Bun+0.030
 Bub+0.030
Neg logit contributions
 elevator-0.026
 are-0.024
eks-0.023
ps-0.023
oos-0.023
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
 Ho+0.189
 Rib+0.186
 H+0.169
 Bub+0.157
 Bun+0.156
Neg logit contributions
oos-0.143
eks-0.142
 elevator-0.140
ays-0.140
cases-0.139
Token It
Token ID632
Feature activation-3.83e-03

Pos logit contributions
 Rib+0.043
 Ho+0.043
 Bun+0.038
 accidentally+0.037
 Bub+0.037
Neg logit contributions
he-0.026
ays-0.025
ases-0.023
 elevator-0.022
otion-0.022
Token is
Token ID318
Feature activation+1.33e-02

Pos logit contributions
 Ho+0.008
 Rib+0.008
 H+0.008
 Bub+0.007
 Butter+0.007
Neg logit contributions
oos-0.004
eks-0.004
cases-0.004
agged-0.004
ays-0.004
Token lav
Token ID21606
Feature activation-1.96e-01

Pos logit contributions
ps+0.017
 elevator+0.016
ags+0.015
cks+0.015
led+0.015
Neg logit contributions
 Rib-0.026
 Ho-0.025
 H-0.024
 Bun-0.023
 Bub-0.022
Tokenender
Token ID2194
Feature activation-1.84e-01

Pos logit contributions
 Ho+0.248
 Rib+0.243
 H+0.217
 Bub+0.193
 Bun+0.192
Neg logit contributions
ays-0.400
oos-0.398
eks-0.389
ases-0.384
agged-0.384
Token.
Token ID13
Feature activation-2.25e-02

Pos logit contributions
 Ho+0.319
 Rib+0.309
 H+0.275
 Butter+0.256
 Bub+0.254
Neg logit contributions
eks-0.296
oos-0.287
agged-0.282
cases-0.280
ases-0.278
Token "
Token ID366
Feature activation-5.65e-03

Pos logit contributions
 Ho+0.044
 Rib+0.044
 Bun+0.040
 accidentally+0.039
 Bub+0.039
Neg logit contributions
ays-0.025
he-0.024
ases-0.022
otion-0.022
 are-0.021
TokenThat
Token ID2504
Feature activation+6.33e-02

Pos logit contributions
 Ho+0.010
 Rib+0.009
 H+0.008
 Bun+0.008
 Bub+0.008
Neg logit contributions
ases-0.009
eks-0.009
ays-0.009
he-0.009
oos-0.008
Token is
Token ID318
Feature activation+1.37e-02

Pos logit contributions
oos+0.063
 elevator+0.063
ays+0.063
eks+0.063
ases+0.059
Neg logit contributions
 Ho-0.143
 Rib-0.141
 H-0.130
 Bub-0.124
 Bun-0.124
Token not
Token ID407
Feature activation-9.81e-03

Pos logit contributions
ps+0.017
 elevator+0.016
eks+0.016
 are+0.016
cks+0.016
Neg logit contributions
 Rib-0.027
 Ho-0.025
 Bun-0.023
 H-0.023
 stub-0.022
Token cheeks
Token ID25839
Feature activation+4.80e-02

Pos logit contributions
oos+0.093
eks+0.093
 elevator+0.091
ays+0.090
ases+0.090
Neg logit contributions
 Ho-0.124
 Rib-0.121
 H-0.110
 Bub-0.103
 Bun-0.103
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
eks+0.090
oos+0.087
agged+0.086
cases+0.084
 elevator+0.083
Neg logit contributions
 Ho-0.071
 Rib-0.068
 H-0.060
 Tw-0.055
 Lucky-0.055
Token That
Token ID1320
Feature activation+3.06e-02

Pos logit contributions
 Ho+0.030
 Rib+0.029
 accidentally+0.026
 H+0.026
 Bun+0.026
Neg logit contributions
ays-0.024
ases-0.023
oos-0.022
 elevator-0.022
eks-0.021
Token is
Token ID318
Feature activation+1.64e-02

Pos logit contributions
eks+0.031
 elevator+0.031
oos+0.031
ays+0.031
ases+0.030
Neg logit contributions
 Ho-0.069
 Rib-0.068
 H-0.063
 Bub-0.060
 Bun-0.059
Token a
Token ID257
Feature activation-1.78e-02

Pos logit contributions
 elevator+0.019
cks+0.019
ps+0.018
 tickets+0.017
eks+0.017
Neg logit contributions
 Rib-0.033
 Ho-0.032
 Bun-0.030
 H-0.030
Ros-0.029
Token ham
Token ID8891
Feature activation-1.83e-01

Pos logit contributions
 Rib+0.035
 Ho+0.034
 H+0.033
 Stri+0.031
 Bun+0.031
Neg logit contributions
 elevator-0.021
 tickets-0.018
eks-0.018
ases-0.018
 stadium-0.018
Tokenster
Token ID1706
Feature activation-5.56e-02

Pos logit contributions
 Ho+0.320
 Rib+0.313
 H+0.303
 Bun+0.284
 Bub+0.279
Neg logit contributions
ays-0.266
ases-0.265
oos-0.257
eks-0.255
out-0.254
Token.
Token ID13
Feature activation-1.71e-02

Pos logit contributions
 Ho+0.107
 Rib+0.106
 H+0.098
 Bub+0.091
 Bun+0.091
Neg logit contributions
 elevator-0.072
ases-0.072
ays-0.072
eks-0.071
oos-0.071
Token A
Token ID317
Feature activation-3.01e-02

Pos logit contributions
 Ho+0.028
 Rib+0.027
 accidentally+0.026
 Bun+0.025
 H+0.025
Neg logit contributions
ases-0.025
ays-0.025
eks-0.023
oos-0.023
 elevator-0.022
Token rabbit
Token ID22746
Feature activation-6.44e-02

Pos logit contributions
 Rib+0.055
 H+0.055
 Ho+0.054
 Bun+0.053
 Bub+0.050
Neg logit contributions
 elevator-0.033
 tickets-0.032
 are-0.032
 men-0.030
 envelope-0.030
Token has
Token ID468
Feature activation-2.99e-02

Pos logit contributions
 Ho+0.126
 Rib+0.123
 H+0.111
 Bub+0.104
 Bun+0.103
Neg logit contributions
oos-0.088
eks-0.087
cases-0.085
ays-0.084
 elevator-0.084
Token cheese
Token ID9891
Feature activation-9.84e-02

Pos logit contributions
ays+0.047
oos+0.046
eks+0.046
ases+0.046
 elevator+0.046
Neg logit contributions
 Ho-0.063
 Rib-0.062
 H-0.057
 Bun-0.053
 Bub-0.052
Token and
Token ID290
Feature activation+2.33e-03

Pos logit contributions
 Ho+0.180
 Rib+0.176
 H+0.160
 Bub+0.148
 Bun+0.147
Neg logit contributions
eks-0.144
oos-0.144
ays-0.139
 elevator-0.139
cases-0.139
Token ol
Token ID25776
Feature activation-3.24e-02

Pos logit contributions
 elevator+0.003
eks+0.003
ases+0.003
oos+0.003
led+0.003
Neg logit contributions
 Ho-0.004
 Rib-0.004
 H-0.004
 Bun-0.004
 Bub-0.004
Tokenives
Token ID1083
Feature activation-4.18e-02

Pos logit contributions
 Ho+0.083
 Rib+0.081
 H+0.075
 Bub+0.072
 Lucky+0.071
Neg logit contributions
eks-0.025
oos-0.024
 elevator-0.024
cases-0.022
ays-0.022
Token and
Token ID290
Feature activation+3.73e-03

Pos logit contributions
 Ho+0.074
 Rib+0.072
 H+0.064
 Bub+0.060
 Lucky+0.059
Neg logit contributions
eks-0.065
oos-0.064
cases-0.063
 elevator-0.063
agged-0.062
Token ham
Token ID8891
Feature activation-1.83e-01

Pos logit contributions
 elevator+0.005
ases+0.005
eks+0.005
ps+0.005
cases+0.005
Neg logit contributions
 Ho-0.007
 Rib-0.007
 H-0.007
 Bun-0.006
 Bub-0.006
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
 Ho+0.350
 Rib+0.342
 H+0.321
 Bun+0.304
 Bub+0.298
Neg logit contributions
ays-0.247
oos-0.246
ases-0.244
eks-0.242
cases-0.237
Token They
Token ID1119
Feature activation+3.86e-02

Pos logit contributions
 Ho+0.045
 Rib+0.044
 Bun+0.042
shadow+0.042
 H+0.042
Neg logit contributions
ays-0.013
ases-0.012
oos-0.012
ags-0.010
 are-0.010
Token see
Token ID766
Feature activation+3.52e-02

Pos logit contributions
oos+0.060
ays+0.058
agged+0.058
cases+0.057
eks+0.057
Neg logit contributions
 Ho-0.070
 Rib-0.068
 H-0.060
 Bub-0.057
 accidentally-0.056
Token mom
Token ID1995
Feature activation+5.96e-02

Pos logit contributions
ays+0.047
oos+0.047
eks+0.047
 elevator+0.047
ases+0.047
Neg logit contributions
 Ho-0.067
 Rib-0.066
 H-0.061
 Bun-0.057
 Bub-0.056
Token's
Token ID338
Feature activation-4.57e-02

Pos logit contributions
oos+0.098
eks+0.096
agged+0.094
cases+0.093
 elevator+0.093
Neg logit contributions
 Ho-0.101
 Rib-0.099
 H-0.087
 Bub-0.081
 Butter-0.079
Token.
Token ID13
Feature activation-1.98e-02

Pos logit contributions
 elevator+0.003
oos+0.003
eks+0.003
ays+0.003
cases+0.003
Neg logit contributions
 Ho-0.004
 Rib-0.004
 H-0.003
 Bub-0.003
 Bun-0.003
Token It
Token ID632
Feature activation-2.46e-03

Pos logit contributions
 Ho+0.042
 Rib+0.041
 Bun+0.039
please+0.038
 accidentally+0.038
Neg logit contributions
ays-0.017
ases-0.016
ags-0.016
agged-0.016
oos-0.015
Token had
Token ID550
Feature activation-3.67e-02

Pos logit contributions
 Ho+0.005
 Rib+0.004
 H+0.004
 Bun+0.004
 Bub+0.004
Neg logit contributions
led-0.003
eks-0.003
hed-0.003
 elevator-0.003
oos-0.003
Token cheese
Token ID9891
Feature activation-1.01e-01

Pos logit contributions
 Ho+0.070
 Rib+0.068
 H+0.064
 Bun+0.060
 Bub+0.059
Neg logit contributions
eks-0.049
oos-0.049
ases-0.048
 elevator-0.048
agged-0.046
Token and
Token ID290
Feature activation-2.28e-03

Pos logit contributions
 Ho+0.182
 Rib+0.177
 H+0.158
 Bub+0.148
 Bun+0.146
Neg logit contributions
eks-0.153
oos-0.152
 elevator-0.147
cases-0.147
ays-0.146
Token ham
Token ID8891
Feature activation-1.83e-01

Pos logit contributions
 Ho+0.004
 Rib+0.004
 H+0.004
 Bun+0.004
 Bub+0.003
Neg logit contributions
 elevator-0.003
led-0.003
oos-0.003
ases-0.003
ps-0.003
Token and
Token ID290
Feature activation-8.13e-04

Pos logit contributions
 Ho+0.347
 Rib+0.341
 H+0.317
 Bun+0.296
 Bub+0.294
Neg logit contributions
oos-0.248
eks-0.246
ays-0.245
ases-0.243
cases-0.239
Token bread
Token ID8509
Feature activation-5.97e-02

Pos logit contributions
 Ho+0.001
 Rib+0.001
 H+0.001
 Bun+0.001
 Bub+0.001
Neg logit contributions
 elevator-0.001
led-0.001
ases-0.001
 are-0.001
 bags-0.001
Token.
Token ID13
Feature activation-1.99e-02

Pos logit contributions
 Ho+0.114
 Rib+0.113
 H+0.104
 Bun+0.097
 Bub+0.096
Neg logit contributions
oos-0.080
eks-0.079
ays-0.079
ases-0.079
cases-0.077
Token He
Token ID679
Feature activation+2.18e-02

Pos logit contributions
 Ho+0.039
 Rib+0.039
 Bun+0.038
please+0.037
Ros+0.036
Neg logit contributions
ays-0.020
ases-0.019
ags-0.018
agged-0.018
oos-0.016
Token also
Token ID635
Feature activation-7.67e-02

Pos logit contributions
led+0.030
eks+0.029
oos+0.028
 elevator+0.028
cases+0.027
Neg logit contributions
 Ho-0.041
 Rib-0.040
 H-0.038
 Bun-0.035
 Bub-0.034
Token and
Token ID290
Feature activation+2.93e-03

Pos logit contributions
 Ho+0.103
 Rib+0.101
 H+0.090
 Bub+0.084
 Bun+0.083
Neg logit contributions
eks-0.091
oos-0.091
 elevator-0.088
cases-0.088
ays-0.088
Token the
Token ID262
Feature activation-1.73e-02

Pos logit contributions
led+0.004
eks+0.004
 elevator+0.004
oos+0.004
cases+0.004
Neg logit contributions
 Rib-0.005
 Ho-0.005
 H-0.005
 Bun-0.005
 Bub-0.004
Token cheese
Token ID9891
Feature activation-9.95e-02

Pos logit contributions
 Ho+0.034
 Rib+0.034
 H+0.032
 Bun+0.030
 Bub+0.030
Neg logit contributions
 elevator-0.022
oos-0.022
eks-0.021
ays-0.021
ases-0.021
Token and
Token ID290
Feature activation+4.14e-03

Pos logit contributions
 Ho+0.170
 Rib+0.165
 H+0.143
 Bub+0.135
 Butter+0.133
Neg logit contributions
eks-0.162
oos-0.159
agged-0.155
 elevator-0.154
cases-0.154
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
led+0.006
eks+0.006
 elevator+0.006
oos+0.006
cases+0.005
Neg logit contributions
 Rib-0.008
 Ho-0.007
 H-0.007
 Bun-0.006
 Bub-0.006
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
 Ho+0.031
 Rib+0.031
 H+0.030
 Bun+0.028
 Bub+0.027
Neg logit contributions
 elevator-0.021
oos-0.020
eks-0.020
ases-0.019
 tickets-0.019
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
 Ho+0.349
 Rib+0.342
 H+0.324
 Bun+0.302
 Bub+0.299
Neg logit contributions
oos-0.247
ays-0.244
eks-0.243
ases-0.241
cases-0.237
Token They
Token ID1119
Feature activation+4.40e-02

Pos logit contributions
 Rib+0.036
 Ho+0.035
 H+0.032
 Bun+0.032
 accidentally+0.031
Neg logit contributions
ays-0.016
ags-0.015
agged-0.014
oos-0.014
he-0.014
Token put
Token ID1234
Feature activation-3.22e-02

Pos logit contributions
eks+0.072
oos+0.072
ays+0.070
cases+0.070
 elevator+0.070
Neg logit contributions
 Ho-0.073
 Rib-0.071
 H-0.064
 Bub-0.059
 Bun-0.058
Token them
Token ID606
Feature activation+4.22e-02

Pos logit contributions
 Ho+0.055
 Rib+0.053
 H+0.047
 Bub+0.044
 Bun+0.043
Neg logit contributions
eks-0.052
oos-0.052
cases-0.051
 elevator-0.050
ases-0.050
Token on
Token ID319
Feature activation+6.71e-04

Pos logit contributions
roads+0.074
ays+0.073
eks+0.072
 elevator+0.072
ases+0.072
Neg logit contributions
 Ho-0.068
 Rib-0.062
 H-0.054
 Bub-0.052
 Lucky-0.051
Token out
Token ID503
Feature activation+2.70e-02

Pos logit contributions
oos+0.010
eks+0.010
ays+0.010
ases+0.010
 elevator+0.010
Neg logit contributions
 Ho-0.015
 Rib-0.015
 H-0.014
 Bun-0.013
 Bub-0.013
Token some
Token ID617
Feature activation+7.25e-02

Pos logit contributions
eks+0.044
oos+0.044
cases+0.044
agged+0.044
ays+0.043
Neg logit contributions
 Ho-0.045
 Rib-0.044
 H-0.039
 Bub-0.036
 Po-0.036
Token cheese
Token ID9891
Feature activation-9.87e-02

Pos logit contributions
eks+0.101
oos+0.100
cases+0.097
ays+0.097
agged+0.096
Neg logit contributions
 Ho-0.140
 Rib-0.137
 H-0.123
 Bub-0.116
 Bun-0.114
Token and
Token ID290
Feature activation+3.89e-03

Pos logit contributions
 Ho+0.178
 Rib+0.175
 H+0.158
 Bub+0.146
 Bun+0.145
Neg logit contributions
oos-0.147
eks-0.147
ays-0.143
cases-0.142
 elevator-0.142
Token some
Token ID617
Feature activation+7.28e-02

Pos logit contributions
led+0.005
eks+0.005
oos+0.005
 elevator+0.005
cases+0.005
Neg logit contributions
 Rib-0.007
 Ho-0.007
 H-0.007
 Bun-0.006
 Fay-0.006
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
oos+0.101
eks+0.098
 elevator+0.098
led+0.098
ases+0.098
Neg logit contributions
 Ho-0.135
 Rib-0.133
 H-0.126
 Bun-0.115
 Bub-0.113
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
 Ho+0.354
 Rib+0.347
 H+0.331
 Bun+0.310
 Bub+0.303
Neg logit contributions
oos-0.240
ays-0.237
ases-0.235
eks-0.232
cases-0.230
Token She
Token ID1375
Feature activation-1.53e-02

Pos logit contributions
 Rib+0.029
 Ho+0.028
 H+0.025
 accidentally+0.024
 Bun+0.024
Neg logit contributions
ays-0.015
oos-0.014
cases-0.013
hed-0.013
he-0.013
Token put
Token ID1234
Feature activation-3.64e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.026
 Bun+0.023
 Butter+0.023
Neg logit contributions
led-0.022
eks-0.022
oos-0.021
hed-0.021
 elevator-0.021
Token them
Token ID606
Feature activation+4.01e-02

Pos logit contributions
 Ho+0.065
 Rib+0.065
 H+0.060
 Bun+0.055
 Bub+0.054
Neg logit contributions
eks-0.053
oos-0.053
ays-0.052
 elevator-0.051
ases-0.050
Token on
Token ID319
Feature activation-3.27e-03

Pos logit contributions
roads+0.066
 elevator+0.065
ases+0.065
cases+0.065
ays+0.065
Neg logit contributions
 Ho-0.069
 Rib-0.063
 H-0.054
 Bub-0.054
 Po-0.053
Token.
Token ID13
Feature activation+1.30e-03

Pos logit contributions
eks+0.055
agged+0.054
oos+0.052
hing+0.051
ags+0.051
Neg logit contributions
 Rib-0.027
 Ho-0.027
onna-0.022
 accidentally-0.022
 Po-0.021
Token It
Token ID632
Feature activation-4.89e-04

Pos logit contributions
ays+0.002
oos+0.002
 elevator+0.002
ases+0.002
eks+0.002
Neg logit contributions
 Ho-0.002
 Rib-0.002
 H-0.002
 Bun-0.002
 Bub-0.002
Token has
Token ID468
Feature activation-2.92e-02

Pos logit contributions
 Ho+0.001
 Rib+0.001
 H+0.001
 Bub+0.001
 Butter+0.001
Neg logit contributions
oos-0.001
eks-0.001
agged-0.001
ases-0.001
cases-0.001
Token cheese
Token ID9891
Feature activation-9.75e-02

Pos logit contributions
 Ho+0.053
 Rib+0.052
 H+0.046
 Bub+0.043
 Bun+0.043
Neg logit contributions
eks-0.044
oos-0.044
ays-0.042
cases-0.042
ases-0.042
Token and
Token ID290
Feature activation+1.03e-02

Pos logit contributions
 Ho+0.167
 Rib+0.158
 H+0.136
 Lucky+0.131
 Po+0.129
Neg logit contributions
eks-0.165
oos-0.162
agged-0.156
 elevator-0.155
ases-0.153
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
oos+0.017
eks+0.017
 elevator+0.016
ays+0.016
cases+0.016
Neg logit contributions
 Ho-0.017
 Rib-0.016
 H-0.015
 Bun-0.014
 Bub-0.014
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
 Ho+0.339
 Rib+0.332
 H+0.300
 Bub+0.280
 Bun+0.277
Neg logit contributions
eks-0.260
oos-0.260
ays-0.251
 elevator-0.251
cases-0.251
Token lettuce
Token ID39406
Feature activation-9.48e-02

Pos logit contributions
 elevator+0.017
eks+0.017
oos+0.016
cases+0.016
ays+0.016
Neg logit contributions
 Ho-0.019
 Rib-0.019
 H-0.018
 Bun-0.016
 Bub-0.016
Token.
Token ID13
Feature activation+9.82e-04

Pos logit contributions
 Ho+0.163
 Rib+0.158
 H+0.137
 Bub+0.128
 Lucky+0.127
Neg logit contributions
oos-0.154
eks-0.154
 elevator-0.150
agged-0.148
cases-0.146
Token It
Token ID632
Feature activation-1.72e-04

Pos logit contributions
ays+0.002
oos+0.002
 elevator+0.002
ases+0.002
agged+0.002
Neg logit contributions
 Ho-0.001
 Rib-0.001
 H-0.001
 Bun-0.001
Ros-0.001
Token looks
Token ID3073
Feature activation+3.52e-02

Pos logit contributions
 Ho+0.000
 Rib+0.000
 H+0.000
 Bub+0.000
 Bun+0.000
Neg logit contributions
oos-0.000
eks-0.000
ays-0.000
cases-0.000
 elevator-0.000
Token Do
Token ID2141
Feature activation-1.17e-01

Pos logit contributions
 accidentally+0.035
 stub+0.031
 Ho+0.031
 Rib+0.030
 Bun+0.030
Neg logit contributions
ases-0.026
ays-0.024
icks-0.024
oops-0.024
 are-0.023
Token you
Token ID345
Feature activation-1.93e-02

Pos logit contributions
 Ho+0.223
 Rib+0.222
 accidentally+0.210
 H+0.206
 Bun+0.202
Neg logit contributions
eks-0.140
 are-0.136
 tickets-0.126
 elevator-0.123
ases-0.122
Token like
Token ID588
Feature activation-7.24e-03

Pos logit contributions
 Ho+0.044
 Rib+0.043
 H+0.040
 Bun+0.038
 Bub+0.037
Neg logit contributions
eks-0.021
ases-0.020
oos-0.019
he-0.019
agged-0.019
Token cheese
Token ID9891
Feature activation-9.87e-02

Pos logit contributions
 Ho+0.012
 H+0.012
 Rib+0.012
 Bun+0.011
 Cle+0.011
Neg logit contributions
ases-0.010
ays-0.010
cks-0.009
 tickets-0.009
eks-0.009
Token and
Token ID290
Feature activation+1.26e-03

Pos logit contributions
 Ho+0.206
 Rib+0.203
 H+0.190
 Bub+0.179
 Bun+0.178
Neg logit contributions
ays-0.112
ases-0.111
oos-0.111
he-0.110
eks-0.109
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
 are+0.001
 bags+0.001
 tickets+0.001
eks+0.001
 candles+0.001
Neg logit contributions
 H-0.002
 Ho-0.002
 Rib-0.002
 Bun-0.002
Ros-0.002
Token?"
Token ID1701
Feature activation-1.44e-02

Pos logit contributions
 Ho+0.356
 Rib+0.353
 H+0.339
 Bun+0.326
 Bub+0.319
Neg logit contributions
ays-0.231
ases-0.225
oos-0.215
eks-0.212
agged-0.211
Token
Token ID198
Feature activation-3.17e-02

Pos logit contributions
die+0.025
 accidentally+0.025
 Ho+0.024
ccoli+0.024
 Rib+0.024
Neg logit contributions
he-0.017
ases-0.016
ays-0.015
oos-0.015
eks-0.014
Token
Token ID198
Feature activation-3.19e-02

Pos logit contributions
 accidentally+0.052
 Rib+0.052
 Ho+0.051
 Butter+0.048
 Tooth+0.047
Neg logit contributions
he-0.044
ases-0.042
eks-0.041
oos-0.039
ays-0.039
TokenL
Token ID43
Feature activation-1.70e-02

Pos logit contributions
 Ho+0.046
 Rib+0.045
 accidentally+0.043
 Benny+0.042
 Butter+0.041
Neg logit contributions
ases-0.052
eks-0.051
he-0.050
oos-0.048
out-0.047
Tokenila
Token ID10102
Feature activation-5.00e-02

Pos logit contributions
 Ho+0.033
 Rib+0.032
 H+0.029
 Bun+0.028
 Bub+0.027
Neg logit contributions
eks-0.024
oos-0.024
ases-0.024
ays-0.024
agged-0.023
Token do
Token ID466
Feature activation-5.16e-02

Pos logit contributions
 Ho+0.067
 Rib+0.066
 H+0.060
 Bun+0.057
 Bub+0.055
Neg logit contributions
eks-0.047
oos-0.045
he-0.045
ases-0.045
out-0.044
Token not
Token ID407
Feature activation-7.13e-03

Pos logit contributions
 Ho+0.087
 Rib+0.085
 H+0.077
 Bun+0.073
 Bub+0.071
Neg logit contributions
eks-0.081
ases-0.081
 elevator-0.079
oos-0.079
out-0.078
Token like
Token ID588
Feature activation-3.61e-03

Pos logit contributions
 Ho+0.017
 Rib+0.016
 H+0.015
 Bun+0.014
 Bub+0.014
Neg logit contributions
eks-0.007
ases-0.007
he-0.007
oos-0.006
 elevator-0.006
Token cheese
Token ID9891
Feature activation-9.75e-02

Pos logit contributions
 Ho+0.006
 Rib+0.006
 H+0.006
 Bun+0.005
 Bub+0.005
Neg logit contributions
ays-0.006
oos-0.006
 elevator-0.006
ases-0.005
eks-0.005
Token and
Token ID290
Feature activation+6.73e-03

Pos logit contributions
 Ho+0.186
 Rib+0.183
 H+0.169
 Bub+0.158
 Bun+0.156
Neg logit contributions
oos-0.131
ays-0.129
ases-0.129
eks-0.128
 elevator-0.127
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
ases+0.010
 elevator+0.010
eks+0.010
oos+0.009
ays+0.009
Neg logit contributions
 Ho-0.011
 Rib-0.011
 H-0.011
 Bun-0.010
 Bub-0.010
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
 Ho+0.342
 Rib+0.336
 H+0.314
 Bun+0.296
 Bub+0.293
Neg logit contributions
oos-0.248
ays-0.248
ases-0.247
eks-0.244
agged-0.236
Token They
Token ID1119
Feature activation+4.37e-02

Pos logit contributions
 Ho+0.020
 Rib+0.020
 accidentally+0.019
 H+0.019
 Bun+0.019
Neg logit contributions
ays-0.016
ases-0.016
icks-0.015
oos-0.015
oops-0.014
Token are
Token ID389
Feature activation+5.34e-02

Pos logit contributions
oos+0.040
agged+0.037
ays+0.037
cases+0.036
eks+0.035
Neg logit contributions
 Ho-0.109
 Rib-0.106
 H-0.097
 Bub-0.094
 Butter-0.093
Token too
Token ID1165
Feature activation-3.15e-02

Pos logit contributions
ps+0.064
cks+0.064
 elevator+0.063
eks+0.061
ases+0.061
Neg logit contributions
 Rib-0.103
 Ho-0.100
 H-0.098
 Bun-0.094
Ros-0.091
Token salty
Token ID36021
Feature activation+7.21e-03

Pos logit contributions
 Ho+0.051
 Rib+0.048
 H+0.043
 accidentally+0.039
 Butter+0.039
Neg logit contributions
eks-0.056
oos-0.056
ays-0.053
cases-0.053
ases-0.053
Tokenmy
Token ID1820
Feature activation-3.69e-02

Pos logit contributions
ays+0.095
he+0.094
eks+0.094
oos+0.093
ases+0.091
Neg logit contributions
 Ho-0.113
 Rib-0.110
 H-0.097
 Bub-0.093
 Bun-0.090
Token hurts
Token ID20406
Feature activation-2.24e-02

Pos logit contributions
 Rib+0.071
 Ho+0.071
 H+0.064
 Bub+0.061
 Po+0.059
Neg logit contributions
eks-0.049
cases-0.048
led-0.048
oos-0.048
ays-0.047
Token from
Token ID422
Feature activation-9.26e-03

Pos logit contributions
 Ho+0.040
 Rib+0.039
 H+0.036
 Bun+0.033
 Bub+0.033
Neg logit contributions
eks-0.034
oos-0.034
ays-0.033
cases-0.033
agged-0.033
Token the
Token ID262
Feature activation-1.60e-02

Pos logit contributions
 Rib+0.017
 Ho+0.016
 H+0.014
Ros+0.014
 Bub+0.014
Neg logit contributions
 elevator-0.014
eks-0.013
oos-0.013
ags-0.013
ases-0.013
Token bad
Token ID2089
Feature activation-1.47e-02

Pos logit contributions
 Rib+0.031
 Ho+0.031
 H+0.028
 Bub+0.027
 Bun+0.026
Neg logit contributions
 elevator-0.022
oos-0.021
eks-0.021
he-0.021
cases-0.020
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
 Ho+0.025
 Rib+0.024
 H+0.022
 Bun+0.020
 Lucky+0.020
Neg logit contributions
eks-0.024
oos-0.024
cases-0.024
ays-0.024
agged-0.024
Token,"
Token ID553
Feature activation-2.99e-02

Pos logit contributions
 Ho+0.340
 Rib+0.336
 H+0.309
 Bub+0.290
 Bun+0.285
Neg logit contributions
oos-0.253
eks-0.252
ays-0.249
cases-0.247
 elevator-0.246
Token Lily
Token ID20037
Feature activation-5.17e-02

Pos logit contributions
 Ho+0.049
 Rib+0.048
 Bun+0.040
 H+0.040
onna+0.040
Neg logit contributions
 elevator-0.047
eks-0.044
ases-0.041
oos-0.040
 are-0.040
Token said
Token ID531
Feature activation-2.57e-02

Pos logit contributions
 Ho+0.091
 Rib+0.091
 H+0.079
 Bub+0.077
 Butter+0.075
Neg logit contributions
cases-0.078
led-0.075
eks-0.075
 elevator-0.073
hed-0.073
Token,
Token ID11
Feature activation-1.33e-02

Pos logit contributions
 Ho+0.055
 Rib+0.054
 H+0.049
 Bub+0.048
 Butter+0.046
Neg logit contributions
led-0.028
oos-0.028
cases-0.028
agged-0.028
out-0.027
Token rubbing
Token ID27714
Feature activation-9.51e-02

Pos logit contributions
 Ho+0.023
 Rib+0.023
 H+0.020
 Bub+0.019
 Bun+0.019
Neg logit contributions
ps-0.019
 elevator-0.019
eks-0.018
led-0.018
agged-0.018
Token had
Token ID550
Feature activation-2.83e-02

Pos logit contributions
 Ho+0.016
 Rib+0.016
 H+0.014
 Bun+0.013
 Bub+0.013
Neg logit contributions
eks-0.015
 elevator-0.015
oos-0.015
cases-0.015
led-0.015
Token already
Token ID1541
Feature activation-4.38e-02

Pos logit contributions
 Ho+0.044
 Rib+0.043
 H+0.038
 Bub+0.035
 Bun+0.035
Neg logit contributions
eks-0.049
oos-0.049
ays-0.048
cases-0.048
 elevator-0.048
Token put
Token ID1234
Feature activation-3.13e-02

Pos logit contributions
 Ho+0.068
 Rib+0.066
 H+0.060
 accidentally+0.059
 Bub+0.053
Neg logit contributions
ays-0.074
cases-0.073
oos-0.073
eks-0.070
agged-0.070
Token cheese
Token ID9891
Feature activation-9.89e-02

Pos logit contributions
 Ho+0.060
 Rib+0.057
 H+0.052
 Bub+0.049
 Butter+0.049
Neg logit contributions
eks-0.044
oos-0.043
cases-0.043
ases-0.043
ays-0.042
Token and
Token ID290
Feature activation+1.10e-02

Pos logit contributions
 Ho+0.180
 Rib+0.174
 H+0.155
 Bub+0.146
 Bun+0.145
Neg logit contributions
eks-0.149
oos-0.147
 elevator-0.143
ays-0.143
ases-0.142
Token ham
Token ID8891
Feature activation-1.82e-01

Pos logit contributions
 elevator+0.015
eks+0.015
oos+0.015
cases+0.014
led+0.014
Neg logit contributions
 Ho-0.020
 Rib-0.020
 H-0.019
 Bun-0.018
 Bub-0.017
Token in
Token ID287
Feature activation-1.96e-02

Pos logit contributions
 Ho+0.349
 Rib+0.344
 H+0.318
 Bun+0.296
 Bub+0.295
Neg logit contributions
oos-0.245
eks-0.244
ays-0.240
cases-0.237
ases-0.237
Token some
Token ID617
Feature activation+7.61e-02

Pos logit contributions
 Ho+0.032
 Rib+0.031
 H+0.028
 Bub+0.025
 Bun+0.025
Neg logit contributions
eks-0.033
oos-0.033
ays-0.032
cases-0.032
 elevator-0.032
Token of
Token ID286
Feature activation-4.26e-02

Pos logit contributions
eks+0.109
oos+0.108
ays+0.105
cases+0.105
ases+0.104
Neg logit contributions
 Ho-0.143
 Rib-0.140
 H-0.126
 Bub-0.118
 Bun-0.117
Token the
Token ID262
Feature activation-8.87e-03

Pos logit contributions
 Ho+0.091
 Rib+0.090
 H+0.083
 Bun+0.078
 Bub+0.076
Neg logit contributions
eks-0.047
oos-0.047
 elevator-0.047
ays-0.045
ases-0.045
Token eggs
Token ID9653
Feature activation-5.60e-02

Pos logit contributions
 Ho+0.019
 Rib+0.019
 H+0.018
 Bub+0.016
 Bun+0.016
Neg logit contributions
eks-0.010
oos-0.010
ays-0.010
cases-0.009
 elevator-0.009
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
eks+0.071
oos+0.070
agged+0.068
ays+0.066
ases+0.066
Neg logit contributions
 Ho-0.049
 Rib-0.046
 H-0.039
 Lucky-0.038
 Bub-0.036
Token They
Token ID1119
Feature activation+4.61e-02

Pos logit contributions
 Rib+0.021
 Ho+0.020
 H+0.018
 Bun+0.018
 Bub+0.017
Neg logit contributions
ays-0.017
he-0.016
oos-0.016
ases-0.016
agged-0.016
Token were
Token ID547
Feature activation+5.28e-02

Pos logit contributions
oos+0.078
eks+0.076
ays+0.076
agged+0.075
ases+0.074
Neg logit contributions
 Ho-0.077
 Rib-0.074
 H-0.066
 Bub-0.061
 Bun-0.061
Token cheese
Token ID9891
Feature activation-9.85e-02

Pos logit contributions
eks+0.072
 elevator+0.072
agged+0.071
ags+0.070
led+0.069
Neg logit contributions
 Rib-0.098
 Ho-0.098
 H-0.091
 Bun-0.085
 Bub-0.083
Token and
Token ID290
Feature activation+5.60e-03

Pos logit contributions
 Ho+0.169
 Rib+0.161
 H+0.137
 Lucky+0.133
 Bun+0.130
Neg logit contributions
eks-0.169
oos-0.166
agged-0.159
ays-0.159
 elevator-0.159
Token ham
Token ID8891
Feature activation-1.81e-01

Pos logit contributions
 elevator+0.008
eks+0.008
oos+0.008
led+0.007
cases+0.007
Neg logit contributions
 Ho-0.010
 Rib-0.010
 H-0.009
 Bun-0.008
 Bub-0.008
Token and
Token ID290
Feature activation+6.67e-03

Pos logit contributions
 Ho+0.341
 Rib+0.335
 H+0.306
 Bub+0.285
 Bun+0.283
Neg logit contributions
oos-0.254
eks-0.253
ays-0.247
cases-0.246
ases-0.245
Token lettuce
Token ID39406
Feature activation-9.48e-02

Pos logit contributions
 elevator+0.009
eks+0.009
ases+0.009
led+0.009
cases+0.009
Neg logit contributions
 Ho-0.012
 Rib-0.012
 H-0.011
 Bun-0.010
 Bub-0.010
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
 Ho+0.168
 Rib+0.163
 H+0.144
 Bub+0.135
 Bun+0.133
Neg logit contributions
eks-0.149
oos-0.148
 elevator-0.143
agged-0.142
ays-0.142
Token They
Token ID1119
Feature activation+4.61e-02

Pos logit contributions
 Rib+0.024
 Ho+0.024
 H+0.021
 Bun+0.021
 accidentally+0.020
Neg logit contributions
ays-0.017
he-0.016
ases-0.015
ags-0.015
agged-0.015
Token were
Token ID547
Feature activation+5.40e-02

Pos logit contributions
oos+0.072
eks+0.072
ays+0.070
 elevator+0.070
cases+0.070
Neg logit contributions
 Ho-0.080
 Rib-0.078
 H-0.070
 Bub-0.065
 Bun-0.064
Token.
Token ID13
Feature activation-1.80e-02

Pos logit contributions
 Ho+0.054
 Rib+0.054
 H+0.049
 Bub+0.045
 Bun+0.045
Neg logit contributions
oos-0.040
eks-0.039
ays-0.039
ases-0.039
cases-0.039
Token It
Token ID632
Feature activation-2.51e-03

Pos logit contributions
 accidentally+0.032
 Ho+0.029
 Rib+0.028
 stub+0.028
 Bun+0.028
Neg logit contributions
ases-0.024
ays-0.022
oops-0.022
 are-0.022
ags-0.022
Token is
Token ID318
Feature activation+1.61e-02

Pos logit contributions
 Ho+0.005
 Rib+0.005
 H+0.005
 Bun+0.005
 Bub+0.005
Neg logit contributions
eks-0.003
ays-0.003
 elevator-0.003
ases-0.003
oos-0.003
Token cheese
Token ID9891
Feature activation-9.86e-02

Pos logit contributions
cks+0.017
ags+0.016
ps+0.015
 candles+0.015
 elevator+0.015
Neg logit contributions
 Rib-0.032
 H-0.031
 Ho-0.030
 Bun-0.030
Ros-0.030
Token and
Token ID290
Feature activation+8.55e-04

Pos logit contributions
 Ho+0.179
 Rib+0.175
 H+0.158
 Bub+0.146
 Bun+0.145
Neg logit contributions
eks-0.147
oos-0.147
ays-0.142
 elevator-0.142
cases-0.141
Token ham
Token ID8891
Feature activation-1.81e-01

Pos logit contributions
 elevator+0.001
eks+0.001
 are+0.001
 bags+0.001
ases+0.001
Neg logit contributions
 Ho-0.001
 Rib-0.001
 H-0.001
 Bun-0.001
 Bub-0.001
Token.
Token ID13
Feature activation-1.93e-02

Pos logit contributions
 Ho+0.340
 Rib+0.336
 H+0.318
 Bun+0.299
 Bub+0.295
Neg logit contributions
ases-0.243
ays-0.243
oos-0.240
eks-0.236
cases-0.232
Token Do
Token ID2141
Feature activation-1.17e-01

Pos logit contributions
 accidentally+0.035
 stub+0.031
 Ho+0.031
 Rib+0.030
 Bun+0.030
Neg logit contributions
ases-0.026
ays-0.024
icks-0.024
oops-0.024
 are-0.023
Token you
Token ID345
Feature activation-1.93e-02

Pos logit contributions
 Ho+0.223
 Rib+0.222
 accidentally+0.210
 H+0.206
 Bun+0.202
Neg logit contributions
eks-0.140
 are-0.136
 tickets-0.126
 elevator-0.123
ases-0.122
Token like
Token ID588
Feature activation-7.24e-03

Pos logit contributions
 Ho+0.044
 Rib+0.043
 H+0.040
 Bun+0.038
 Bub+0.037
Neg logit contributions
eks-0.021
ases-0.020
oos-0.019
he-0.019
agged-0.019
Token cheese
Token ID9891
Feature activation-9.87e-02

Pos logit contributions
 Ho+0.012
 H+0.012
 Rib+0.012
 Bun+0.011
 Cle+0.011
Neg logit contributions
ases-0.010
ays-0.010
cks-0.009
 tickets-0.009
eks-0.009
Token watching
Token ID4964
Feature activation-4.02e-02

Pos logit contributions
 Ho+0.065
 Rib+0.064
 H+0.058
 Bub+0.054
 Bun+0.053
Neg logit contributions
eks-0.047
oos-0.046
 elevator-0.046
led-0.045
ases-0.044
Token her
Token ID607
Feature activation-1.72e-02

Pos logit contributions
 Rib+0.073
 Ho+0.073
 H+0.065
 accidentally+0.062
 Bub+0.060
Neg logit contributions
oos-0.055
 elevator-0.052
eks-0.051
ases-0.051
cases-0.050
Token eat
Token ID4483
Feature activation-1.63e-02

Pos logit contributions
 Ho+0.033
 Rib+0.032
 H+0.029
 accidentally+0.028
 Bub+0.027
Neg logit contributions
oos-0.022
eks-0.022
cases-0.022
ases-0.022
he-0.022
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
 Ho+0.030
 Rib+0.030
 H+0.027
 Bub+0.025
 Bun+0.025
Neg logit contributions
oos-0.023
eks-0.023
 elevator-0.023
ays-0.022
ases-0.022
Token pine
Token ID20161
Feature activation-5.51e-02

Pos logit contributions
 Ho+0.020
 Rib+0.020
 H+0.018
 Bub+0.016
 Bun+0.016
Neg logit contributions
oos-0.015
 elevator-0.015
eks-0.015
cases-0.015
he-0.015
Tokencon
Token ID1102
Feature activation-1.81e-01

Pos logit contributions
 Ho+0.106
 Rib+0.105
 H+0.095
 Bub+0.090
 accidentally+0.086
Neg logit contributions
oos-0.074
 elevator-0.074
cases-0.073
he-0.073
eks-0.071
Tokenes
Token ID274
Feature activation-1.14e-02

Pos logit contributions
 Ho+0.383
 Rib+0.376
 H+0.345
 Bub+0.324
 Bun+0.320
Neg logit contributions
oos-0.214
eks-0.212
cases-0.207
ays-0.205
 elevator-0.204
Token.
Token ID13
Feature activation-9.97e-03

Pos logit contributions
 Ho+0.019
 Rib+0.019
 H+0.017
 Bun+0.016
 Bub+0.016
Neg logit contributions
eks-0.018
oos-0.018
agged-0.018
ays-0.018
ases-0.018
Token The
Token ID383
Feature activation-5.96e-03

Pos logit contributions
 Rib+0.019
 Ho+0.018
please+0.016
 Stri+0.016
 H+0.015
Neg logit contributions
cases-0.011
oos-0.010
he-0.010
hed-0.010
 elevator-0.009
Token squirrel
Token ID33039
Feature activation-2.69e-02

Pos logit contributions
 Rib+0.009
 Ho+0.009
onna+0.008
 accidentally+0.007
 H+0.007
Neg logit contributions
 elevator-0.010
eks-0.010
he-0.010
oos-0.009
agged-0.009
Token said
Token ID531
Feature activation-2.10e-02

Pos logit contributions
 Ho+0.045
 Rib+0.044
 H+0.039
 Bub+0.035
 Butter+0.035
Neg logit contributions
eks-0.044
oos-0.043
cases-0.043
led-0.042
 elevator-0.042
Token and
Token ID290
Feature activation+3.99e-03

Pos logit contributions
 Ho+0.095
 Rib+0.092
 H+0.081
 Bub+0.076
 Butter+0.074
Neg logit contributions
eks-0.097
oos-0.096
agged-0.094
 elevator-0.092
ases-0.092
Token the
Token ID262
Feature activation-1.34e-02

Pos logit contributions
eks+0.006
 elevator+0.005
oos+0.005
ases+0.005
cases+0.005
Neg logit contributions
 Rib-0.007
 Ho-0.007
 H-0.007
 Bun-0.006
 Bub-0.006
Token cheese
Token ID9891
Feature activation-9.79e-02

Pos logit contributions
 Ho+0.027
 Rib+0.026
 H+0.026
 Bun+0.024
 Bub+0.024
Neg logit contributions
 elevator-0.016
oos-0.016
eks-0.016
 tickets-0.015
ases-0.015
Token and
Token ID290
Feature activation+5.27e-03

Pos logit contributions
 Ho+0.156
 Rib+0.149
 H+0.126
 accidentally+0.120
 Lucky+0.120
Neg logit contributions
eks-0.170
oos-0.167
agged-0.166
ases-0.159
ays-0.158
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
eks+0.008
 elevator+0.007
oos+0.007
ases+0.007
ays+0.007
Neg logit contributions
 Ho-0.009
 Rib-0.009
 H-0.009
 Bun-0.008
 Bub-0.008
Token ham
Token ID8891
Feature activation-1.81e-01

Pos logit contributions
 Rib+0.025
 Ho+0.025
 H+0.024
 Bun+0.022
 Bub+0.022
Neg logit contributions
 elevator-0.016
oos-0.015
eks-0.015
 tickets-0.015
ases-0.015
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
 Ho+0.334
 Rib+0.327
 H+0.297
 Bub+0.276
 Bun+0.274
Neg logit contributions
eks-0.262
oos-0.262
ays-0.255
cases-0.253
 elevator-0.253
Token Can
Token ID1680
Feature activation-1.02e-01

Pos logit contributions
 Ho+0.022
 Rib+0.022
 accidentally+0.021
 Bun+0.021
 H+0.020
Neg logit contributions
ays-0.016
ases-0.016
ags-0.015
 are-0.014
oos-0.014
Token you
Token ID345
Feature activation-1.83e-02

Pos logit contributions
 Ho+0.178
 Rib+0.177
 H+0.161
 Bub+0.150
 Bun+0.149
Neg logit contributions
 elevator-0.141
eks-0.136
ays-0.135
oos-0.133
cases-0.132
Token help
Token ID1037
Feature activation-6.46e-03

Pos logit contributions
 Ho+0.036
 Rib+0.036
 H+0.032
 Bun+0.030
 Bub+0.029
Neg logit contributions
eks-0.025
he-0.024
oos-0.023
 elevator-0.023
ases-0.023
Token me
Token ID502
Feature activation-2.46e-02

Pos logit contributions
 Rib+0.012
 Ho+0.012
 H+0.011
 Bub+0.010
 Bun+0.010
Neg logit contributions
eks-0.009
oos-0.009
ases-0.009
he-0.009
 elevator-0.009
Token light
Token ID1657
Feature activation-1.88e-02

Pos logit contributions
 elevator+0.082
oos+0.077
he+0.076
eks+0.076
ays+0.074
Neg logit contributions
 Ho-0.124
 Rib-0.124
 H-0.109
 Bub-0.102
 Stri-0.102
Token way
Token ID835
Feature activation+1.29e-02

Pos logit contributions
 Ho+0.034
 Rib+0.033
 H+0.030
 Bun+0.028
 Bub+0.028
Neg logit contributions
eks-0.028
oos-0.028
ases-0.027
agged-0.027
cases-0.027
Token off
Token ID572
Feature activation+1.47e-02

Pos logit contributions
eks+0.021
oos+0.021
ases+0.020
agged+0.020
cases+0.020
Neg logit contributions
 Ho-0.022
 Rib-0.021
 H-0.020
 Bub-0.018
 Bun-0.018
Token in
Token ID287
Feature activation-1.14e-02

Pos logit contributions
eks+0.028
oos+0.027
cases+0.027
ases+0.027
ays+0.027
Neg logit contributions
 Ho-0.021
 Rib-0.020
 H-0.018
 Bub-0.017
 Bun-0.017
Token the
Token ID262
Feature activation-1.31e-03

Pos logit contributions
 Ho+0.017
 Rib+0.016
 H+0.015
 Bub+0.013
 Po+0.013
Neg logit contributions
cases-0.023
agged-0.022
oos-0.022
led-0.021
ays-0.021
Token distance
Token ID5253
Feature activation+1.04e-01

Pos logit contributions
 Ho+0.002
 Rib+0.002
 H+0.002
 Bun+0.002
 Bub+0.002
Neg logit contributions
ays-0.002
eks-0.002
oos-0.002
ases-0.002
cases-0.002
Token.
Token ID13
Feature activation+8.79e-03

Pos logit contributions
oos+0.141
eks+0.138
 elevator+0.137
ays+0.136
cases+0.136
Neg logit contributions
 Ho-0.202
 Rib-0.198
 H-0.178
 Bub-0.167
 Bun-0.166
Token He
Token ID679
Feature activation+3.20e-02

Pos logit contributions
oos+0.013
 elevator+0.013
cases+0.013
agged+0.012
eks+0.012
Neg logit contributions
 Rib-0.016
 Ho-0.016
 H-0.013
 Bub-0.012
 Lucky-0.012
Token ran
Token ID4966
Feature activation+7.44e-02

Pos logit contributions
eks+0.042
led+0.041
oos+0.039
 elevator+0.037
out+0.037
Neg logit contributions
 Rib-0.064
 Ho-0.063
 H-0.055
onna-0.054
 Butter-0.054
Token over
Token ID625
Feature activation+4.03e-02

Pos logit contributions
ays+0.120
oos+0.119
eks+0.118
ases+0.117
agged+0.115
Neg logit contributions
 Ho-0.129
 Rib-0.124
 H-0.115
 Bub-0.108
 Bun-0.107
Token to
Token ID284
Feature activation-5.35e-03

Pos logit contributions
oos+0.073
eks+0.073
 elevator+0.071
ases+0.070
ays+0.069
Neg logit contributions
 Ho-0.060
 Rib-0.059
 H-0.051
 Bub-0.047
 Bun-0.046
Token were
Token ID547
Feature activation+5.31e-02

Pos logit contributions
 Ho+0.090
 Rib+0.087
 H+0.079
 Bub+0.075
 Bun+0.075
Neg logit contributions
ays-0.073
oos-0.073
eks-0.072
ases-0.071
 elevator-0.070
Token ready
Token ID3492
Feature activation+6.86e-04

Pos logit contributions
oos+0.088
eks+0.088
ays+0.086
cases+0.085
ases+0.085
Neg logit contributions
 Ho-0.088
 Rib-0.086
 H-0.076
 Bub-0.070
 Bun-0.070
Token for
Token ID329
Feature activation+2.56e-02

Pos logit contributions
eks+0.001
oos+0.001
ays+0.001
ases+0.001
 elevator+0.001
Neg logit contributions
 Ho-0.001
 Rib-0.001
 H-0.001
 Bub-0.001
 Bun-0.001
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
eks+0.037
oos+0.037
 elevator+0.036
ays+0.035
cases+0.035
Neg logit contributions
 Ho-0.047
 Rib-0.047
 H-0.042
 Bub-0.039
 Bun-0.039
Token next
Token ID1306
Feature activation+7.46e-02

Pos logit contributions
 Ho+0.023
 Rib+0.023
 H+0.021
 Bub+0.019
 Bun+0.019
Neg logit contributions
eks-0.017
oos-0.017
ays-0.016
cases-0.016
ases-0.016
Token journey
Token ID7002
Feature activation+8.85e-02

Pos logit contributions
eks+0.107
oos+0.107
ays+0.104
cases+0.103
ases+0.103
Neg logit contributions
 Ho-0.140
 Rib-0.137
 H-0.124
 Bub-0.115
 Bun-0.115
Token!
Token ID0
Feature activation+3.38e-02

Pos logit contributions
eks+0.143
oos+0.139
ays+0.137
ases+0.137
agged+0.136
Neg logit contributions
 Ho-0.151
 Rib-0.147
 H-0.133
 Bun-0.124
 Bub-0.123
Token<|endoftext|>
Token ID50256
Feature activation+1.15e-01

Pos logit contributions
cases+0.060
ays+0.059
he+0.058
oos+0.058
 elevator+0.057
Neg logit contributions
 Ho-0.049
 Rib-0.049
 H-0.042
 accidentally-0.040
 Bub-0.039
TokenSam
Token ID16305
Feature activation+2.84e-02

Pos logit contributions
he+0.153
hed+0.145
ays+0.141
oos+0.139
agged+0.132
Neg logit contributions
 Ho-0.226
 Rib-0.226
 H-0.203
 accidentally-0.194
 Butter-0.193
Tokenmy
Token ID1820
Feature activation-1.25e-02

Pos logit contributions
eks+0.052
oos+0.051
cases+0.051
agged+0.051
ays+0.051
Neg logit contributions
 Ho-0.042
 Rib-0.040
 H-0.036
 Bun-0.033
 Bub-0.033
Token and
Token ID290
Feature activation+2.51e-02

Pos logit contributions
 Ho+0.020
 Rib+0.019
 H+0.017
 Bun+0.016
 accidentally+0.016
Neg logit contributions
eks-0.021
oos-0.021
agged-0.021
ases-0.021
cases-0.021
Token was
Token ID373
Feature activation+8.21e-03

Pos logit contributions
eks+0.002
oos+0.002
 elevator+0.002
cases+0.002
ays+0.002
Neg logit contributions
 Ho-0.002
 Rib-0.002
 H-0.002
 Bub-0.002
 Bun-0.002
Token living
Token ID2877
Feature activation-5.04e-02

Pos logit contributions
 elevator+0.010
oos+0.010
eks+0.010
ays+0.010
ases+0.010
Neg logit contributions
 Ho-0.016
 Rib-0.016
 H-0.015
 Bub-0.014
 Bun-0.014
Token.
Token ID13
Feature activation-9.36e-03

Pos logit contributions
 Ho+0.091
 Rib+0.089
 H+0.081
 Bub+0.074
 Bun+0.073
Neg logit contributions
eks-0.076
oos-0.075
cases-0.075
agged-0.074
ays-0.073
Token He
Token ID679
Feature activation+2.55e-02

Pos logit contributions
 Rib+0.018
 Ho+0.018
please+0.015
Ros+0.015
 accidentally+0.015
Neg logit contributions
cases-0.011
 elevator-0.010
oos-0.010
he-0.010
roads-0.009
Token was
Token ID373
Feature activation+7.21e-03

Pos logit contributions
eks+0.036
cases+0.035
led+0.034
oos+0.034
 elevator+0.033
Neg logit contributions
 Rib-0.047
 Ho-0.047
 H-0.042
 Butter-0.039
 Bub-0.038
Token eager
Token ID11069
Feature activation+8.63e-02

Pos logit contributions
eks+0.010
 elevator+0.010
cases+0.009
oos+0.009
ases+0.009
Neg logit contributions
 Ho-0.013
 Rib-0.013
 H-0.012
 Bub-0.011
 Bun-0.011
Token to
Token ID284
Feature activation-1.75e-02

Pos logit contributions
oos+0.153
eks+0.151
 elevator+0.150
cases+0.150
ases+0.147
Neg logit contributions
 Ho-0.130
 Rib-0.128
 H-0.110
 Bub-0.102
 Butter-0.101
Token find
Token ID1064
Feature activation-1.76e-03

Pos logit contributions
 Ho+0.034
 Rib+0.033
 H+0.030
 Bub+0.028
 Bun+0.028
Neg logit contributions
oos-0.024
eks-0.024
ays-0.024
cases-0.023
 elevator-0.023
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
 Ho+0.003
 Rib+0.003
 H+0.003
 Bub+0.003
 Bun+0.003
Neg logit contributions
oos-0.003
agged-0.003
ays-0.003
cases-0.003
eks-0.002
Token creature
Token ID7185
Feature activation+7.93e-04

Pos logit contributions
 Ho+0.029
 Rib+0.029
 H+0.026
 Bun+0.024
 Bub+0.024
Neg logit contributions
 elevator-0.022
eks-0.021
oos-0.020
he-0.020
cases-0.019
Token!
Token ID0
Feature activation+3.48e-02

Pos logit contributions
eks+0.001
oos+0.001
ays+0.001
ases+0.001
agged+0.001
Neg logit contributions
 Ho-0.001
 Rib-0.001
 H-0.001
 Bub-0.001
 Bun-0.001
Token we
Token ID356
Feature activation+1.89e-02

Pos logit contributions
 Rib+0.054
 Ho+0.054
 H+0.047
 Bub+0.045
 Fro+0.045
Neg logit contributions
 elevator-0.045
oos-0.043
cases-0.043
eks-0.043
 tickets-0.042
Token can
Token ID460
Feature activation-9.79e-02

Pos logit contributions
eks+0.029
oos+0.028
ays+0.028
 elevator+0.028
cases+0.028
Neg logit contributions
 Ho-0.034
 Rib-0.033
 H-0.030
 Bub-0.028
 Bun-0.028
Token fix
Token ID4259
Feature activation-8.45e-02

Pos logit contributions
 Ho+0.183
 Rib+0.181
 H+0.161
 Butter+0.150
 Bub+0.149
Neg logit contributions
he-0.140
eks-0.138
oos-0.137
ases-0.136
ays-0.134
Token it
Token ID340
Feature activation+1.20e-02

Pos logit contributions
 Rib+0.123
 Ho+0.122
 H+0.104
 Bub+0.097
 Bun+0.095
Neg logit contributions
ays-0.153
oos-0.152
eks-0.151
 elevator-0.150
ases-0.149
Token."
Token ID526
Feature activation-7.09e-03

Pos logit contributions
eks+0.019
oos+0.019
ays+0.018
 elevator+0.018
cases+0.018
Neg logit contributions
 Ho-0.021
 Rib-0.020
 H-0.018
 Bub-0.017
 Bun-0.017
Token<|endoftext|>
Token ID50256
Feature activation+1.18e-01

Pos logit contributions
 Rib+0.011
 Ho+0.011
 H+0.009
 Bub+0.009
 Bun+0.009
Neg logit contributions
he-0.012
ays-0.012
oos-0.011
agged-0.011
ags-0.011
TokenSam
Token ID16305
Feature activation+3.64e-02

Pos logit contributions
he+0.129
ays+0.124
hed+0.120
oos+0.119
ases+0.117
Neg logit contributions
 Ho-0.255
 Rib-0.255
 H-0.232
 Bub-0.229
 accidentally-0.227
Token likes
Token ID7832
Feature activation+3.99e-02

Pos logit contributions
eks+0.067
oos+0.067
cases+0.066
ays+0.066
 elevator+0.065
Neg logit contributions
 Ho-0.053
 Rib-0.050
 H-0.046
 Bun-0.041
 Bub-0.041
Token to
Token ID284
Feature activation-2.38e-03

Pos logit contributions
 elevator+0.057
oos+0.055
 tickets+0.051
 bags+0.050
ases+0.050
Neg logit contributions
 Ho-0.072
 Rib-0.071
 H-0.062
Ros-0.060
 Tw-0.060
Token play
Token ID711
Feature activation+8.16e-03

Pos logit contributions
 Ho+0.004
 Rib+0.004
 H+0.004
 Bub+0.003
 Bun+0.003
Neg logit contributions
eks-0.004
oos-0.004
ays-0.004
 elevator-0.004
cases-0.004
Token with
Token ID351
Feature activation+4.39e-02

Pos logit contributions
oos+0.012
eks+0.012
 elevator+0.012
ays+0.012
ases+0.012
Neg logit contributions
 Ho-0.015
 Rib-0.015
 H-0.013
 Bub-0.012
 Butter-0.012
Token a
Token ID257
Feature activation-1.67e-02

Pos logit contributions
eks+0.033
oos+0.032
 elevator+0.032
ases+0.032
he+0.030
Neg logit contributions
 Ho-0.046
 Rib-0.046
 H-0.040
 Bub-0.039
 Butter-0.038
Token year
Token ID614
Feature activation+1.02e-01

Pos logit contributions
 Rib+0.029
 Ho+0.028
 H+0.024
 Stri+0.024
 Fro+0.023
Neg logit contributions
 elevator-0.024
cases-0.024
he-0.023
ued-0.023
 tickets-0.023
Token and
Token ID290
Feature activation+3.02e-03

Pos logit contributions
eks+0.157
oos+0.156
ays+0.152
ases+0.151
agged+0.150
Neg logit contributions
 Ho-0.179
 Rib-0.175
 H-0.159
 Bub-0.146
 Bun-0.146
Token more
Token ID517
Feature activation-1.03e-01

Pos logit contributions
cases+0.004
eks+0.004
 elevator+0.004
 are+0.004
oos+0.004
Neg logit contributions
 Rib-0.005
 Ho-0.005
 H-0.005
 Bub-0.004
 Bun-0.004
Token.
Token ID13
Feature activation-1.60e-02

Pos logit contributions
 Ho+0.202
 Rib+0.201
 H+0.179
 Bub+0.170
 Butter+0.165
Neg logit contributions
oos-0.135
 elevator-0.134
ases-0.131
led-0.130
cases-0.128
Token<|endoftext|>
Token ID50256
Feature activation+1.09e-01

Pos logit contributions
 Ho+0.027
 Rib+0.027
 accidentally+0.025
 H+0.024
 Bun+0.023
Neg logit contributions
ays-0.022
ases-0.022
he-0.022
agged-0.021
ags-0.021
TokenAnna
Token ID31160
Feature activation-3.06e-02

Pos logit contributions
he+0.196
ays+0.185
oos+0.185
hed+0.183
ases+0.182
Neg logit contributions
 Ho-0.169
 Rib-0.166
 H-0.144
 Bub-0.137
 accidentally-0.136
Token and
Token ID290
Feature activation+1.93e-02

Pos logit contributions
 Ho+0.053
 Rib+0.052
 H+0.047
 Bub+0.043
 Bun+0.043
Neg logit contributions
eks-0.048
oos-0.048
ays-0.047
cases-0.047
 elevator-0.047
Token Ben
Token ID3932
Feature activation+1.35e-02

Pos logit contributions
oos+0.034
eks+0.033
ays+0.033
cases+0.033
 elevator+0.032
Neg logit contributions
 Ho-0.031
 Rib-0.030
 H-0.027
 Bub-0.024
 Bun-0.024
Token love
Token ID1842
Feature activation+3.32e-02

Pos logit contributions
cases+0.022
ays+0.022
oos+0.021
agged+0.021
irens+0.021
Neg logit contributions
 Ho-0.025
 Rib-0.022
 H-0.022
 Bub-0.020
 accidentally-0.020
Token to
Token ID284
Feature activation-6.92e-03

Pos logit contributions
oos+0.054
 elevator+0.054
ases+0.052
ays+0.051
 tickets+0.050
Neg logit contributions
 Ho-0.055
 Rib-0.053
 H-0.048
 Bub-0.046
 Bun-0.045
Token vendor
Token ID18371
Feature activation+6.92e-02

Pos logit contributions
cks+0.010
eks+0.010
ases+0.010
ays+0.010
oos+0.010
Neg logit contributions
 Lily-0.004
 Rib-0.004
 "-0.004
-0.003
 friend-0.003
Token is
Token ID318
Feature activation+2.06e-02

Pos logit contributions
agged+0.094
oos+0.094
ags+0.088
cases+0.087
ays+0.087
Neg logit contributions
 Ho-0.133
 Rib-0.130
 H-0.112
 Tw-0.108
 Will-0.106
Token happy
Token ID3772
Feature activation+1.48e-02

Pos logit contributions
 elevator+0.031
eks+0.031
agged+0.030
ases+0.030
ags+0.030
Neg logit contributions
 Ho-0.037
 Rib-0.036
 H-0.032
 Bun-0.031
 Bub-0.031
Token to
Token ID284
Feature activation-1.41e-02

Pos logit contributions
ases+0.017
oos+0.017
ays+0.017
 elevator+0.017
out+0.017
Neg logit contributions
 Ho-0.030
 Rib-0.030
 H-0.027
 Bub-0.026
 Bun-0.026
Token see
Token ID766
Feature activation+3.53e-02

Pos logit contributions
 Ho+0.023
 Rib+0.023
 H+0.021
 Bub+0.019
 Bun+0.018
Neg logit contributions
ays-0.025
cases-0.024
oos-0.024
led-0.023
 elevator-0.023
Token them
Token ID606
Feature activation+4.54e-02

Pos logit contributions
oos+0.065
eks+0.065
ays+0.064
 elevator+0.063
ases+0.063
Neg logit contributions
 Ho-0.051
 Rib-0.050
 H-0.044
 Bub-0.039
 Bun-0.039
Token.
Token ID13
Feature activation-1.55e-02

Pos logit contributions
oos+0.080
eks+0.079
agged+0.078
ays+0.076
 elevator+0.075
Neg logit contributions
 Ho-0.072
 Rib-0.071
 H-0.063
 Bub-0.058
 Bun-0.057
Token He
Token ID679
Feature activation+2.25e-02

Pos logit contributions
 Rib+0.029
 Ho+0.029
 Bun+0.026
 H+0.025
Ros+0.025
Neg logit contributions
ays-0.020
 elevator-0.019
cases-0.019
agged-0.019
ags-0.019
Token gives
Token ID3607
Feature activation-2.26e-02

Pos logit contributions
oos+0.028
eks+0.027
ays+0.027
cases+0.026
 elevator+0.026
Neg logit contributions
 Ho-0.047
 Rib-0.046
 H-0.042
 Bub-0.039
 Bun-0.039
Token them
Token ID606
Feature activation+4.47e-02

Pos logit contributions
 Ho+0.047
 Rib+0.047
 H+0.043
 Bun+0.040
 Bub+0.040
Neg logit contributions
oos-0.027
eks-0.027
ays-0.026
 elevator-0.026
ases-0.025
Token each
Token ID1123
Feature activation+1.03e-01

Pos logit contributions
eks+0.084
roads+0.083
ays+0.082
cks+0.081
ement+0.079
Neg logit contributions
 Ho-0.071
 Rib-0.067
 H-0.059
 Bub-0.056
 Lucky-0.055
Token asleep
Token ID16039
Feature activation-4.95e-02

Pos logit contributions
 Rib+0.024
 Ho+0.024
 H+0.020
 Butter+0.019
 Bub+0.019
Neg logit contributions
oos-0.028
eks-0.028
ays-0.027
 elevator-0.027
cases-0.027
Token with
Token ID351
Feature activation+2.93e-02

Pos logit contributions
 Rib+0.093
 Ho+0.091
 H+0.079
 Butter+0.077
 Bub+0.077
Neg logit contributions
he-0.070
led-0.066
eks-0.066
 elevator-0.065
cases-0.065
Token a
Token ID257
Feature activation-1.99e-02

Pos logit contributions
eks+0.046
oos+0.046
ays+0.044
 elevator+0.044
cases+0.044
Neg logit contributions
 Ho-0.050
 Rib-0.050
 H-0.044
 Bub-0.041
 Bun-0.041
Token tum
Token ID11814
Feature activation+6.23e-02

Pos logit contributions
 Rib+0.044
 Ho+0.042
 H+0.040
 Bub+0.037
 Stri+0.037
Neg logit contributions
he-0.022
 elevator-0.020
cases-0.019
eks-0.019
 lobby-0.018
Tokenmy
Token ID1820
Feature activation-3.59e-02

Pos logit contributions
ays+0.098
oos+0.098
he+0.097
eks+0.097
agged+0.096
Neg logit contributions
 Ho-0.108
 Rib-0.106
 H-0.093
 Bub-0.088
 Bun-0.086
Token full
Token ID1336
Feature activation+4.68e-02

Pos logit contributions
 Rib+0.067
 Ho+0.066
 H+0.060
 Bub+0.056
 Fro+0.054
Neg logit contributions
he-0.050
led-0.049
cases-0.049
 elevator-0.048
oos-0.048
Token of
Token ID286
Feature activation-4.73e-02

Pos logit contributions
eks+0.058
oos+0.057
ays+0.055
cases+0.055
ases+0.055
Neg logit contributions
 Ho-0.098
 Rib-0.096
 H-0.088
 Bub-0.083
 Bun-0.082
Token y
Token ID331
Feature activation-9.38e-03

Pos logit contributions
 Ho+0.087
 Rib+0.086
 H+0.077
 Bub+0.072
 Bun+0.071
Neg logit contributions
eks-0.068
oos-0.068
 elevator-0.066
ays-0.066
ases-0.065
Tokenummy
Token ID13513
Feature activation+1.41e-02

Pos logit contributions
 Ho+0.015
 Rib+0.014
 H+0.012
 Po+0.012
 Benny+0.012
Neg logit contributions
eks-0.017
roads-0.017
cases-0.016
 elevator-0.016
ued-0.016
Token cookies
Token ID14746
Feature activation-5.46e-02

Pos logit contributions
eks+0.023
oos+0.022
ays+0.022
ases+0.022
cases+0.021
Neg logit contributions
 Ho-0.025
 Rib-0.024
 H-0.021
 Bun-0.020
 Bub-0.020
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 Ho+0.095
 Rib+0.091
 H+0.082
 Bun+0.076
 Bub+0.076
Neg logit contributions
eks-0.088
oos-0.087
ases-0.084
ays-0.083
agged-0.083
Token to
Token ID284
Feature activation-1.51e-02

Pos logit contributions
oos+0.037
eks+0.037
agged+0.037
ays+0.036
ases+0.036
Neg logit contributions
 Ho-0.034
 Rib-0.033
 H-0.031
 Bub-0.027
 Bun-0.027
Token the
Token ID262
Feature activation-1.17e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.023
 Bub+0.022
 Bun+0.022
Neg logit contributions
eks-0.023
oos-0.022
 elevator-0.022
ases-0.022
ays-0.021
Token theater
Token ID13766
Feature activation+9.01e-03

Pos logit contributions
 Ho+0.025
 Rib+0.024
 H+0.023
 Bub+0.021
 Tw+0.021
Neg logit contributions
agged-0.014
eks-0.014
ays-0.014
oos-0.014
ases-0.014
Token again
Token ID757
Feature activation-3.61e-02

Pos logit contributions
agged+0.017
eks+0.017
ays+0.016
oos+0.016
ases+0.016
Neg logit contributions
 Ho-0.013
 Rib-0.012
 H-0.012
 Tw-0.010
 Bun-0.010
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
 Ho+0.075
 Rib+0.074
 H+0.065
 Bub+0.064
 Bun+0.062
Neg logit contributions
oos-0.044
eks-0.043
he-0.042
ases-0.042
 elevator-0.041
Token They
Token ID1119
Feature activation+4.37e-02

Pos logit contributions
 Ho+0.028
 Rib+0.027
 accidentally+0.025
please+0.025
 H+0.025
Neg logit contributions
ays-0.013
oos-0.012
cases-0.011
ases-0.011
he-0.011
Token never
Token ID1239
Feature activation+1.27e-02

Pos logit contributions
oos+0.075
eks+0.074
ays+0.074
agged+0.073
ases+0.073
Neg logit contributions
 Ho-0.070
 Rib-0.067
 H-0.061
 Bub-0.056
 Bun-0.055
Token missed
Token ID6825
Feature activation+1.92e-02

Pos logit contributions
eks+0.021
oos+0.021
ases+0.020
cases+0.020
 elevator+0.020
Neg logit contributions
 Ho-0.021
 Rib-0.020
 H-0.018
 Bub-0.017
 Bun-0.017
Token one
Token ID530
Feature activation+6.54e-02

Pos logit contributions
eks+0.031
oos+0.031
ays+0.030
 elevator+0.030
cases+0.030
Neg logit contributions
 Ho-0.033
 Rib-0.032
 H-0.029
 Bub-0.026
 Bun-0.026
Token show
Token ID905
Feature activation+2.16e-03

Pos logit contributions
eks+0.108
oos+0.107
ays+0.105
cases+0.104
agged+0.104
Neg logit contributions
 Ho-0.109
 Rib-0.107
 H-0.095
 Bub-0.088
 Bun-0.087
Token!
Token ID0
Feature activation+3.28e-02

Pos logit contributions
eks+0.003
oos+0.003
ays+0.003
cases+0.003
 elevator+0.003
Neg logit contributions
 Ho-0.004
 Rib-0.004
 H-0.003
 Bub-0.003
 Bun-0.003
Token to
Token ID284
Feature activation-3.13e-03

Pos logit contributions
oos+0.071
ays+0.070
ases+0.069
eks+0.069
agged+0.068
Neg logit contributions
 Ho-0.070
 Rib-0.065
 H-0.064
 Bun-0.058
 Bub-0.057
Token the
Token ID262
Feature activation+1.40e-02

Pos logit contributions
 Rib+0.006
 Ho+0.006
Ros+0.005
 Bub+0.005
 H+0.005
Neg logit contributions
 elevator-0.004
 tickets-0.004
eks-0.004
oos-0.004
ases-0.004
Token beach
Token ID10481
Feature activation+3.99e-02

Pos logit contributions
 elevator+0.015
oos+0.013
 tickets+0.012
 lobby+0.012
out+0.012
Neg logit contributions
 Rib-0.032
 Ho-0.031
 H-0.028
 Bub-0.028
 Bun-0.027
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
eks+0.076
agged+0.074
ases+0.072
ays+0.071
oos+0.071
Neg logit contributions
 Ho-0.059
 Rib-0.057
 H-0.051
 Bun-0.045
 Bub-0.045
Token One
Token ID1881
Feature activation+6.13e-02

Pos logit contributions
 elevator+0.013
ays+0.013
he+0.013
 downtown+0.012
oos+0.012
Neg logit contributions
 Rib-0.026
 Ho-0.026
onna-0.023
 accidentally-0.022
 fle-0.022
Token day
Token ID1110
Feature activation+1.38e-02

Pos logit contributions
eks+0.120
ases+0.118
oos+0.118
agged+0.117
cases+0.117
Neg logit contributions
 Ho-0.084
 Rib-0.083
 H-0.073
 Bub-0.066
 Butter-0.064
Token,
Token ID11
Feature activation+6.69e-03

Pos logit contributions
oos+0.015
 elevator+0.014
cases+0.014
eks+0.014
led+0.014
Neg logit contributions
 Rib-0.030
 Ho-0.029
 H-0.026
 Bub-0.025
 Butter-0.025
Token he
Token ID339
Feature activation+9.93e-03

Pos logit contributions
 elevator+0.010
cases+0.009
he+0.009
oos+0.009
 downtown+0.009
Neg logit contributions
 Rib-0.012
 Ho-0.011
onna-0.010
 Tw-0.009
 H-0.009
Token saw
Token ID2497
Feature activation+6.39e-02

Pos logit contributions
eks+0.015
oos+0.015
ays+0.015
cases+0.015
 elevator+0.015
Neg logit contributions
 Ho-0.018
 Rib-0.017
 H-0.015
 Bub-0.014
 Bun-0.014
Token a
Token ID257
Feature activation-3.58e-03

Pos logit contributions
eks+0.100
oos+0.100
ays+0.097
cases+0.097
ases+0.097
Neg logit contributions
 Ho-0.112
 Rib-0.109
 H-0.099
 Bub-0.091
 Bun-0.090
Token big
Token ID1263
Feature activation+7.64e-02

Pos logit contributions
 Rib+0.008
 Ho+0.007
 H+0.007
 Bub+0.006
 Bun+0.006
Neg logit contributions
 elevator-0.004
he-0.004
 lobby-0.004
eks-0.004
 tickets-0.004
Token it
Token ID340
Feature activation+1.37e-02

Pos logit contributions
 elevator+0.017
eks+0.017
led+0.017
cases+0.016
oos+0.016
Neg logit contributions
 Rib-0.017
 Ho-0.016
 H-0.013
onna-0.013
please-0.013
Token wouldn
Token ID3636
Feature activation-9.85e-02

Pos logit contributions
eks+0.020
led+0.020
 elevator+0.019
oos+0.019
cases+0.019
Neg logit contributions
 Rib-0.025
 Ho-0.024
 H-0.021
 Bub-0.020
 Butter-0.019
Token't
Token ID470
Feature activation-1.50e-02

Pos logit contributions
 Ho+0.174
 Rib+0.170
 H+0.154
 Bub+0.142
 Bun+0.142
Neg logit contributions
oos-0.151
eks-0.151
ays-0.146
 elevator-0.146
cases-0.146
Token bud
Token ID3600
Feature activation-5.37e-02

Pos logit contributions
 Ho+0.029
 Rib+0.028
 H+0.026
 Bun+0.024
 Bub+0.024
Neg logit contributions
oos-0.021
eks-0.021
ays-0.020
ases-0.020
agged-0.020
Tokenge
Token ID469
Feature activation-3.05e-02

Pos logit contributions
 Ho+0.095
 Rib+0.094
 H+0.081
 Bub+0.077
 Butter+0.077
Neg logit contributions
cases-0.082
eks-0.082
oos-0.081
ays-0.081
ases-0.079
Token.
Token ID13
Feature activation+5.41e-03

Pos logit contributions
 Ho+0.052
 Rib+0.049
 H+0.046
 Bun+0.042
 Bub+0.041
Neg logit contributions
eks-0.050
oos-0.049
ays-0.048
agged-0.048
 elevator-0.048
Token Then
Token ID3244
Feature activation-7.72e-02

Pos logit contributions
oos+0.007
cases+0.007
agged+0.007
 elevator+0.007
ued+0.007
Neg logit contributions
 Rib-0.009
 Ho-0.008
onna-0.008
please-0.008
 Tooth-0.008
Token,
Token ID11
Feature activation-4.22e-04

Pos logit contributions
 Rib+0.172
 Ho+0.164
onna+0.150
 H+0.146
 Butter+0.142
Neg logit contributions
eks-0.078
oos-0.073
led-0.073
 elevator-0.072
cases-0.070
Token Bun
Token ID28515
Feature activation-7.75e-02

Pos logit contributions
 Rib+0.001
onna+0.001
 Ho+0.001
please+0.001
die+0.001
Neg logit contributions
eks-0.001
led-0.001
 elevator-0.001
cases-0.001
ued-0.001
Token remembered
Token ID12086
Feature activation-4.30e-02

Pos logit contributions
 Rib+0.145
onna+0.132
 Ho+0.126
 Butter+0.126
Pract+0.117
Neg logit contributions
led-0.112
eks-0.096
ed-0.094
out-0.093
hed-0.093
Token that
Token ID326
Feature activation-5.69e-03

Pos logit contributions
 Rib+0.094
 Ho+0.091
 H+0.079
 Butter+0.079
 Bub+0.078
Neg logit contributions
eks-0.045
oos-0.045
 elevator-0.044
out-0.043
cases-0.040
Token and
Token ID290
Feature activation+8.56e-03

Pos logit contributions
eks+0.002
ases+0.002
 elevator+0.002
oos+0.002
agged+0.002
Neg logit contributions
 Ho-0.003
 Rib-0.002
 H-0.002
 Bun-0.002
 Bub-0.002
Token move
Token ID1445
Feature activation-7.55e-03

Pos logit contributions
eks+0.011
oos+0.010
 are+0.010
 elevator+0.010
cases+0.010
Neg logit contributions
 Ho-0.017
 Rib-0.016
 H-0.015
 Tooth-0.014
 Stri-0.014
Token in
Token ID287
Feature activation-2.09e-02

Pos logit contributions
 Ho+0.014
 Rib+0.014
 H+0.013
 Bub+0.012
 Bun+0.012
Neg logit contributions
oos-0.010
eks-0.010
ays-0.010
 elevator-0.010
cases-0.010
Token circles
Token ID13332
Feature activation+1.14e-02

Pos logit contributions
 Ho+0.032
 Rib+0.031
 H+0.029
 Bun+0.026
 Bub+0.026
Neg logit contributions
eks-0.037
cases-0.037
oos-0.036
agged-0.036
ays-0.036
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
eks+0.018
oos+0.017
ays+0.017
ases+0.017
 elevator+0.017
Neg logit contributions
 Ho-0.020
 Rib-0.019
 H-0.017
 Bun-0.016
 Bub-0.016
Token Stella
Token ID45856
Feature activation-1.64e-02

Pos logit contributions
 Rib+0.021
 Ho+0.021
 H+0.019
 Stri+0.018
 Fro+0.017
Neg logit contributions
oos-0.017
cases-0.017
agged-0.017
ays-0.016
hed-0.016
Token followed
Token ID3940
Feature activation+3.46e-02

Pos logit contributions
 Rib+0.031
 Ho+0.031
 H+0.028
 Bub+0.027
 Butter+0.026
Neg logit contributions
hed-0.022
led-0.022
eks-0.021
cases-0.021
oos-0.021
Token her
Token ID607
Feature activation-2.20e-02

Pos logit contributions
oos+0.051
eks+0.050
 elevator+0.049
he+0.048
cases+0.048
Neg logit contributions
 Rib-0.062
 Ho-0.062
 H-0.055
 Bub-0.051
 Stri-0.050
Token mom
Token ID1995
Feature activation+5.53e-02

Pos logit contributions
 Rib+0.040
 Ho+0.039
 H+0.034
 Bub+0.033
 Butter+0.033
Neg logit contributions
 elevator-0.032
oos-0.032
cases-0.032
eks-0.031
ases-0.031
Token's
Token ID338
Feature activation-4.83e-02

Pos logit contributions
oos+0.064
cases+0.063
eks+0.062
 elevator+0.062
out+0.060
Neg logit contributions
 Rib-0.118
 Ho-0.116
 H-0.104
 Bub-0.101
 Butter-0.098
Token lead
Token ID1085
Feature activation+3.07e-02

Pos logit contributions
 Ho+0.097
 Rib+0.094
 H+0.086
 Bub+0.080
 Bun+0.080
Neg logit contributions
eks-0.064
oos-0.064
ays-0.062
cases-0.062
ases-0.061
Token against
Token ID1028
Feature activation+2.23e-02

Pos logit contributions
 Ho+0.020
 Rib+0.019
 H+0.017
 Bub+0.016
 Bun+0.016
Neg logit contributions
oos-0.016
eks-0.015
cases-0.015
ays-0.015
 elevator-0.015
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
oos+0.032
eks+0.031
 elevator+0.031
ases+0.030
he+0.030
Neg logit contributions
 Ho-0.041
 Rib-0.040
 H-0.036
 Bub-0.034
 Bun-0.033
Token fat
Token ID3735
Feature activation-1.47e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.025
 Stri+0.022
 Bub+0.022
Neg logit contributions
 elevator-0.029
oos-0.028
eks-0.027
ases-0.027
ps-0.027
Token frog
Token ID21264
Feature activation-5.58e-02

Pos logit contributions
 Ho+0.021
 Rib+0.020
 H+0.018
 Bun+0.016
 Bub+0.016
Neg logit contributions
oos-0.027
 elevator-0.026
ases-0.026
eks-0.026
agged-0.026
Tokenâ
Token ID22940
Feature activation+1.16e-02

Pos logit contributions
 Ho+0.110
 Rib+0.109
 H+0.101
 Bub+0.094
 Bun+0.091
Neg logit contributions
oos-0.071
cases-0.070
 elevator-0.068
eks-0.067
he-0.067
Token
Token ID26391
Feature activation-8.61e-02

Pos logit contributions
oos+0.017
eks+0.017
agged+0.016
ases+0.016
 elevator+0.016
Neg logit contributions
 Ho-0.022
 Rib-0.021
 H-0.019
 Bub-0.018
 Bun-0.018
Token
Token ID8151
Feature activation+9.57e-03

Pos logit contributions
 Ho+0.149
 Rib+0.146
 H+0.131
 Bub+0.124
 Bun+0.118
Neg logit contributions
oos-0.136
eks-0.132
cases-0.132
ays-0.131
ases-0.128
Tokens
Token ID82
Feature activation-2.48e-02

Pos logit contributions
oos+0.013
eks+0.013
ays+0.013
cases+0.013
 elevator+0.013
Neg logit contributions
 Ho-0.018
 Rib-0.018
 H-0.016
 Bub-0.015
 Bun-0.015
Token shell
Token ID7582
Feature activation-8.88e-03

Pos logit contributions
 Ho+0.046
 Rib+0.046
 H+0.041
 Bub+0.039
 Bun+0.038
Neg logit contributions
oos-0.035
eks-0.035
cases-0.034
ases-0.034
ays-0.034
Token.
Token ID13
Feature activation-2.52e-03

Pos logit contributions
 Ho+0.017
 Rib+0.016
 H+0.015
 Bub+0.014
 Bun+0.014
Neg logit contributions
oos-0.013
eks-0.013
cases-0.012
ays-0.012
 elevator-0.012
Token The
Token ID383
Feature activation-7.06e-03

Pos logit contributions
 Rib+0.005
 Ho+0.005
 accidentally+0.004
 Tw+0.004
Ros+0.004
Neg logit contributions
he-0.003
hed-0.003
ays-0.003
cases-0.003
agged-0.003
Token himself
Token ID2241
Feature activation+2.63e-02

Pos logit contributions
oos+0.073
 elevator+0.072
eks+0.072
he+0.069
ases+0.069
Neg logit contributions
 Rib-0.109
 Ho-0.109
 H-0.095
 Butter-0.090
 Bub-0.088
Token in
Token ID287
Feature activation-1.96e-02

Pos logit contributions
cases+0.030
he+0.028
oos+0.028
 elevator+0.028
ays+0.028
Neg logit contributions
 Ho-0.056
 Rib-0.056
 H-0.050
 Bub-0.048
 Butter-0.048
Token the
Token ID262
Feature activation-1.02e-02

Pos logit contributions
 Ho+0.034
 Rib+0.033
 H+0.030
 Bub+0.027
 Bun+0.027
Neg logit contributions
oos-0.031
eks-0.031
cases-0.031
ays-0.031
agged-0.030
Token mirror
Token ID10162
Feature activation-5.72e-02

Pos logit contributions
 Rib+0.020
 Ho+0.020
 H+0.018
 Bub+0.018
 Bun+0.017
Neg logit contributions
 elevator-0.014
oos-0.013
eks-0.013
he-0.012
ags-0.012
Token.
Token ID13
Feature activation-4.50e-03

Pos logit contributions
 Ho+0.111
 Rib+0.108
 H+0.098
 Bub+0.093
 Bun+0.092
Neg logit contributions
oos-0.078
cases-0.078
eks-0.077
 elevator-0.077
ays-0.076
Token
Token ID198
Feature activation-2.03e-02

Pos logit contributions
 Rib+0.008
 Ho+0.008
 fle+0.007
 Tw+0.007
onna+0.007
Neg logit contributions
ays-0.006
oos-0.006
hed-0.006
he-0.006
cases-0.006
Token
Token ID198
Feature activation-2.21e-02

Pos logit contributions
 Ho+0.033
 Rib+0.033
 H+0.028
 Butter+0.027
 fle+0.025
Neg logit contributions
he-0.038
oos-0.033
hed-0.032
eks-0.032
agged-0.032
TokenHis
Token ID6653
Feature activation+4.52e-02

Pos logit contributions
 Ho+0.036
 Rib+0.035
 H+0.031
 Bub+0.028
 Butter+0.028
Neg logit contributions
oos-0.038
he-0.038
eks-0.037
cases-0.037
 elevator-0.036
Token Mom
Token ID11254
Feature activation+7.47e-02

Pos logit contributions
 elevator+0.065
 tickets+0.060
 bags+0.057
oos+0.057
eks+0.057
Neg logit contributions
 Rib-0.088
 Ho-0.084
 H-0.076
 Butter-0.075
 Bub-0.074
Tokenmy
Token ID1820
Feature activation-3.18e-02

Pos logit contributions
eks+0.106
hed+0.106
he+0.104
 elevator+0.104
oos+0.104
Neg logit contributions
 Rib-0.139
 Ho-0.138
 H-0.119
 Butter-0.115
 Bub-0.114
Token thought
Token ID1807
Feature activation+4.97e-02

Pos logit contributions
 Rib+0.059
 Ho+0.058
 H+0.051
 Butter+0.049
 Bub+0.048
Neg logit contributions
hed-0.044
cases-0.044
eks-0.044
led-0.043
oos-0.043
Token She
Token ID1375
Feature activation-1.36e-02

Pos logit contributions
 Ho+0.016
 Rib+0.016
 H+0.014
 Bub+0.013
 Bun+0.013
Neg logit contributions
 elevator-0.015
oos-0.014
ays-0.014
cases-0.014
eks-0.014
Token saw
Token ID2497
Feature activation+5.06e-02

Pos logit contributions
 Ho+0.027
 Rib+0.027
 H+0.024
 Bun+0.023
 Bub+0.023
Neg logit contributions
eks-0.018
 elevator-0.017
oos-0.017
cases-0.017
led-0.017
Token the
Token ID262
Feature activation-1.64e-02

Pos logit contributions
agged+0.108
eks+0.106
oos+0.105
ags+0.102
cases+0.101
Neg logit contributions
 Ho-0.067
 Rib-0.061
 H-0.056
 Bub-0.052
 Teddy-0.051
Token dough
Token ID15756
Feature activation-8.63e-02

Pos logit contributions
 Ho+0.031
 Rib+0.030
 H+0.027
 Bub+0.025
 accidentally+0.025
Neg logit contributions
eks-0.024
oos-0.023
cases-0.023
ases-0.023
agged-0.022
Token on
Token ID319
Feature activation+8.73e-05

Pos logit contributions
 Ho+0.133
 Rib+0.129
 H+0.110
 accidentally+0.109
 Lucky+0.106
Neg logit contributions
eks-0.152
agged-0.151
oos-0.147
cases-0.145
ases-0.141
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
oos+0.000
 elevator+0.000
eks+0.000
ays+0.000
ases+0.000
Neg logit contributions
 Ho-0.000
 Rib-0.000
 H-0.000
 Bub-0.000
 Bun-0.000
Token table
Token ID3084
Feature activation+2.14e-02

Pos logit contributions
 Ho+0.029
 Rib+0.028
 H+0.025
 Bub+0.024
 Bun+0.024
Neg logit contributions
eks-0.024
oos-0.023
agged-0.023
ays-0.023
ases-0.023
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
eks+0.045
agged+0.043
oos+0.042
ued+0.041
ases+0.040
Neg logit contributions
 Ho-0.024
 Rib-0.023
 accidentally-0.021
 H-0.021
 Tw-0.018
Token She
Token ID1375
Feature activation-1.52e-02

Pos logit contributions
 Ho+0.021
 Rib+0.021
 H+0.018
 Bun+0.017
 Bub+0.017
Neg logit contributions
 elevator-0.017
ays-0.017
oos-0.017
cases-0.017
he-0.016
Token saw
Token ID2497
Feature activation+5.02e-02

Pos logit contributions
 Ho+0.026
 Rib+0.026
 H+0.023
 Bun+0.021
 Bub+0.021
Neg logit contributions
eks-0.024
 elevator-0.024
oos-0.023
cases-0.023
led-0.023
Token Lily
Token ID20037
Feature activation-4.58e-02

Pos logit contributions
agged+0.105
eks+0.104
oos+0.103
ags+0.100
cases+0.099
Neg logit contributions
 Ho-0.067
 Rib-0.062
 H-0.057
 Bub-0.052
 Teddy-0.051
Token
Token ID198
Feature activation-1.63e-02

Pos logit contributions
 Rib+0.003
 Ho+0.003
 H+0.003
 accidentally+0.003
 Po+0.003
Neg logit contributions
he-0.003
oos-0.003
 elevator-0.003
cases-0.003
hed-0.003
Token
Token ID198
Feature activation-1.72e-02

Pos logit contributions
 Rib+0.024
 Ho+0.024
 H+0.020
 Butter+0.019
 Po+0.018
Neg logit contributions
he-0.032
eks-0.029
oos-0.028
hed-0.028
cases-0.028
TokenThe
Token ID464
Feature activation-1.02e-02

Pos logit contributions
 Ho+0.025
 Rib+0.024
 H+0.021
 Bub+0.019
 Bun+0.019
Neg logit contributions
eks-0.032
oos-0.032
cases-0.031
 elevator-0.031
ases-0.031
Token people
Token ID661
Feature activation+2.98e-02

Pos logit contributions
 Ho+0.016
 Rib+0.014
 H+0.014
 Bub+0.013
 Bun+0.013
Neg logit contributions
ays-0.019
oos-0.018
ases-0.018
cases-0.017
eks-0.017
Token of
Token ID286
Feature activation-4.28e-02

Pos logit contributions
oos+0.051
ays+0.051
ags+0.051
agged+0.049
ases+0.048
Neg logit contributions
 Ho-0.046
 Rib-0.043
 H-0.042
 accidentally-0.042
 Bub-0.040
Token the
Token ID262
Feature activation-1.05e-02

Pos logit contributions
 Ho+0.063
 Rib+0.060
 H+0.054
 Bub+0.050
 Bun+0.049
Neg logit contributions
cases-0.082
ays-0.080
oos-0.079
eks-0.078
agged-0.077
Token city
Token ID1748
Feature activation+7.84e-02

Pos logit contributions
 Ho+0.017
 H+0.015
 Rib+0.015
 Bun+0.014
 accidentally+0.014
Neg logit contributions
ays-0.019
oos-0.018
ases-0.018
agged-0.017
eks-0.017
Token cheered
Token ID34767
Feature activation+4.00e-02

Pos logit contributions
ags+0.145
agged+0.143
ays+0.143
ases+0.143
eks+0.143
Neg logit contributions
 Ho-0.108
 Rib-0.104
 accidentally-0.098
 H-0.098
 Bub-0.091
Token and
Token ID290
Feature activation+1.19e-02

Pos logit contributions
eks+0.069
oos+0.067
agged+0.067
ays+0.067
 elevator+0.067
Neg logit contributions
 Ho-0.065
 Rib-0.062
 H-0.058
 Bun-0.053
 Bub-0.052
Token cl
Token ID537
Feature activation-2.76e-02

Pos logit contributions
eks+0.018
oos+0.018
 elevator+0.017
cases+0.017
ases+0.017
Neg logit contributions
 Ho-0.021
 Rib-0.021
 H-0.019
 Bun-0.017
 Butter-0.017
Tokenapped
Token ID6320
Feature activation+5.24e-02

Pos logit contributions
 Rib+0.053
 Ho+0.051
 H+0.048
 Bub+0.046
 Fro+0.042
Neg logit contributions
 elevator-0.041
eks-0.039
roads-0.037
cases-0.037
 tickets-0.036
Token messy
Token ID24097
Feature activation+9.01e-03

Pos logit contributions
 Ho+0.035
 Rib+0.034
 H+0.032
 Bun+0.031
 Bub+0.030
Neg logit contributions
 elevator-0.022
cases-0.020
eks-0.020
he-0.020
ays-0.020
Token pile
Token ID14540
Feature activation-1.64e-03

Pos logit contributions
eks+0.013
cases+0.013
oos+0.013
ases+0.013
ays+0.013
Neg logit contributions
 Ho-0.016
 Rib-0.016
 H-0.014
 accidentally-0.014
 Bub-0.013
Token of
Token ID286
Feature activation-4.43e-02

Pos logit contributions
 Rib+0.003
 Ho+0.003
 H+0.002
 Po+0.002
 Tw+0.002
Neg logit contributions
eks-0.003
oos-0.003
agged-0.003
cases-0.003
ags-0.002
Token flour
Token ID10601
Feature activation-6.66e-02

Pos logit contributions
 Ho+0.090
 Rib+0.088
 H+0.080
 Bub+0.076
 Butter+0.075
Neg logit contributions
eks-0.056
oos-0.056
cases-0.054
ays-0.054
agged-0.054
Token and
Token ID290
Feature activation+4.70e-03

Pos logit contributions
 Ho+0.099
 Rib+0.095
 H+0.080
 accidentally+0.074
 Butter+0.073
Neg logit contributions
eks-0.125
agged-0.120
oos-0.120
ases-0.116
ags-0.112
Token sugar
Token ID7543
Feature activation-1.37e-01

Pos logit contributions
oos+0.007
eks+0.007
 elevator+0.006
cases+0.006
ays+0.006
Neg logit contributions
 Ho-0.009
 Rib-0.009
 H-0.008
 Bun-0.007
 Bub-0.007
Token.
Token ID13
Feature activation-1.45e-02

Pos logit contributions
 Ho+0.233
 Rib+0.225
 H+0.197
 Bub+0.183
 Butter+0.181
Neg logit contributions
eks-0.224
oos-0.217
agged-0.214
ases-0.212
 elevator-0.209
Token "
Token ID366
Feature activation+1.02e-03

Pos logit contributions
 Rib+0.026
 Ho+0.025
 Tooth+0.022
 Bun+0.022
please+0.022
Neg logit contributions
ays-0.019
oos-0.017
ases-0.016
agged-0.016
ags-0.015
TokenDo
Token ID5211
Feature activation-1.04e-01

Pos logit contributions
eks+0.002
oos+0.002
ases+0.002
 elevator+0.002
ays+0.002
Neg logit contributions
 Ho-0.002
 Rib-0.002
 H-0.001
 Bub-0.001
 Bun-0.001
Token you
Token ID345
Feature activation-1.79e-02

Pos logit contributions
 Ho+0.182
 Rib+0.179
 H+0.161
 Bun+0.150
 Bub+0.150
Neg logit contributions
eks-0.158
 elevator-0.155
oos-0.153
cases-0.151
ases-0.150
Token want
Token ID765
Feature activation+6.98e-02

Pos logit contributions
 Ho+0.039
 Rib+0.038
 H+0.035
 Bun+0.033
 Bub+0.033
Neg logit contributions
eks-0.021
oos-0.021
ases-0.020
 elevator-0.020
ays-0.020
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
 Ho+0.071
 Rib+0.070
 H+0.064
 Bun+0.059
 Bub+0.059
Neg logit contributions
oos-0.055
eks-0.054
ays-0.053
cases-0.053
ases-0.053
Token They
Token ID1119
Feature activation+5.94e-02

Pos logit contributions
oos+0.018
 elevator+0.017
cases+0.017
ays+0.017
agged+0.016
Neg logit contributions
 Rib-0.020
 Ho-0.019
 H-0.016
 Fro-0.016
 Stri-0.016
Token also
Token ID635
Feature activation-6.62e-02

Pos logit contributions
oos+0.076
eks+0.075
ays+0.074
ases+0.073
agged+0.073
Neg logit contributions
 Ho-0.122
 Rib-0.118
 H-0.108
 Bub-0.102
 Bun-0.101
Token got
Token ID1392
Feature activation+1.96e-02

Pos logit contributions
 Ho+0.110
 Rib+0.107
 H+0.096
 Bub+0.088
 accidentally+0.088
Neg logit contributions
oos-0.110
eks-0.109
ays-0.107
cases-0.107
agged-0.107
Token some
Token ID617
Feature activation+8.11e-02

Pos logit contributions
eks+0.027
oos+0.026
 elevator+0.026
ays+0.026
ases+0.025
Neg logit contributions
 Ho-0.038
 Rib-0.037
 H-0.034
 Bun-0.032
 Bub-0.032
Token milk
Token ID7545
Feature activation-1.14e-01

Pos logit contributions
eks+0.137
oos+0.132
ays+0.130
cases+0.128
ases+0.128
Neg logit contributions
 Ho-0.136
 Rib-0.130
 H-0.114
 Bub-0.110
 Butter-0.108
Token and
Token ID290
Feature activation+1.86e-02

Pos logit contributions
 Ho+0.190
 Rib+0.179
 H+0.160
 Lucky+0.150
 Bub+0.149
Neg logit contributions
eks-0.202
oos-0.191
agged-0.191
ases-0.188
 elevator-0.186
Token bread
Token ID8509
Feature activation-5.21e-02

Pos logit contributions
oos+0.025
 elevator+0.025
eks+0.025
cases+0.025
led+0.024
Neg logit contributions
 Ho-0.035
 Rib-0.035
 H-0.032
 Bub-0.029
 Bun-0.029
Token.
Token ID13
Feature activation+9.40e-03

Pos logit contributions
 Ho+0.093
 Rib+0.091
 H+0.082
 Bub+0.077
 Bun+0.076
Neg logit contributions
eks-0.079
oos-0.078
 elevator-0.076
ays-0.076
cases-0.076
Token
Token ID198
Feature activation-7.39e-03

Pos logit contributions
oos+0.015
ays+0.015
cases+0.014
 elevator+0.014
hed+0.014
Neg logit contributions
 Rib-0.016
 Ho-0.015
 Fro-0.013
 H-0.013
 Stri-0.013
Token
Token ID198
Feature activation-8.10e-03

Pos logit contributions
 Rib+0.012
 Ho+0.012
 H+0.010
 Butter+0.009
 fle+0.009
Neg logit contributions
he-0.014
cases-0.012
oos-0.012
eks-0.011
hed-0.011
Token cl
Token ID537
Feature activation-3.34e-02

Pos logit contributions
oos+0.121
ays+0.121
ags+0.120
eks+0.120
agged+0.119
Neg logit contributions
 Ho-0.075
 Rib-0.073
 H-0.062
 accidentally-0.058
 Bun-0.058
Tokenapped
Token ID6320
Feature activation+5.25e-02

Pos logit contributions
 Rib+0.068
 Ho+0.067
 H+0.061
 Bub+0.057
 Lucky+0.056
Neg logit contributions
 elevator-0.044
cases-0.041
eks-0.040
 tickets-0.039
roads-0.039
Token as
Token ID355
Feature activation-2.84e-02

Pos logit contributions
eks+0.080
oos+0.079
ays+0.078
cases+0.077
 elevator+0.077
Neg logit contributions
 Ho-0.094
 Rib-0.092
 H-0.083
 Bub-0.077
 Bun-0.076
Token the
Token ID262
Feature activation-1.14e-02

Pos logit contributions
 Ho+0.053
 Rib+0.052
 H+0.046
Ros+0.044
 Bub+0.043
Neg logit contributions
 elevator-0.038
he-0.035
cases-0.035
led-0.035
oos-0.035
Token cow
Token ID9875
Feature activation-7.25e-02

Pos logit contributions
 Ho+0.020
 Rib+0.020
 H+0.018
 Bub+0.017
 Bun+0.017
Neg logit contributions
eks-0.017
oos-0.017
 elevator-0.017
cases-0.017
ays-0.017
Token gently
Token ID15165
Feature activation-1.12e-01

Pos logit contributions
 Ho+0.124
 Rib+0.122
 H+0.110
 Bub+0.101
 Bun+0.100
Neg logit contributions
oos-0.113
eks-0.113
cases-0.111
 elevator-0.109
ays-0.109
Token carried
Token ID5281
Feature activation-1.37e-02

Pos logit contributions
 Ho+0.192
 Rib+0.188
 H+0.169
 Bub+0.156
 Bun+0.154
Neg logit contributions
oos-0.176
eks-0.175
cases-0.171
ays-0.170
 elevator-0.170
Token the
Token ID262
Feature activation-1.17e-02

Pos logit contributions
 Ho+0.025
 Rib+0.025
 H+0.023
 Bub+0.021
 accidentally+0.021
Neg logit contributions
oos-0.020
eks-0.019
 elevator-0.019
ases-0.019
cases-0.018
Token sheep
Token ID15900
Feature activation-3.47e-02

Pos logit contributions
 Ho+0.022
 Rib+0.021
 H+0.019
 Bub+0.018
 Bun+0.018
Neg logit contributions
 elevator-0.017
oos-0.017
eks-0.017
cases-0.016
he-0.016
Token to
Token ID284
Feature activation-1.87e-02

Pos logit contributions
 Ho+0.060
 Rib+0.057
 H+0.052
 Bun+0.049
 Bub+0.048
Neg logit contributions
eks-0.056
agged-0.055
oos-0.055
ays-0.054
ases-0.053
Token safety
Token ID3747
Feature activation+1.81e-03

Pos logit contributions
 Ho+0.035
 Rib+0.035
 H+0.031
 Bub+0.029
 accidentally+0.029
Neg logit contributions
eks-0.025
oos-0.025
 elevator-0.025
ases-0.024
he-0.024
Token like
Token ID588
Feature activation-4.87e-03

Pos logit contributions
 Ho+0.019
 Rib+0.019
Ros+0.017
 H+0.016
 Bub+0.016
Neg logit contributions
eks-0.011
ps-0.010
out-0.010
led-0.010
 elevator-0.010
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
 Rib+0.009
 Ho+0.009
 H+0.008
 Bub+0.007
Ros+0.007
Neg logit contributions
 elevator-0.007
oos-0.007
eks-0.006
ases-0.006
ays-0.006
Token butterfly
Token ID35113
Feature activation-5.03e-02

Pos logit contributions
 Ho+0.020
 Rib+0.019
 H+0.017
 Bub+0.016
 Bun+0.016
Neg logit contributions
eks-0.021
 elevator-0.021
oos-0.021
ays-0.020
he-0.020
Token and
Token ID290
Feature activation+9.63e-03

Pos logit contributions
 Ho+0.097
 Rib+0.096
 H+0.086
 Bub+0.081
 Stri+0.078
Neg logit contributions
oos-0.066
eks-0.065
 elevator-0.064
ays-0.064
cases-0.064
Token she
Token ID673
Feature activation-4.04e-02

Pos logit contributions
eks+0.017
oos+0.017
 elevator+0.016
ays+0.016
cases+0.016
Neg logit contributions
 Ho-0.015
 Rib-0.015
 H-0.013
 Bub-0.012
 Bun-0.012
Token can
Token ID460
Feature activation-1.04e-01

Pos logit contributions
 Ho+0.065
 Rib+0.064
 H+0.056
 Bub+0.053
 Bun+0.050
Neg logit contributions
eks-0.069
oos-0.067
led-0.067
cases-0.066
ays-0.066
Token't
Token ID470
Feature activation-1.73e-02

Pos logit contributions
 Ho+0.179
 Rib+0.175
 H+0.157
 Bub+0.145
 Bun+0.143
Neg logit contributions
eks-0.162
oos-0.160
ases-0.156
he-0.155
 elevator-0.154
Token fly
Token ID6129
Feature activation-6.71e-02

Pos logit contributions
 Ho+0.033
 Rib+0.032
 H+0.028
 Bub+0.026
 Stri+0.026
Neg logit contributions
eks-0.025
he-0.024
oos-0.024
ases-0.023
 elevator-0.023
Token away
Token ID1497
Feature activation+3.40e-02

Pos logit contributions
 Ho+0.132
 Rib+0.130
 H+0.117
 Bub+0.110
 Bun+0.108
Neg logit contributions
eks-0.089
oos-0.089
ases-0.085
ays-0.085
 elevator-0.084
Token whenever
Token ID8797
Feature activation-1.56e-02

Pos logit contributions
eks+0.052
oos+0.052
ays+0.051
cases+0.050
 elevator+0.050
Neg logit contributions
 Ho-0.060
 Rib-0.059
 H-0.053
 Bub-0.049
 Bun-0.049
Token she
Token ID673
Feature activation-3.80e-02

Pos logit contributions
 Ho+0.025
 Rib+0.025
 H+0.021
 Stri+0.021
 Bub+0.020
Neg logit contributions
oos-0.024
 elevator-0.024
eks-0.023
 are-0.022
led-0.022
Token skirt
Token ID23967
Feature activation-1.31e-02

Pos logit contributions
 Rib+0.070
 Ho+0.069
 H+0.061
 Bub+0.057
 Butter+0.056
Neg logit contributions
oos-0.067
eks-0.066
 elevator-0.066
cases-0.064
ays-0.064
Token is
Token ID318
Feature activation+2.19e-02

Pos logit contributions
 Ho+0.024
 Rib+0.022
 H+0.021
 accidentally+0.020
 Bun+0.020
Neg logit contributions
agged-0.020
oos-0.019
eks-0.019
ags-0.019
ases-0.018
Token broken
Token ID5445
Feature activation-1.92e-02

Pos logit contributions
 elevator+0.025
eks+0.025
ays+0.024
oos+0.023
ps+0.023
Neg logit contributions
 Rib-0.046
 Ho-0.045
 H-0.040
 Bub-0.038
 Stri-0.038
Token.
Token ID13
Feature activation-3.80e-03

Pos logit contributions
 Ho+0.035
 Rib+0.034
 H+0.031
 Bun+0.029
 Bub+0.028
Neg logit contributions
eks-0.029
oos-0.029
cases-0.028
agged-0.028
ases-0.028
Token What
Token ID1867
Feature activation-4.27e-04

Pos logit contributions
 Rib+0.007
 Ho+0.007
 Fro+0.006
 accidentally+0.006
 Bub+0.006
Neg logit contributions
ays-0.005
 elevator-0.005
ases-0.005
cases-0.005
oos-0.005
Token can
Token ID460
Feature activation-1.04e-01

Pos logit contributions
 Ho+0.001
 Rib+0.001
 H+0.001
 Bub+0.001
 Bun+0.001
Neg logit contributions
eks-0.001
oos-0.001
 elevator-0.001
ases-0.001
ays-0.001
Token I
Token ID314
Feature activation-3.23e-02

Pos logit contributions
 Ho+0.140
 Rib+0.136
 H+0.118
 Bub+0.106
 Bun+0.105
Neg logit contributions
eks-0.202
oos-0.202
ays-0.197
 elevator-0.197
cases-0.197
Token do
Token ID466
Feature activation-5.11e-02

Pos logit contributions
 Ho+0.062
 Rib+0.062
 H+0.054
 Butter+0.050
 Bub+0.050
Neg logit contributions
eks-0.045
he-0.044
 elevator-0.043
oos-0.043
ases-0.043
Token?"
Token ID1701
Feature activation-6.26e-03

Pos logit contributions
 Ho+0.087
 Rib+0.084
 H+0.078
 Bun+0.072
 Bub+0.071
Neg logit contributions
eks-0.082
oos-0.081
cases-0.080
ays-0.079
agged-0.078
Token Her
Token ID2332
Feature activation-7.08e-02

Pos logit contributions
 Rib+0.012
 Ho+0.011
onna+0.010
 Stri+0.010
die+0.010
Neg logit contributions
oos-0.008
agged-0.008
he-0.008
hed-0.007
 elevator-0.007
Token mom
Token ID1995
Feature activation+6.19e-02

Pos logit contributions
 Rib+0.148
 Ho+0.136
 Butter+0.127
onna+0.125
 Bub+0.125
Neg logit contributions
 elevator-0.085
ags-0.072
 bags-0.071
oos-0.071
ays-0.071