TOP ACTIVATIONS
MAX = 0.105

and makes a z ig zag shape . It is very
her friends . While playing , she saw a scared dog
the ground . Mia liked her shadow , so she said
" Let 's go for a spin ,"
I want to read it !" Jo shouted .
flashed . It made a funny noise . L
Lily said , making a funny face . "
and yellow and made a funny shape . Lily and Sam
wanted to keep it , so she put it in her
walking . Suddenly , Julia heard a mysterious voice
on and off and made funny shadows on the wall .
twists and turns made her g iggle and laugh .
. He wants to make one too . He dips his
circles and made the passengers g iggle . The aer opl
jumped and danced and made funny faces . Jill cl apped
she was playing the piano , she started to feel funny
in circles . It made her feel so good inside .
Ben says . " Let 's go and ask Mom !"
. " Let 's go and see ," Jill
look , I can make my shadow go on a walk

MIN ACTIVATIONS
MIN = -0.105

they had never seen the av oc ados . They wished
afternoon , Lucy asked Jack , " Why don 't you
recommendation and picked the right av oc ados .
. Johnson asked Lily , " Do you need a tutor
for being honest and said , " You are a good
Mrs . Johnson asked Lily , " Do you need a
. Lucy smiled and asked " May I have one ?"
food they bought from the grocery store . <|endoftext|> Once upon
. He gave the ice cream to the waiter as a
neighbour , Mrs Clar ise , for help .
always loved going to the grocery store with her mom my
to get two sa us ages . Gary knew
give the cash ier some money . Tim my got frustrated
was walking home from the grocery store when something wonderful happened
an old man and asked , " Please , could you
a kind man named Mr . Bear . He had a
a kind man named Mr . Smith . He had a
people use to buy things they want or need .
happy ! He thanked R uf us and they became good
visit their neighbor , Mrs . Lee . Mrs . Lee

INTERVAL 0.052 - 0.105
CONTAINS 0.083%

. She would watch them tw inkle in the sky every
The little girl took the golden circle in her hands and
. He can also make funny faces ." They
She loved to dance and tw irl around . One day
wonderful pictures . One day , Zoe y wanted to try

INTERVAL 0.000 - 0.052
CONTAINS 50.355%

match ! L izzy was so proud of
saw a big rock and wanted to climb it .
a little girl named Lily . She loved the color blue
Jack went to the park to play on the swings .
her room . So she tid ied her room

INTERVAL -0.052 - 0.000
CONTAINS 49.444%

olly friends were sad to say goodbye to the plane .
the day , Lily was tired but happy . She said
the cup board and saw some y ummy sauces . He
want to share . They start to fight over
inside and they would make cookies together . In no time

INTERVAL -0.105 - -0.052
CONTAINS 0.119%

wait to have an ice cream cone . Suddenly
So he asked his dad , " Why can 't I
of his pocket and asked , " What is that Tom
Tim my didn 't like onions and said , " Mom
playing is more important than candy . <|endoftext|> Once upon a
Token and
Token ID290
Feature activation+2.12e-02

Pos logit contributions
kered+0.045
iggle+0.044
ered+0.042
irled+0.040
ped+0.039
Neg logit contributions
 butcher-0.027
 paramed-0.025
 cart-0.023
 extingu-0.023
oc-0.022
Token makes
Token ID1838
Feature activation+4.64e-02

Pos logit contributions
iggle+0.037
kered+0.036
ered+0.032
owed+0.031
ped+0.030
Neg logit contributions
 butcher-0.039
 paramed-0.037
riger-0.034
oc-0.034
 Which-0.033
Token a
Token ID257
Feature activation+4.95e-02

Pos logit contributions
iggle+0.077
atively+0.075
owed+0.075
kered+0.075
irled+0.071
Neg logit contributions
 paramed-0.073
 butcher-0.061
 fires-0.060
 oil-0.057
Far-0.057
Token z
Token ID1976
Feature activation+3.45e-02

Pos logit contributions
kered+0.058
iggle+0.054
ered+0.049
ped+0.047
ia+0.043
Neg logit contributions
 butcher-0.121
 paramed-0.116
oc-0.107
riger-0.106
icer-0.105
Tokenig
Token ID328
Feature activation+6.59e-02

Pos logit contributions
kered+0.065
iggle+0.062
ered+0.058
ped+0.057
ia+0.055
Neg logit contributions
 butcher-0.060
 paramed-0.056
riger-0.050
icer-0.049
oc-0.049
Tokenzag
Token ID50183
Feature activation+9.39e-02

Pos logit contributions
kered+0.090
iggle+0.083
ped+0.081
 blinked+0.078
irled+0.076
Neg logit contributions
 paramed-0.120
oc-0.114
riger-0.107
 stret-0.106
 cart-0.105
Token shape
Token ID5485
Feature activation+4.77e-02

Pos logit contributions
kered+0.123
ped+0.117
iggle+0.116
irled+0.110
uttered+0.106
Neg logit contributions
oc-0.182
 paramed-0.167
 stret-0.160
 cart-0.156
 butcher-0.156
Token.
Token ID13
Feature activation+1.88e-02

Pos logit contributions
kered+0.085
iggle+0.083
ped+0.078
ered+0.077
atively+0.074
Neg logit contributions
 butcher-0.073
 paramed-0.071
oc-0.064
riger-0.061
 dollars-0.061
Token It
Token ID632
Feature activation+3.81e-02

Pos logit contributions
kered+0.029
iggle+0.028
ered+0.025
ia+0.024
ped+0.024
Neg logit contributions
 butcher-0.039
 paramed-0.037
riger-0.034
oc-0.033
icer-0.033
Token is
Token ID318
Feature activation+2.75e-02

Pos logit contributions
kered+0.067
iggle+0.065
ped+0.057
ered+0.057
owed+0.056
Neg logit contributions
 butcher-0.064
oc-0.062
 paramed-0.061
icer-0.060
riger-0.059
Token very
Token ID845
Feature activation+2.63e-02

Pos logit contributions
kered+0.054
iggle+0.051
ered+0.046
owed+0.046
atively+0.045
Neg logit contributions
 butcher-0.044
 paramed-0.042
riger-0.036
icer-0.035
Far-0.035
Token her
Token ID607
Feature activation+5.02e-02

Pos logit contributions
kered+0.085
atively+0.085
rated+0.080
iggle+0.077
owed+0.076
Neg logit contributions
 butcher-0.048
iw-0.045
 Mitt-0.043
P-0.043
 cart-0.041
Token friends
Token ID2460
Feature activation-1.26e-03

Pos logit contributions
kered+0.105
ered+0.100
iggle+0.098
owed+0.096
atively+0.093
Neg logit contributions
 butcher-0.065
P-0.062
 cart-0.061
 sausage-0.060
 paramed-0.059
Token.
Token ID13
Feature activation+4.53e-02

Pos logit contributions
 butcher+0.003
 paramed+0.003
icer+0.003
oc+0.003
riger+0.003
Neg logit contributions
kered-0.001
iggle-0.001
ered-0.001
 danced-0.001
ped-0.001
Token While
Token ID2893
Feature activation+4.48e-02

Pos logit contributions
kered+0.127
ered+0.118
ped+0.117
iggle+0.116
 flashed+0.116
Neg logit contributions
 butcher-0.032
 Which-0.031
 Why-0.025
 paramed-0.023
iw-0.021
Token playing
Token ID2712
Feature activation+1.61e-02

Pos logit contributions
kered+0.103
ered+0.091
iggle+0.089
atively+0.087
aned+0.086
Neg logit contributions
 butcher-0.054
etchup-0.054
iw-0.053
 shopping-0.052
P-0.050
Token,
Token ID11
Feature activation+8.12e-02

Pos logit contributions
kered+0.027
iggle+0.025
ered+0.023
ped+0.023
 flashed+0.022
Neg logit contributions
 butcher-0.031
 paramed-0.029
riger-0.026
 Which-0.026
oc-0.026
Token she
Token ID673
Feature activation+2.40e-02

Pos logit contributions
kered+0.175
aned+0.169
iggle+0.163
ered+0.158
ped+0.153
Neg logit contributions
Why-0.087
 Why-0.085
 Which-0.084
 Mitt-0.081
Which-0.081
Token saw
Token ID2497
Feature activation+2.57e-02

Pos logit contributions
kered+0.059
ered+0.054
iggle+0.053
ped+0.052
atively+0.051
Neg logit contributions
 butcher-0.029
 paramed-0.023
icer-0.023
 cart-0.022
P-0.022
Token a
Token ID257
Feature activation+2.14e-03

Pos logit contributions
iggle+0.057
kered+0.055
owed+0.050
ered+0.050
atively+0.048
Neg logit contributions
 paramed-0.037
 butcher-0.037
Which-0.033
 Which-0.030
Why-0.029
Token scared
Token ID12008
Feature activation+1.55e-02

Pos logit contributions
kered+0.003
iggle+0.003
ia+0.003
 flashed+0.003
 blinked+0.003
Neg logit contributions
 butcher-0.004
 paramed-0.004
riger-0.004
icer-0.004
uf-0.004
Token dog
Token ID3290
Feature activation-1.74e-03

Pos logit contributions
kered+0.029
iggle+0.028
ered+0.026
ped+0.025
ia+0.024
Neg logit contributions
 butcher-0.028
 paramed-0.026
riger-0.023
oc-0.022
uf-0.022
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
kered+0.008
iggle+0.007
ered+0.007
owed+0.007
ped+0.007
Neg logit contributions
 butcher-0.007
 paramed-0.006
icer-0.005
 sausage-0.005
uf-0.005
Token ground
Token ID2323
Feature activation+1.60e-02

Pos logit contributions
kered+0.038
iggle+0.034
ered+0.033
ped+0.030
irled+0.030
Neg logit contributions
 butcher-0.058
 paramed-0.054
uf-0.049
icer-0.049
 cart-0.048
Token.
Token ID13
Feature activation+5.64e-02

Pos logit contributions
kered+0.036
iggle+0.033
ered+0.033
ped+0.032
irled+0.031
Neg logit contributions
 butcher-0.019
Why-0.016
 paramed-0.016
iw-0.016
icer-0.015
Token Mia
Token ID32189
Feature activation+4.58e-02

Pos logit contributions
kered+0.126
iggle+0.118
ered+0.117
ped+0.115
 flashed+0.112
Neg logit contributions
 butcher-0.068
 Which-0.066
 Why-0.062
 paramed-0.057
iw-0.056
Token liked
Token ID8288
Feature activation+3.13e-02

Pos logit contributions
kered+0.087
iggle+0.083
 avail+0.074
ered+0.073
atively+0.072
Neg logit contributions
 butcher-0.071
�-0.067
'-0.066
 paramed-0.066
oc-0.064
Token her
Token ID607
Feature activation+8.07e-02

Pos logit contributions
kered+0.073
iggle+0.068
ered+0.065
owed+0.064
atively+0.063
Neg logit contributions
 butcher-0.042
 paramed-0.037
 Which-0.032
 cart-0.032
 sausage-0.031
Token shadow
Token ID9082
Feature activation+3.03e-02

Pos logit contributions
kered+0.145
ves+0.126
ered+0.126
ittered+0.119
iggle+0.118
Neg logit contributions
 cart-0.106
 truck-0.102
oc-0.101
 Which-0.095
 Cop-0.094
Token,
Token ID11
Feature activation+7.52e-03

Pos logit contributions
kered+0.069
iggle+0.065
ered+0.062
atively+0.061
ped+0.061
Neg logit contributions
 butcher-0.034
 cart-0.033
 paramed-0.032
 sausage-0.028
oc-0.027
Token so
Token ID523
Feature activation+5.42e-02

Pos logit contributions
kered+0.020
iggle+0.018
ered+0.018
irled+0.017
ped+0.017
Neg logit contributions
 butcher-0.007
 paramed-0.007
 sausage-0.006
 Which-0.006
Why-0.006
Token she
Token ID673
Feature activation+3.35e-02

Pos logit contributions
kered+0.124
iggle+0.115
ered+0.114
aned+0.111
atively+0.110
Neg logit contributions
 Mitt-0.054
 butcher-0.053
Which-0.052
iw-0.051
 cart-0.050
Token said
Token ID531
Feature activation+6.37e-03

Pos logit contributions
iggle+0.060
kered+0.058
 happen+0.053
 avail+0.051
ered+0.051
Neg logit contributions
 butcher-0.054
 paramed-0.052
P-0.051
Mic-0.048
 sa-0.048
Token
Token ID220
Feature activation+3.52e-02

Pos logit contributions
kered+0.044
iggle+0.042
ered+0.039
ped+0.039
ia+0.038
Neg logit contributions
 butcher-0.034
 paramed-0.030
 Which-0.027
oc-0.026
uf-0.026
Token
Token ID198
Feature activation+4.93e-03

Pos logit contributions
kered+0.076
iggle+0.073
ered+0.069
ped+0.067
ia+0.066
Neg logit contributions
 butcher-0.052
 paramed-0.047
riger-0.041
oc-0.040
uf-0.040
Token
Token ID198
Feature activation-4.24e-03

Pos logit contributions
kered+0.011
iggle+0.011
ered+0.010
ped+0.010
 flashed+0.009
Neg logit contributions
 butcher-0.007
 paramed-0.006
riger-0.005
oc-0.005
uf-0.005
Token"
Token ID1
Feature activation-1.19e-02

Pos logit contributions
 butcher+0.006
 paramed+0.006
riger+0.005
uf+0.005
icer+0.005
Neg logit contributions
kered-0.009
iggle-0.008
ered-0.008
ia-0.008
 flashed-0.008
TokenLet
Token ID5756
Feature activation+1.24e-03

Pos logit contributions
 butcher+0.018
 paramed+0.016
uf+0.015
riger+0.015
oc+0.014
Neg logit contributions
kered-0.025
iggle-0.023
 flashed-0.022
 danced-0.022
ped-0.022
Token's
Token ID338
Feature activation+7.97e-02

Pos logit contributions
kered+0.003
iggle+0.003
ered+0.002
ped+0.002
 flashed+0.002
Neg logit contributions
 butcher-0.002
 paramed-0.002
riger-0.001
uf-0.001
oc-0.001
Token go
Token ID467
Feature activation+2.70e-02

Pos logit contributions
kered+0.147
ped+0.138
atively+0.133
ia+0.125
iggle+0.124
Neg logit contributions
 paramed-0.128
riger-0.122
 butcher-0.118
 cart-0.113
 least-0.109
Token for
Token ID329
Feature activation+1.92e-02

Pos logit contributions
kered+0.050
iggle+0.047
ered+0.043
ped+0.043
ia+0.042
Neg logit contributions
 butcher-0.048
 paramed-0.045
riger-0.041
oc-0.040
icer-0.040
Token a
Token ID257
Feature activation+1.79e-02

Pos logit contributions
kered+0.033
iggle+0.031
owed+0.028
ped+0.028
atively+0.027
Neg logit contributions
 butcher-0.036
 paramed-0.034
riger-0.032
uf-0.031
icer-0.030
Token spin
Token ID7906
Feature activation+4.56e-02

Pos logit contributions
kered+0.028
iggle+0.027
ered+0.024
ped+0.023
ia+0.023
Neg logit contributions
 butcher-0.037
 paramed-0.034
riger-0.031
oc-0.031
icer-0.031
Token,"
Token ID553
Feature activation+2.39e-02

Pos logit contributions
kered+0.080
iggle+0.074
ped+0.070
ered+0.070
ia+0.067
Neg logit contributions
 butcher-0.082
 paramed-0.079
riger-0.072
icer-0.071
oc-0.071
TokenI
Token ID40
Feature activation-6.00e-03

Pos logit contributions
 butcher+0.011
 paramed+0.010
 dollars+0.009
riger+0.009
uf+0.009
Neg logit contributions
kered-0.014
 blinked-0.013
ered-0.012
 flew-0.012
ped-0.012
Token want
Token ID765
Feature activation+8.25e-03

Pos logit contributions
 butcher+0.013
 paramed+0.012
riger+0.011
icer+0.011
uf+0.011
Neg logit contributions
kered-0.009
iggle-0.009
ered-0.008
 blinked-0.007
 danced-0.007
Token to
Token ID284
Feature activation+3.52e-02

Pos logit contributions
kered+0.012
iggle+0.012
ered+0.011
 flew+0.011
 danced+0.011
Neg logit contributions
 butcher-0.017
 paramed-0.016
icer-0.014
riger-0.014
oc-0.014
Token read
Token ID1100
Feature activation+2.46e-02

Pos logit contributions
kered+0.065
iggle+0.061
ped+0.061
irled+0.058
led+0.056
Neg logit contributions
 butcher-0.062
 paramed-0.055
oc-0.053
uf-0.052
riger-0.051
Token it
Token ID340
Feature activation+1.08e-02

Pos logit contributions
kered+0.036
iggle+0.034
ered+0.032
ped+0.030
ia+0.030
Neg logit contributions
 butcher-0.053
 paramed-0.050
riger-0.045
uf-0.045
oc-0.044
Token!"
Token ID2474
Feature activation+7.90e-02

Pos logit contributions
kered+0.019
iggle+0.018
ped+0.016
ered+0.016
 flashed+0.016
Neg logit contributions
 butcher-0.020
 paramed-0.018
riger-0.017
oc-0.017
 Which-0.016
Token Jo
Token ID5302
Feature activation+5.14e-02

Pos logit contributions
iggle+0.148
kered+0.145
ittered+0.128
ped+0.125
kin+0.125
Neg logit contributions
 paramed-0.113
 butcher-0.106
riger-0.101
Wil-0.098
 cart-0.098
Token shouted
Token ID17293
Feature activation+1.75e-02

Pos logit contributions
kered+0.085
iggle+0.085
 patterns+0.075
 flashed+0.072
 happen+0.072
Neg logit contributions
 paramed-0.084
 butcher-0.081
uf-0.079
oc-0.079
riger-0.074
Token.
Token ID13
Feature activation+4.94e-02

Pos logit contributions
kered+0.026
iggle+0.025
ered+0.023
ped+0.022
ia+0.022
Neg logit contributions
 butcher-0.037
 paramed-0.035
riger-0.032
oc-0.031
uf-0.031
Token
Token ID198
Feature activation+3.41e-02

Pos logit contributions
kered+0.119
iggle+0.117
ped+0.105
 flashed+0.105
ered+0.102
Neg logit contributions
 butcher-0.055
 paramed-0.055
 Which-0.046
riger-0.044
 cart-0.043
Token
Token ID198
Feature activation+3.93e-02

Pos logit contributions
kered+0.086
iggle+0.084
ped+0.079
 flashed+0.078
ered+0.076
Neg logit contributions
 butcher-0.034
 paramed-0.031
riger-0.025
Charl-0.025
 Which-0.025
Token flashed
Token ID30050
Feature activation+4.01e-02

Pos logit contributions
iggle+0.033
kered+0.031
ered+0.028
ia+0.027
owed+0.026
Neg logit contributions
 butcher-0.028
 paramed-0.026
 ju-0.026
riger-0.026
iw-0.026
Token.
Token ID13
Feature activation+1.78e-02

Pos logit contributions
iggle+0.077
kered+0.074
ered+0.069
irled+0.068
ped+0.066
Neg logit contributions
 butcher-0.055
 paramed-0.051
oc-0.045
 Which-0.045
 cart-0.045
Token It
Token ID632
Feature activation+3.59e-02

Pos logit contributions
kered+0.033
iggle+0.032
ia+0.029
ered+0.029
ped+0.028
Neg logit contributions
 butcher-0.032
 paramed-0.029
riger-0.027
oc-0.026
icer-0.026
Token made
Token ID925
Feature activation+4.67e-02

Pos logit contributions
iggle+0.069
kered+0.061
azes+0.055
 avail+0.055
aby+0.053
Neg logit contributions
Why-0.050
oc-0.049
How-0.045
Which-0.044
 paramed-0.042
Token a
Token ID257
Feature activation+4.84e-02

Pos logit contributions
kered+0.089
iggle+0.086
owed+0.086
atively+0.085
ered+0.082
Neg logit contributions
 paramed-0.063
 butcher-0.054
 oil-0.048
 sausage-0.047
icer-0.047
Token funny
Token ID8258
Feature activation+7.88e-02

Pos logit contributions
kered+0.065
iggle+0.060
ered+0.059
ped+0.057
owed+0.053
Neg logit contributions
 butcher-0.107
 paramed-0.103
oc-0.098
icer-0.092
uf-0.092
Token noise
Token ID7838
Feature activation+4.31e-02

Pos logit contributions
kered+0.100
ered+0.094
ped+0.089
irled+0.084
owed+0.083
Neg logit contributions
oc-0.164
 paramed-0.153
 butcher-0.153
 sausage-0.150
 dish-0.145
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
kered+0.079
iggle+0.076
ered+0.073
ped+0.071
irled+0.069
Neg logit contributions
 butcher-0.072
 paramed-0.067
oc-0.061
riger-0.060
uf-0.057
Token
Token ID198
Feature activation+1.00e-03

Pos logit contributions
kered+0.044
iggle+0.042
ered+0.039
ia+0.038
ped+0.038
Neg logit contributions
 butcher-0.040
 paramed-0.037
riger-0.033
oc-0.033
icer-0.032
Token
Token ID198
Feature activation-6.52e-03

Pos logit contributions
kered+0.002
iggle+0.002
ered+0.002
ped+0.002
ia+0.002
Neg logit contributions
 butcher-0.001
 paramed-0.001
riger-0.001
oc-0.001
uf-0.001
TokenL
Token ID43
Feature activation+6.92e-03

Pos logit contributions
 butcher+0.011
 paramed+0.010
icer+0.009
uf+0.009
riger+0.009
Neg logit contributions
kered-0.013
iggle-0.012
ia-0.011
 flew-0.011
ered-0.011
Token Lily
Token ID20037
Feature activation+3.48e-02

Pos logit contributions
kered+0.035
iggle+0.034
ered+0.032
owed+0.031
ped+0.031
Neg logit contributions
 butcher-0.031
 paramed-0.030
 sausage-0.026
uf-0.025
riger-0.024
Token said
Token ID531
Feature activation+1.74e-02

Pos logit contributions
kered+0.057
iggle+0.056
ered+0.051
ped+0.049
 happen+0.049
Neg logit contributions
 butcher-0.064
 paramed-0.063
oc-0.056
uf-0.055
 sausage-0.054
Token,
Token ID11
Feature activation+8.12e-04

Pos logit contributions
kered+0.034
 flashed+0.031
iggle+0.030
 soared+0.030
ia+0.030
Neg logit contributions
 butcher-0.025
 paramed-0.024
'-0.021
 cart-0.020
 sausage-0.020
Token making
Token ID1642
Feature activation+4.70e-02

Pos logit contributions
kered+0.001
iggle+0.001
ia+0.001
ered+0.001
ped+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
 sausage-0.001
riger-0.001
uf-0.001
Token a
Token ID257
Feature activation+4.68e-02

Pos logit contributions
kered+0.089
owed+0.083
atively+0.083
 flashed+0.080
ped+0.078
Neg logit contributions
 paramed-0.066
 butcher-0.064
 sausage-0.060
 cart-0.056
 stret-0.055
Token funny
Token ID8258
Feature activation+7.83e-02

Pos logit contributions
kered+0.072
iggle+0.064
ered+0.063
ped+0.062
owed+0.057
Neg logit contributions
 butcher-0.099
 paramed-0.095
oc-0.086
icer-0.084
 sausage-0.083
Token face
Token ID1986
Feature activation+2.41e-02

Pos logit contributions
kered+0.108
ered+0.096
ped+0.090
owed+0.088
 soared+0.087
Neg logit contributions
 paramed-0.153
oc-0.147
 butcher-0.146
 cart-0.145
 sausage-0.143
Token.
Token ID13
Feature activation+7.39e-03

Pos logit contributions
kered+0.039
iggle+0.038
ered+0.035
ped+0.034
ia+0.033
Neg logit contributions
 butcher-0.047
 paramed-0.045
oc-0.040
riger-0.039
uf-0.038
Token
Token ID198
Feature activation+6.35e-03

Pos logit contributions
kered+0.015
iggle+0.014
ered+0.013
ped+0.013
 flashed+0.013
Neg logit contributions
 butcher-0.012
 paramed-0.011
uf-0.010
 Which-0.010
riger-0.010
Token
Token ID198
Feature activation+5.13e-03

Pos logit contributions
kered+0.014
iggle+0.014
ered+0.013
ped+0.013
 flashed+0.012
Neg logit contributions
 butcher-0.009
 paramed-0.008
riger-0.007
uf-0.007
oc-0.007
Token"
Token ID1
Feature activation-5.35e-03

Pos logit contributions
kered+0.011
iggle+0.011
ered+0.010
ia+0.010
ped+0.010
Neg logit contributions
 butcher-0.007
 paramed-0.007
icer-0.006
riger-0.006
oc-0.006
Token and
Token ID290
Feature activation+1.61e-02

Pos logit contributions
kered+0.010
iggle+0.009
ered+0.009
ped+0.008
ia+0.008
Neg logit contributions
 butcher-0.008
 paramed-0.007
oc-0.007
icer-0.007
 sausage-0.006
Token yellow
Token ID7872
Feature activation+1.19e-02

Pos logit contributions
iggle+0.026
kered+0.025
ered+0.022
ped+0.021
ia+0.021
Neg logit contributions
 butcher-0.032
 paramed-0.031
riger-0.028
oc-0.027
 Which-0.027
Token and
Token ID290
Feature activation+1.84e-02

Pos logit contributions
kered+0.024
iggle+0.024
ered+0.022
irled+0.021
ped+0.021
Neg logit contributions
 butcher-0.018
 paramed-0.017
oc-0.015
 sausage-0.015
 cart-0.014
Token made
Token ID925
Feature activation+4.41e-02

Pos logit contributions
iggle+0.031
kered+0.030
ered+0.026
ped+0.025
ia+0.025
Neg logit contributions
 butcher-0.035
 paramed-0.034
riger-0.031
 Which-0.031
oc-0.031
Token a
Token ID257
Feature activation+4.53e-02

Pos logit contributions
iggle+0.080
kered+0.075
owed+0.074
irled+0.073
ered+0.072
Neg logit contributions
 paramed-0.064
 butcher-0.056
 fires-0.053
 oil-0.052
icer-0.050
Token funny
Token ID8258
Feature activation+7.81e-02

Pos logit contributions
kered+0.058
iggle+0.054
ered+0.050
ped+0.049
owed+0.045
Neg logit contributions
 butcher-0.105
 paramed-0.101
oc-0.094
riger-0.092
icer-0.091
Token shape
Token ID5485
Feature activation+4.42e-02

Pos logit contributions
kered+0.088
ered+0.079
ped+0.078
iggle+0.078
owed+0.073
Neg logit contributions
 paramed-0.176
oc-0.175
 butcher-0.174
 sausage-0.160
icer-0.157
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
kered+0.076
iggle+0.075
ped+0.070
ered+0.070
ia+0.067
Neg logit contributions
 butcher-0.074
 paramed-0.071
oc-0.065
 dollars-0.062
 sausage-0.061
Token Lily
Token ID20037
Feature activation+3.58e-02

Pos logit contributions
kered+0.038
iggle+0.036
ered+0.033
ia+0.032
ped+0.032
Neg logit contributions
 butcher-0.045
 paramed-0.042
riger-0.039
oc-0.038
icer-0.038
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
kered+0.078
iggle+0.077
ered+0.073
ped+0.068
 happen+0.068
Neg logit contributions
 butcher-0.049
 paramed-0.044
oc-0.043
arre-0.039
uf-0.038
Token Sam
Token ID3409
Feature activation+2.53e-02

Pos logit contributions
 butcher+0.042
 paramed+0.039
uf+0.035
riger+0.035
Mic+0.034
Neg logit contributions
kered-0.035
iggle-0.032
ered-0.030
ped-0.028
irled-0.028
Token wanted
Token ID2227
Feature activation+2.15e-02

Pos logit contributions
kered+0.061
iggle+0.060
 happen+0.056
 avail+0.054
ped+0.051
Neg logit contributions
 butcher-0.042
 paramed-0.039
 jun-0.038
oc-0.038
P-0.037
Token to
Token ID284
Feature activation+3.76e-02

Pos logit contributions
kered+0.052
iggle+0.049
ped+0.045
atively+0.045
ered+0.045
Neg logit contributions
 butcher-0.027
 paramed-0.023
 Which-0.021
iw-0.020
Which-0.020
Token keep
Token ID1394
Feature activation+3.54e-02

Pos logit contributions
kered+0.079
ped+0.076
led+0.075
irled+0.072
owed+0.072
Neg logit contributions
 butcher-0.046
 paramed-0.042
oc-0.041
 charity-0.041
Mic-0.039
Token it
Token ID340
Feature activation+9.93e-03

Pos logit contributions
kered+0.055
iggle+0.049
ia+0.045
atively+0.043
ped+0.042
Neg logit contributions
 butcher-0.073
 paramed-0.067
riger-0.064
iw-0.064
icer-0.063
Token,
Token ID11
Feature activation+5.91e-03

Pos logit contributions
kered+0.020
ped+0.018
iggle+0.018
 flashed+0.018
ia+0.017
Neg logit contributions
 butcher-0.015
 paramed-0.013
riger-0.012
 dollars-0.012
 charity-0.012
Token so
Token ID523
Feature activation+7.75e-02

Pos logit contributions
kered+0.014
iggle+0.012
ped+0.012
ered+0.012
ia+0.012
Neg logit contributions
 butcher-0.008
 paramed-0.007
 Which-0.007
iw-0.006
 sausage-0.006
Token she
Token ID673
Feature activation+1.45e-02

Pos logit contributions
kered+0.191
ittered+0.174
ped+0.173
aned+0.171
iggle+0.171
Neg logit contributions
ip-0.038
Which-0.038
ossible-0.037
Why-0.034
 forward-0.033
Token put
Token ID1234
Feature activation+2.04e-02

Pos logit contributions
iggle+0.022
kered+0.022
 happen+0.019
ia+0.018
 flashed+0.018
Neg logit contributions
 butcher-0.029
 paramed-0.028
Mic-0.025
P-0.025
uf-0.024
Token it
Token ID340
Feature activation-4.03e-03

Pos logit contributions
kered+0.029
iggle+0.028
ia+0.024
ered+0.023
 flashed+0.023
Neg logit contributions
 butcher-0.044
 paramed-0.041
iw-0.038
 Which-0.038
icer-0.038
Token in
Token ID287
Feature activation-1.07e-02

Pos logit contributions
 butcher+0.005
 paramed+0.005
 Which+0.004
iw+0.004
riger+0.004
Neg logit contributions
kered-0.009
iggle-0.008
ia-0.008
 flashed-0.008
ered-0.007
Token her
Token ID607
Feature activation+1.36e-02

Pos logit contributions
 butcher+0.025
 paramed+0.023
icer+0.021
riger+0.021
uf+0.021
Neg logit contributions
kered-0.014
iggle-0.013
ered-0.012
ped-0.012
ia-0.011
Token walking
Token ID6155
Feature activation+9.93e-03

Pos logit contributions
kered+0.021
iggle+0.020
ered+0.018
ped+0.017
 danced+0.017
Neg logit contributions
 butcher-0.041
 paramed-0.039
oc-0.036
riger-0.035
uf-0.035
Token.
Token ID13
Feature activation+5.19e-02

Pos logit contributions
kered+0.015
iggle+0.014
ered+0.013
ped+0.013
ia+0.012
Neg logit contributions
 butcher-0.021
 paramed-0.020
riger-0.018
oc-0.018
icer-0.018
Token
Token ID198
Feature activation+3.69e-02

Pos logit contributions
kered+0.150
ped+0.140
 flashed+0.139
iggle+0.137
 happen+0.136
Neg logit contributions
 Which-0.028
 butcher-0.027
 Why-0.020
-0.020
Which-0.018
Token
Token ID198
Feature activation+4.62e-02

Pos logit contributions
kered+0.105
ped+0.100
 flashed+0.097
iggle+0.097
ered+0.095
Neg logit contributions
 butcher-0.024
oc-0.018
 paramed-0.015
Mrs-0.015
uf-0.015
TokenSuddenly
Token ID38582
Feature activation+6.42e-02

Pos logit contributions
ped+0.113
iggle+0.112
kered+0.112
owed+0.105
 happen+0.103
Neg logit contributions
P-0.038
 butcher-0.037
Which-0.036
Why-0.036
 Which-0.034
Token,
Token ID11
Feature activation+7.73e-02

Pos logit contributions
kered+0.169
ped+0.157
iggle+0.156
aned+0.152
 happen+0.143
Neg logit contributions
'-0.033
 Which-0.032
 paramed-0.032
 butcher-0.031
 grocery-0.031
Token Julia
Token ID22300
Feature activation+1.29e-02

Pos logit contributions
kered+0.181
aned+0.177
iggle+0.176
ped+0.171
ittered+0.155
Neg logit contributions
Why-0.063
Which-0.061
 Why-0.059
 grocery-0.058
-0.055
Token heard
Token ID2982
Feature activation+4.10e-02

Pos logit contributions
kered+0.026
iggle+0.026
ped+0.023
ered+0.023
 happen+0.023
Neg logit contributions
 butcher-0.019
 paramed-0.018
oc-0.017
'-0.017
uf-0.017
Token a
Token ID257
Feature activation-2.44e-03

Pos logit contributions
iggle+0.091
kered+0.089
irled+0.087
ittered+0.084
kin+0.083
Neg logit contributions
 paramed-0.050
 butcher-0.043
Mrs-0.039
Which-0.036
Far-0.035
Token mysterious
Token ID11428
Feature activation+1.62e-02

Pos logit contributions
 butcher+0.006
 paramed+0.006
riger+0.006
oc+0.006
uf+0.006
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.002
ped-0.002
ia-0.002
Token voice
Token ID3809
Feature activation+2.31e-02

Pos logit contributions
kered+0.016
iggle+0.015
ered+0.013
ped+0.012
ia+0.011
Neg logit contributions
 butcher-0.043
 paramed-0.041
oc-0.038
riger-0.037
uf-0.037
Token on
Token ID319
Feature activation-6.94e-03

Pos logit contributions
kered+0.005
iggle+0.005
ia+0.005
ped+0.004
irled+0.004
Neg logit contributions
 butcher-0.002
 cart-0.002
 Which-0.002
 paramed-0.002
riger-0.002
Token and
Token ID290
Feature activation+2.36e-02

Pos logit contributions
 butcher+0.015
 paramed+0.014
riger+0.013
iw+0.013
uf+0.013
Neg logit contributions
kered-0.010
iggle-0.009
ered-0.009
 flashed-0.008
ia-0.008
Token off
Token ID572
Feature activation+1.16e-02

Pos logit contributions
iggle+0.042
kered+0.040
ia+0.037
ped+0.034
irled+0.032
Neg logit contributions
 butcher-0.040
 paramed-0.039
riger-0.035
 Which-0.035
 jun-0.035
Token and
Token ID290
Feature activation+2.98e-02

Pos logit contributions
iggle+0.020
kered+0.020
ped+0.017
ered+0.017
owed+0.016
Neg logit contributions
 butcher-0.021
 paramed-0.020
riger-0.018
 cart-0.018
 Which-0.017
Token made
Token ID925
Feature activation+6.54e-02

Pos logit contributions
iggle+0.051
kered+0.050
ia+0.046
ped+0.042
irled+0.041
Neg logit contributions
 butcher-0.050
 paramed-0.048
 cart-0.044
riger-0.043
 Which-0.043
Token funny
Token ID8258
Feature activation+7.72e-02

Pos logit contributions
owed+0.122
atively+0.121
kered+0.118
iggle+0.117
ped+0.115
Neg logit contributions
 paramed-0.070
 fires-0.065
 cart-0.063
 butcher-0.062
 oil-0.059
Token shadows
Token ID16187
Feature activation+5.74e-02

Pos logit contributions
kered+0.096
atively+0.090
ped+0.089
iggle+0.088
ered+0.085
Neg logit contributions
oc-0.151
 butcher-0.145
 paramed-0.144
arre-0.138
 cart-0.137
Token on
Token ID319
Feature activation+3.30e-02

Pos logit contributions
kered+0.102
iggle+0.099
ped+0.096
ered+0.094
irled+0.091
Neg logit contributions
 paramed-0.090
 butcher-0.088
riger-0.079
oc-0.076
 cart-0.074
Token the
Token ID262
Feature activation+3.43e-02

Pos logit contributions
kered+0.062
iggle+0.060
owed+0.057
ped+0.056
irled+0.054
Neg logit contributions
 butcher-0.052
icer-0.047
 paramed-0.047
oc-0.046
riger-0.044
Token wall
Token ID3355
Feature activation+4.09e-02

Pos logit contributions
kered+0.057
iggle+0.056
ered+0.052
irled+0.049
owed+0.049
Neg logit contributions
 butcher-0.065
 paramed-0.058
 cart-0.056
icer-0.055
riger-0.055
Token.
Token ID13
Feature activation+1.34e-02

Pos logit contributions
kered+0.077
iggle+0.076
ped+0.074
ered+0.069
irled+0.068
Neg logit contributions
 butcher-0.058
 paramed-0.056
oc-0.052
riger-0.050
 cart-0.049
Token twists
Token ID30953
Feature activation+1.32e-02

Pos logit contributions
kered+0.049
iggle+0.046
ered+0.045
ped+0.042
owed+0.041
Neg logit contributions
 butcher-0.058
 paramed-0.056
 cart-0.048
 Which-0.048
riger-0.048
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
kered+0.026
iggle+0.026
ered+0.024
ia+0.024
owed+0.023
Neg logit contributions
 butcher-0.019
 paramed-0.018
 Which-0.016
riger-0.015
 cart-0.015
Token turns
Token ID4962
Feature activation+4.32e-02

Pos logit contributions
iggle+0.026
kered+0.026
ia+0.023
atively+0.023
ped+0.023
Neg logit contributions
riger-0.029
 Which-0.027
 ju-0.026
 paramed-0.026
arre-0.025
Token made
Token ID925
Feature activation+3.51e-02

Pos logit contributions
kered+0.072
iggle+0.068
ia+0.066
ped+0.064
ered+0.063
Neg logit contributions
 paramed-0.075
 butcher-0.066
riger-0.066
 cart-0.061
 Which-0.060
Token her
Token ID607
Feature activation+7.16e-02

Pos logit contributions
kered+0.058
owed+0.053
irled+0.053
iggle+0.052
ped+0.052
Neg logit contributions
 butcher-0.057
 paramed-0.056
Far-0.048
arre-0.048
 Mitt-0.047
Token g
Token ID308
Feature activation+7.72e-02

Pos logit contributions
kered+0.134
ped+0.117
atively+0.112
ered+0.107
ves+0.103
Neg logit contributions
 cart-0.113
 paramed-0.102
arre-0.100
 shopping-0.093
 butcher-0.093
Tokeniggle
Token ID24082
Feature activation+4.56e-02

Pos logit contributions
kered+0.057
 flew+0.054
 soared+0.052
 flashed+0.051
 blinked+0.050
Neg logit contributions
arre-0.196
uf-0.189
icer-0.188
 paramed-0.183
og-0.175
Token and
Token ID290
Feature activation+2.81e-02

Pos logit contributions
kered+0.091
ped+0.084
iggle+0.082
ia+0.082
ered+0.081
Neg logit contributions
 paramed-0.057
 butcher-0.053
arre-0.053
oc-0.049
riger-0.048
Token laugh
Token ID6487
Feature activation+4.76e-02

Pos logit contributions
kered+0.050
iggle+0.042
atively+0.042
ia+0.042
ves+0.041
Neg logit contributions
riger-0.042
 paramed-0.040
 Which-0.040
 cart-0.040
Why-0.039
Token.
Token ID13
Feature activation+1.03e-02

Pos logit contributions
kered+0.088
ered+0.085
iggle+0.084
ped+0.082
ia+0.082
Neg logit contributions
 butcher-0.068
 paramed-0.067
riger-0.061
oc-0.061
arre-0.059
Token
Token ID198
Feature activation+1.25e-02

Pos logit contributions
kered+0.022
iggle+0.021
ered+0.020
ped+0.019
 flashed+0.019
Neg logit contributions
 butcher-0.016
 paramed-0.014
riger-0.012
oc-0.012
uf-0.012
Token.
Token ID13
Feature activation+1.39e-02

Pos logit contributions
kered+0.059
iggle+0.057
ered+0.055
ped+0.054
irled+0.050
Neg logit contributions
 butcher-0.048
 paramed-0.044
 cart-0.042
oc-0.042
 dollars-0.042
Token He
Token ID679
Feature activation+2.49e-02

Pos logit contributions
kered+0.027
iggle+0.026
ered+0.024
ped+0.024
ia+0.023
Neg logit contributions
 butcher-0.023
 paramed-0.022
riger-0.019
oc-0.019
uf-0.019
Token wants
Token ID3382
Feature activation+1.67e-02

Pos logit contributions
kered+0.044
iggle+0.040
ped+0.037
ered+0.037
owed+0.036
Neg logit contributions
 butcher-0.044
 paramed-0.041
 Which-0.039
iw-0.039
riger-0.038
Token to
Token ID284
Feature activation+3.66e-02

Pos logit contributions
kered+0.037
iggle+0.036
ered+0.033
ped+0.033
owed+0.032
Neg logit contributions
 butcher-0.024
 paramed-0.022
 Which-0.019
iw-0.018
riger-0.018
Token make
Token ID787
Feature activation+6.16e-02

Pos logit contributions
kered+0.072
ped+0.067
atively+0.066
iggle+0.065
led+0.065
Neg logit contributions
 paramed-0.053
 butcher-0.049
iw-0.047
 Which-0.046
riger-0.046
Token one
Token ID530
Feature activation+7.67e-02

Pos logit contributions
kered+0.115
ped+0.104
atively+0.102
owed+0.102
iggle+0.100
Neg logit contributions
 butcher-0.093
 paramed-0.087
icer-0.082
 Which-0.079
 cart-0.079
Token too
Token ID1165
Feature activation+2.59e-02

Pos logit contributions
kered+0.158
ped+0.149
ered+0.140
iggle+0.139
atively+0.130
Neg logit contributions
 butcher-0.104
 Which-0.102
oc-0.099
iw-0.098
Which-0.094
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
kered+0.043
iggle+0.041
ered+0.038
ped+0.038
 danced+0.036
Neg logit contributions
 butcher-0.051
 paramed-0.046
oc-0.043
uf-0.042
riger-0.042
Token He
Token ID679
Feature activation+1.02e-02

Pos logit contributions
kered+0.023
iggle+0.022
ia+0.021
ered+0.020
ped+0.020
Neg logit contributions
 butcher-0.021
 paramed-0.020
riger-0.017
uf-0.017
icer-0.017
Token dips
Token ID48904
Feature activation+2.15e-02

Pos logit contributions
kered+0.016
iggle+0.015
ered+0.013
ped+0.013
 flashed+0.012
Neg logit contributions
 butcher-0.021
 paramed-0.020
icer-0.018
riger-0.018
oc-0.018
Token his
Token ID465
Feature activation+4.99e-02

Pos logit contributions
kered+0.037
iggle+0.036
ered+0.032
 flashed+0.031
owed+0.031
Neg logit contributions
 butcher-0.038
 paramed-0.034
icer-0.034
 Which-0.034
iw-0.033
Token circles
Token ID13332
Feature activation+4.67e-02

Pos logit contributions
kered+0.002
iggle+0.002
ered+0.002
ped+0.002
ia+0.002
Neg logit contributions
 butcher-0.003
 paramed-0.003
riger-0.002
uf-0.002
oc-0.002
Token and
Token ID290
Feature activation+2.30e-02

Pos logit contributions
kered+0.097
ered+0.092
iggle+0.092
ia+0.089
ped+0.088
Neg logit contributions
 paramed-0.045
 butcher-0.045
'-0.044
arre-0.040
 cart-0.040
Token made
Token ID925
Feature activation+5.40e-02

Pos logit contributions
kered+0.044
iggle+0.041
ia+0.039
ered+0.036
owed+0.036
Neg logit contributions
 butcher-0.035
riger-0.033
 paramed-0.033
 Which-0.032
 jun-0.032
Token the
Token ID262
Feature activation+2.94e-02

Pos logit contributions
owed+0.099
atively+0.096
kered+0.095
iggle+0.094
kin+0.089
Neg logit contributions
 paramed-0.074
 butcher-0.065
oc-0.060
 cart-0.060
 sa-0.058
Token passengers
Token ID10405
Feature activation+5.51e-02

Pos logit contributions
kered+0.055
iggle+0.053
ered+0.049
ped+0.048
ia+0.047
Neg logit contributions
 butcher-0.051
 paramed-0.048
riger-0.042
icer-0.042
oc-0.042
Token g
Token ID308
Feature activation+7.64e-02

Pos logit contributions
kered+0.078
ia+0.075
iggle+0.075
ped+0.072
irled+0.068
Neg logit contributions
 paramed-0.103
 butcher-0.096
 cart-0.091
oc-0.090
riger-0.090
Tokeniggle
Token ID24082
Feature activation+4.24e-02

Pos logit contributions
 blinked+0.064
kered+0.064
atively+0.061
 flashed+0.061
 flew+0.057
Neg logit contributions
arre-0.173
 paramed-0.167
uf-0.165
icer-0.161
og-0.159
Token.
Token ID13
Feature activation+2.08e-02

Pos logit contributions
kered+0.076
iggle+0.074
ered+0.070
ia+0.070
ped+0.068
Neg logit contributions
 butcher-0.061
 paramed-0.060
oc-0.057
arre-0.053
 cart-0.051
Token The
Token ID383
Feature activation+1.69e-02

Pos logit contributions
kered+0.044
iggle+0.043
ered+0.040
ped+0.039
ia+0.038
Neg logit contributions
 butcher-0.031
 paramed-0.029
oc-0.025
riger-0.025
icer-0.024
Token aer
Token ID9551
Feature activation+1.18e-02

Pos logit contributions
kered+0.032
iggle+0.031
ered+0.029
ped+0.028
 flashed+0.028
Neg logit contributions
 butcher-0.029
 paramed-0.027
riger-0.024
uf-0.024
oc-0.023
Tokenopl
Token ID20106
Feature activation+3.01e-02

Pos logit contributions
kered+0.027
iggle+0.026
ered+0.024
ped+0.024
ia+0.023
Neg logit contributions
 butcher-0.016
 paramed-0.015
riger-0.013
uf-0.012
oc-0.012
Token jumped
Token ID11687
Feature activation+1.82e-02

Pos logit contributions
iggle+0.061
kered+0.059
ped+0.052
ered+0.052
atively+0.049
Neg logit contributions
 paramed-0.058
 butcher-0.056
oc-0.055
 sa-0.053
arre-0.052
Token and
Token ID290
Feature activation+2.37e-02

Pos logit contributions
kered+0.031
iggle+0.029
ered+0.027
ped+0.026
ia+0.026
Neg logit contributions
 butcher-0.035
 paramed-0.033
riger-0.030
oc-0.029
icer-0.029
Token danced
Token ID39480
Feature activation+3.21e-02

Pos logit contributions
iggle+0.036
kered+0.035
ia+0.032
ered+0.031
atively+0.029
Neg logit contributions
riger-0.045
 paramed-0.044
 butcher-0.042
 sa-0.042
Charl-0.041
Token and
Token ID290
Feature activation+3.56e-02

Pos logit contributions
kered+0.060
iggle+0.059
ered+0.057
ped+0.054
ia+0.053
Neg logit contributions
 butcher-0.048
 paramed-0.046
oc-0.043
riger-0.042
 cart-0.040
Token made
Token ID925
Feature activation+6.08e-02

Pos logit contributions
iggle+0.053
kered+0.052
ia+0.049
ered+0.047
atively+0.047
Neg logit contributions
riger-0.061
 sa-0.058
 paramed-0.056
 ju-0.054
 vending-0.054
Token funny
Token ID8258
Feature activation+7.63e-02

Pos logit contributions
owed+0.104
kered+0.101
atively+0.100
iggle+0.096
ered+0.096
Neg logit contributions
 paramed-0.085
 butcher-0.081
oc-0.075
 fires-0.071
 cart-0.071
Token faces
Token ID6698
Feature activation+3.59e-02

Pos logit contributions
kered+0.089
ered+0.089
atively+0.085
ped+0.084
iggle+0.080
Neg logit contributions
oc-0.157
 paramed-0.153
 butcher-0.147
arre-0.145
 cart-0.136
Token.
Token ID13
Feature activation+1.20e-02

Pos logit contributions
kered+0.060
iggle+0.059
ered+0.056
ped+0.054
ia+0.052
Neg logit contributions
 butcher-0.066
 paramed-0.063
oc-0.056
riger-0.055
 sausage-0.053
Token Jill
Token ID22772
Feature activation+6.77e-02

Pos logit contributions
kered+0.023
iggle+0.022
ered+0.020
ped+0.020
 flashed+0.019
Neg logit contributions
 butcher-0.021
 paramed-0.019
 Which-0.017
oc-0.017
icer-0.017
Token cl
Token ID537
Feature activation+3.98e-02

Pos logit contributions
iggle+0.109
kered+0.108
 avail+0.103
ered+0.098
ped+0.095
Neg logit contributions
'-0.107
 paramed-0.102
oc-0.102
arre-0.101
 butcher-0.097
Tokenapped
Token ID6320
Feature activation+4.09e-02

Pos logit contributions
 happen+0.053
kered+0.048
ered+0.048
iggle+0.048
atively+0.046
Neg logit contributions
 paramed-0.081
oc-0.078
arre-0.077
 butcher-0.074
iw-0.073
Token she
Token ID673
Feature activation+2.12e-02

Pos logit contributions
kered+0.111
ped+0.103
iggle+0.099
ered+0.091
atively+0.090
Neg logit contributions
 butcher-0.075
Far-0.067
Which-0.067
icer-0.067
riger-0.067
Token was
Token ID373
Feature activation+2.49e-03

Pos logit contributions
kered+0.036
iggle+0.034
atively+0.032
ered+0.031
aby+0.031
Neg logit contributions
 paramed-0.033
P-0.033
oc-0.032
 butcher-0.032
 sausage-0.032
Token playing
Token ID2712
Feature activation+3.77e-03

Pos logit contributions
kered+0.005
ered+0.004
iggle+0.004
ped+0.004
atively+0.004
Neg logit contributions
 butcher-0.004
 paramed-0.004
riger-0.004
arre-0.003
uf-0.003
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
kered+0.005
iggle+0.005
ered+0.004
 danced+0.004
ped+0.004
Neg logit contributions
 butcher-0.009
 paramed-0.008
uf-0.008
icer-0.008
riger-0.008
Token piano
Token ID19132
Feature activation+3.57e-03

Pos logit contributions
kered+0.035
iggle+0.033
ered+0.032
ped+0.031
ia+0.031
Neg logit contributions
 butcher-0.026
 paramed-0.024
riger-0.021
icer-0.020
Mic-0.020
Token,
Token ID11
Feature activation+7.63e-02

Pos logit contributions
kered+0.006
iggle+0.006
ered+0.006
ped+0.006
ia+0.005
Neg logit contributions
 butcher-0.007
 paramed-0.006
riger-0.006
 cart-0.005
oc-0.005
Token she
Token ID673
Feature activation+1.30e-02

Pos logit contributions
kered+0.159
iggle+0.158
ped+0.149
ittered+0.133
aned+0.132
Neg logit contributions
 paramed-0.089
Which-0.086
Why-0.085
 Which-0.085
 Why-0.081
Token started
Token ID2067
Feature activation+2.82e-02

Pos logit contributions
kered+0.030
iggle+0.028
 happen+0.026
ered+0.026
ped+0.026
Neg logit contributions
 butcher-0.017
 paramed-0.015
arre-0.014
P-0.013
 cart-0.013
Token to
Token ID284
Feature activation+1.91e-02

Pos logit contributions
kered+0.063
iggle+0.059
ered+0.056
ped+0.055
ia+0.055
Neg logit contributions
 butcher-0.040
 paramed-0.038
riger-0.031
uf-0.030
iw-0.030
Token feel
Token ID1254
Feature activation-1.71e-02

Pos logit contributions
kered+0.032
ped+0.027
iggle+0.027
ia+0.026
ered+0.025
Neg logit contributions
 butcher-0.038
 paramed-0.037
riger-0.034
arre-0.032
 sausage-0.032
Token funny
Token ID8258
Feature activation+3.78e-02

Pos logit contributions
 butcher+0.030
 paramed+0.028
uf+0.024
 sausage+0.024
riger+0.024
Neg logit contributions
kered-0.032
iggle-0.030
ered-0.028
ia-0.028
ped-0.027
Token in
Token ID287
Feature activation+1.45e-02

Pos logit contributions
kered+0.057
iggle+0.051
ered+0.050
ped+0.049
owed+0.048
Neg logit contributions
 butcher-0.043
 paramed-0.042
riger-0.039
 cart-0.037
 sausage-0.036
Token circles
Token ID13332
Feature activation+4.68e-02

Pos logit contributions
kered+0.028
iggle+0.025
ped+0.024
ered+0.024
owed+0.024
Neg logit contributions
 butcher-0.024
 paramed-0.022
 Which-0.021
icer-0.020
riger-0.020
Token.
Token ID13
Feature activation+2.37e-02

Pos logit contributions
kered+0.092
ered+0.089
iggle+0.085
ped+0.085
ia+0.082
Neg logit contributions
 paramed-0.056
 butcher-0.056
'-0.051
 cart-0.049
riger-0.049
Token It
Token ID632
Feature activation+5.07e-02

Pos logit contributions
kered+0.046
ered+0.041
iggle+0.041
 flashed+0.040
ped+0.039
Neg logit contributions
 butcher-0.041
 paramed-0.036
 Which-0.035
uf-0.034
riger-0.033
Token made
Token ID925
Feature activation+4.63e-02

Pos logit contributions
kered+0.103
iggle+0.099
ped+0.091
azes+0.089
 avail+0.088
Neg logit contributions
Why-0.058
arre-0.057
Which-0.056
m-0.055
�-0.054
Token her
Token ID607
Feature activation+7.62e-02

Pos logit contributions
kered+0.085
owed+0.081
atively+0.081
 rang+0.080
ered+0.079
Neg logit contributions
 Mitt-0.057
 paramed-0.054
 butcher-0.054
Why-0.052
Mrs-0.051
Token feel
Token ID1254
Feature activation+1.59e-02

Pos logit contributions
kered+0.177
ped+0.154
ves+0.149
atively+0.147
ered+0.147
Neg logit contributions
 cart-0.085
 least-0.073
 sausage-0.073
 ju-0.071
arre-0.069
Token so
Token ID523
Feature activation+4.78e-02

Pos logit contributions
kered+0.036
atively+0.034
ered+0.034
ped+0.034
ia+0.033
Neg logit contributions
 paramed-0.017
 butcher-0.016
 ju-0.015
Charl-0.014
Why-0.014
Token good
Token ID922
Feature activation+2.18e-02

Pos logit contributions
atively+0.101
ped+0.101
kered+0.100
ered+0.094
owed+0.092
Neg logit contributions
riger-0.041
arre-0.039
 paramed-0.039
 ju-0.039
conf-0.039
Token inside
Token ID2641
Feature activation+5.18e-03

Pos logit contributions
kered+0.042
iggle+0.038
ered+0.037
ped+0.035
ia+0.035
Neg logit contributions
 butcher-0.037
 paramed-0.033
riger-0.031
uf-0.029
iw-0.029
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
kered+0.008
iggle+0.008
ped+0.007
ered+0.007
 flashed+0.007
Neg logit contributions
 butcher-0.010
 paramed-0.009
 Which-0.008
iw-0.008
icer-0.008
Token Ben
Token ID3932
Feature activation+3.93e-02

Pos logit contributions
kered+0.048
ered+0.044
iggle+0.043
owed+0.043
ped+0.043
Neg logit contributions
 butcher-0.029
uf-0.025
 paramed-0.025
 sausage-0.024
 cart-0.024
Token says
Token ID1139
Feature activation+1.35e-02

Pos logit contributions
kered+0.065
iggle+0.059
ered+0.054
ped+0.053
atively+0.052
Neg logit contributions
 butcher-0.073
riger-0.066
 paramed-0.065
oc-0.064
arre-0.061
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
kered+0.025
 soared+0.024
iggle+0.024
 flashed+0.024
ped+0.023
Neg logit contributions
 paramed-0.020
 butcher-0.020
 dollars-0.016
oc-0.016
riger-0.016
Token "
Token ID366
Feature activation-1.32e-02

Pos logit contributions
kered+0.028
iggle+0.027
ered+0.025
ped+0.024
ia+0.024
Neg logit contributions
 butcher-0.023
 paramed-0.021
riger-0.019
oc-0.019
uf-0.018
TokenLet
Token ID5756
Feature activation-4.00e-03

Pos logit contributions
 butcher+0.022
 paramed+0.021
uf+0.019
icer+0.019
riger+0.018
Neg logit contributions
kered-0.025
iggle-0.022
 blinked-0.022
 flew-0.022
 danced-0.022
Token's
Token ID338
Feature activation+7.56e-02

Pos logit contributions
 butcher+0.006
 paramed+0.006
riger+0.005
oc+0.005
uf+0.005
Neg logit contributions
kered-0.008
iggle-0.008
ered-0.007
ped-0.007
 flashed-0.007
Token go
Token ID467
Feature activation+3.57e-02

Pos logit contributions
kered+0.121
ped+0.107
iggle+0.106
ia+0.100
atively+0.100
Neg logit contributions
 butcher-0.139
 paramed-0.132
riger-0.131
oc-0.127
uf-0.124
Token and
Token ID290
Feature activation+3.83e-02

Pos logit contributions
kered+0.065
iggle+0.061
ped+0.055
ered+0.055
ia+0.054
Neg logit contributions
 butcher-0.065
 paramed-0.061
riger-0.055
oc-0.055
icer-0.054
Token ask
Token ID1265
Feature activation+1.31e-02

Pos logit contributions
kered+0.068
iggle+0.064
ia+0.058
ped+0.057
ered+0.055
Neg logit contributions
 butcher-0.073
 paramed-0.068
riger-0.065
 Which-0.062
oc-0.061
Token Mom
Token ID11254
Feature activation+1.04e-03

Pos logit contributions
kered+0.024
iggle+0.023
ered+0.021
ped+0.021
 flashed+0.020
Neg logit contributions
 butcher-0.024
 paramed-0.022
riger-0.019
uf-0.019
oc-0.019
Token!"
Token ID2474
Feature activation+1.99e-02

Pos logit contributions
iggle+0.002
kered+0.002
ered+0.001
ia+0.001
owed+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
riger-0.002
Mic-0.002
uf-0.002
Token.
Token ID13
Feature activation+1.64e-02

Pos logit contributions
kered+0.010
iggle+0.009
ered+0.009
ped+0.009
irled+0.008
Neg logit contributions
 butcher-0.010
 paramed-0.009
oc-0.008
 Which-0.008
icer-0.008
Token
Token ID198
Feature activation+6.55e-03

Pos logit contributions
kered+0.024
iggle+0.023
ia+0.023
ered+0.021
 Lia+0.021
Neg logit contributions
 butcher-0.033
 paramed-0.032
riger-0.028
icer-0.028
arre-0.028
Token
Token ID198
Feature activation+1.03e-03

Pos logit contributions
kered+0.013
iggle+0.012
ered+0.012
ia+0.012
ped+0.011
Neg logit contributions
 butcher-0.011
 paramed-0.010
riger-0.009
icer-0.009
uf-0.009
Token"
Token ID1
Feature activation-1.36e-02

Pos logit contributions
kered+0.002
ia+0.002
iggle+0.002
ered+0.002
ves+0.002
Neg logit contributions
 butcher-0.002
 paramed-0.002
icer-0.002
uf-0.002
 sausage-0.002
TokenLet
Token ID5756
Feature activation-4.58e-03

Pos logit contributions
 butcher+0.020
 paramed+0.018
riger+0.016
oc+0.015
uf+0.015
Neg logit contributions
kered-0.030
iggle-0.029
ered-0.027
ped-0.027
ia-0.026
Token's
Token ID338
Feature activation+7.56e-02

Pos logit contributions
 butcher+0.007
 paramed+0.006
riger+0.005
uf+0.005
oc+0.005
Neg logit contributions
kered-0.010
iggle-0.009
ped-0.009
 flashed-0.009
ered-0.009
Token go
Token ID467
Feature activation+2.82e-02

Pos logit contributions
kered+0.144
ped+0.134
atively+0.125
led+0.121
owed+0.116
Neg logit contributions
riger-0.111
 butcher-0.109
'-0.108
 paramed-0.107
 charity-0.107
Token and
Token ID290
Feature activation+3.42e-02

Pos logit contributions
kered+0.051
iggle+0.049
ered+0.045
ped+0.044
ia+0.043
Neg logit contributions
 butcher-0.052
 paramed-0.048
riger-0.043
oc-0.042
uf-0.042
Token see
Token ID766
Feature activation+2.38e-02

Pos logit contributions
kered+0.064
iggle+0.057
ped+0.054
ia+0.052
ered+0.051
Neg logit contributions
 butcher-0.061
 paramed-0.058
riger-0.057
 Which-0.054
use-0.053
Token,"
Token ID553
Feature activation+1.68e-02

Pos logit contributions
kered+0.040
iggle+0.038
ered+0.035
ped+0.034
ia+0.033
Neg logit contributions
 butcher-0.047
 paramed-0.044
riger-0.039
oc-0.039
uf-0.039
Token Jill
Token ID22772
Feature activation+2.90e-02

Pos logit contributions
kered+0.028
iggle+0.026
ered+0.024
ped+0.023
 flashed+0.022
Neg logit contributions
 butcher-0.034
 paramed-0.032
riger-0.029
uf-0.028
 Which-0.028
Token look
Token ID804
Feature activation-5.10e-03

Pos logit contributions
kered+0.003
iggle+0.003
ered+0.003
 danced+0.003
ia+0.003
Neg logit contributions
 butcher-0.005
 paramed-0.005
Mic-0.005
uf-0.004
icer-0.004
Token,
Token ID11
Feature activation+1.29e-02

Pos logit contributions
 butcher+0.010
 paramed+0.010
uf+0.008
riger+0.008
Mic+0.008
Neg logit contributions
kered-0.008
iggle-0.008
ered-0.007
ia-0.007
ped-0.007
Token I
Token ID314
Feature activation-3.51e-03

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.017
ia+0.016
ped+0.016
Neg logit contributions
 butcher-0.028
 paramed-0.026
riger-0.023
oc-0.023
uf-0.023
Token can
Token ID460
Feature activation+4.31e-02

Pos logit contributions
 butcher+0.007
 paramed+0.006
riger+0.006
oc+0.006
uf+0.005
Neg logit contributions
kered-0.006
iggle-0.006
ered-0.005
ped-0.005
ia-0.005
Token make
Token ID787
Feature activation+6.25e-02

Pos logit contributions
kered+0.074
iggle+0.065
ped+0.065
ia+0.060
 flashed+0.059
Neg logit contributions
 butcher-0.079
 paramed-0.075
riger-0.071
uf-0.068
oc-0.067
Token my
Token ID616
Feature activation+7.54e-02

Pos logit contributions
kered+0.119
atively+0.107
iggle+0.105
ped+0.104
owed+0.102
Neg logit contributions
 paramed-0.092
 butcher-0.092
oc-0.084
riger-0.083
icer-0.083
Token shadow
Token ID9082
Feature activation+4.40e-02

Pos logit contributions
kered+0.128
ered+0.103
iggle+0.101
ves+0.098
ped+0.097
Neg logit contributions
oc-0.136
 butcher-0.125
icer-0.124
 Which-0.122
 cart-0.121
Token go
Token ID467
Feature activation+1.86e-02

Pos logit contributions
kered+0.074
iggle+0.068
ped+0.065
ered+0.062
ia+0.060
Neg logit contributions
 butcher-0.080
 paramed-0.079
oc-0.072
riger-0.071
 Which-0.068
Token on
Token ID319
Feature activation+5.78e-03

Pos logit contributions
kered+0.033
iggle+0.031
ered+0.029
ped+0.028
ia+0.028
Neg logit contributions
 butcher-0.035
 paramed-0.032
riger-0.029
oc-0.029
icer-0.028
Token a
Token ID257
Feature activation+2.18e-02

Pos logit contributions
kered+0.009
iggle+0.009
ered+0.008
ped+0.008
ia+0.008
Neg logit contributions
 butcher-0.012
 paramed-0.011
riger-0.010
oc-0.010
uf-0.010
Token walk
Token ID2513
Feature activation+1.01e-02

Pos logit contributions
kered+0.033
iggle+0.031
ered+0.028
ia+0.027
ped+0.027
Neg logit contributions
 butcher-0.046
 paramed-0.044
riger-0.039
uf-0.039
icer-0.039
Token they
Token ID484
Feature activation-3.10e-02

Pos logit contributions
kered+0.012
iggle+0.011
ered+0.010
ped+0.010
ia+0.009
Neg logit contributions
 butcher-0.016
 paramed-0.015
riger-0.014
uf-0.014
oc-0.014
Token had
Token ID550
Feature activation-3.55e-02

Pos logit contributions
 butcher+0.068
 paramed+0.063
riger+0.058
uf+0.057
oc+0.057
Neg logit contributions
kered-0.044
iggle-0.044
ered-0.037
ped-0.037
ia-0.037
Token never
Token ID1239
Feature activation-2.75e-02

Pos logit contributions
 butcher+0.079
 paramed+0.074
riger+0.067
uf+0.067
oc+0.066
Neg logit contributions
kered-0.051
iggle-0.048
ered-0.043
ped-0.042
ia-0.041
Token seen
Token ID1775
Feature activation-3.25e-02

Pos logit contributions
 butcher+0.050
 paramed+0.046
use+0.043
riger+0.042
 Which+0.041
Neg logit contributions
iggle-0.048
kered-0.048
ia-0.041
atively-0.040
ered-0.040
Token the
Token ID262
Feature activation-4.05e-02

Pos logit contributions
 butcher+0.070
 paramed+0.068
riger+0.065
oc+0.062
icer+0.061
Neg logit contributions
kered-0.044
iggle-0.043
ered-0.040
ped-0.039
 blinked-0.037
Token av
Token ID1196
Feature activation-8.61e-02

Pos logit contributions
 paramed+0.072
oc+0.071
enn+0.070
arre+0.069
uf+0.069
Neg logit contributions
 happen-0.056
 blinked-0.056
kered-0.055
 glow-0.055
 flashed-0.054
Tokenoc
Token ID420
Feature activation-7.03e-02

Pos logit contributions
 paramed+0.106
 charity+0.083
 butcher+0.080
 Which+0.078
Which+0.074
Neg logit contributions
kered-0.195
 flew-0.185
iggle-0.183
 soared-0.176
 soar-0.176
Tokenados
Token ID22484
Feature activation-5.92e-02

Pos logit contributions
Charl+0.120
Which+0.115
riger+0.113
 paramed+0.111
 charity+0.111
Neg logit contributions
ped-0.120
kered-0.117
ered-0.105
iggle-0.102
atively-0.098
Token.
Token ID13
Feature activation-3.50e-03

Pos logit contributions
 butcher+0.135
 paramed+0.134
icer+0.119
Mic+0.118
uf+0.118
Neg logit contributions
kered-0.076
iggle-0.074
ered-0.065
 flew-0.062
 blinked-0.062
Token They
Token ID1119
Feature activation-2.53e-02

Pos logit contributions
 butcher+0.007
 paramed+0.006
riger+0.006
oc+0.006
icer+0.006
Neg logit contributions
kered-0.006
iggle-0.006
ered-0.005
ped-0.005
ia-0.005
Token wished
Token ID16555
Feature activation+1.26e-02

Pos logit contributions
 butcher+0.048
 paramed+0.045
uf+0.041
oc+0.041
Mic+0.040
Neg logit contributions
iggle-0.043
kered-0.042
ia-0.037
ered-0.036
ped-0.035
Token afternoon
Token ID6672
Feature activation-4.04e-03

Pos logit contributions
 butcher+0.031
 paramed+0.028
oc+0.025
 sausage+0.025
arre+0.025
Neg logit contributions
kered-0.024
iggle-0.024
ped-0.021
ered-0.021
owed-0.020
Token,
Token ID11
Feature activation+9.51e-03

Pos logit contributions
 butcher+0.009
 paramed+0.008
riger+0.007
oc+0.007
uf+0.007
Neg logit contributions
kered-0.006
iggle-0.006
ered-0.005
ped-0.005
ia-0.005
Token Lucy
Token ID22162
Feature activation-7.72e-04

Pos logit contributions
kered+0.016
iggle+0.015
ered+0.014
ped+0.014
ia+0.013
Neg logit contributions
 butcher-0.019
 paramed-0.017
riger-0.016
oc-0.015
uf-0.015
Token asked
Token ID1965
Feature activation-1.67e-02

Pos logit contributions
 butcher+0.002
 paramed+0.002
oc+0.001
uf+0.001
riger+0.001
Neg logit contributions
kered-0.001
iggle-0.001
ered-0.001
ia-0.001
ped-0.001
Token Jack
Token ID3619
Feature activation-4.26e-02

Pos logit contributions
 butcher+0.035
 paramed+0.033
riger+0.030
oc+0.029
uf+0.029
Neg logit contributions
kered-0.026
iggle-0.025
ered-0.022
ped-0.022
ia-0.021
Token,
Token ID11
Feature activation-8.36e-02

Pos logit contributions
 paramed+0.090
 butcher+0.087
icer+0.084
riger+0.081
Mic+0.080
Neg logit contributions
iggle-0.058
kered-0.056
ered-0.054
ia-0.053
owed-0.051
Token "
Token ID366
Feature activation-5.09e-02

Pos logit contributions
icer+0.175
 butcher+0.173
iw+0.165
 paramed+0.160
etchup+0.158
Neg logit contributions
iggle-0.103
kered-0.098
atively-0.097
ered-0.097
fully-0.095
TokenWhy
Token ID5195
Feature activation-2.20e-02

Pos logit contributions
 paramed+0.078
 butcher+0.071
riger+0.069
oc+0.068
uf+0.067
Neg logit contributions
kered-0.087
 blinked-0.086
 danced-0.083
 flew-0.082
fully-0.081
Token don
Token ID836
Feature activation+8.06e-03

Pos logit contributions
 butcher+0.048
 paramed+0.045
riger+0.041
oc+0.040
icer+0.040
Neg logit contributions
kered-0.032
iggle-0.031
ered-0.028
ped-0.026
ia-0.026
Token't
Token ID470
Feature activation+2.95e-02

Pos logit contributions
kered+0.009
iggle+0.009
ered+0.008
 happen+0.007
ves+0.007
Neg logit contributions
 butcher-0.020
iw-0.019
 paramed-0.019
icer-0.018
oc-0.018
Token you
Token ID345
Feature activation+1.65e-03

Pos logit contributions
kered+0.050
iggle+0.049
ered+0.044
 danced+0.042
ia+0.042
Neg logit contributions
 butcher-0.057
 paramed-0.054
icer-0.049
iw-0.048
oc-0.048
Token recommendation
Token ID15602
Feature activation-1.68e-02

Pos logit contributions
 butcher+0.049
 paramed+0.045
riger+0.044
icer+0.044
iw+0.043
Neg logit contributions
kered-0.045
iggle-0.043
ered-0.041
ped-0.039
ia-0.039
Token and
Token ID290
Feature activation-1.81e-02

Pos logit contributions
 butcher+0.036
 paramed+0.034
riger+0.031
icer+0.030
uf+0.030
Neg logit contributions
kered-0.025
iggle-0.024
ered-0.022
ped-0.021
ia-0.021
Token picked
Token ID6497
Feature activation-1.49e-02

Pos logit contributions
 butcher+0.035
 paramed+0.033
oc+0.029
 sausage+0.028
iw+0.028
Neg logit contributions
kered-0.030
iggle-0.029
ia-0.026
ped-0.025
 flashed-0.025
Token the
Token ID262
Feature activation-4.58e-02

Pos logit contributions
 butcher+0.037
 paramed+0.037
riger+0.035
uf+0.033
icer+0.033
Neg logit contributions
kered-0.017
iggle-0.015
ered-0.014
ped-0.014
 flew-0.012
Token right
Token ID826
Feature activation-2.41e-02

Pos logit contributions
riger+0.078
enn+0.076
uf+0.075
 paramed+0.074
oc+0.073
Neg logit contributions
kered-0.069
 idea-0.068
ped-0.068
 blinked-0.068
 glow-0.067
Token av
Token ID1196
Feature activation-7.78e-02

Pos logit contributions
 butcher+0.050
riger+0.048
 paramed+0.048
uf+0.047
Charl+0.047
Neg logit contributions
ered-0.034
kered-0.033
iggle-0.032
ped-0.029
 blinked-0.028
Tokenoc
Token ID420
Feature activation-6.09e-02

Pos logit contributions
 paramed+0.106
 stret+0.084
 butcher+0.083
 charity+0.077
 Mechan+0.071
Neg logit contributions
kered-0.178
iggle-0.161
 flew-0.157
ped-0.151
 soared-0.150
Tokenados
Token ID22484
Feature activation-6.32e-02

Pos logit contributions
Charl+0.108
riger+0.107
Which+0.101
 butcher+0.101
 charity+0.099
Neg logit contributions
kered-0.103
ped-0.102
ered-0.092
iggle-0.087
ia-0.079
Token.
Token ID13
Feature activation-9.09e-03

Pos logit contributions
 paramed+0.157
 butcher+0.152
icer+0.141
uf+0.137
Mic+0.136
Neg logit contributions
kered-0.070
iggle-0.069
ered-0.062
 flew-0.060
 happen-0.058
Token
Token ID198
Feature activation-1.07e-02

Pos logit contributions
 butcher+0.018
 paramed+0.018
riger+0.017
use+0.016
 dollars+0.016
Neg logit contributions
kered-0.013
iggle-0.013
ia-0.012
 blinked-0.011
ped-0.011
Token
Token ID198
Feature activation-1.99e-02

Pos logit contributions
 butcher+0.020
 paramed+0.019
riger+0.017
 dollars+0.016
icer+0.016
Neg logit contributions
kered-0.019
iggle-0.019
ia-0.017
ered-0.017
ped-0.016
Token.
Token ID13
Feature activation-6.03e-02

Pos logit contributions
 butcher+0.045
 paramed+0.044
riger+0.042
icer+0.041
oc+0.040
Neg logit contributions
kered-0.021
iggle-0.020
ia-0.019
ped-0.018
ered-0.017
Token Johnson
Token ID5030
Feature activation-1.74e-02

Pos logit contributions
 butcher+0.072
 dollars+0.064
 paramed+0.064
riger+0.061
uf+0.060
Neg logit contributions
kered-0.128
iggle-0.124
 blinked-0.123
ped-0.122
ered-0.119
Token asked
Token ID1965
Feature activation-5.10e-02

Pos logit contributions
 butcher+0.042
 paramed+0.039
riger+0.036
icer+0.036
uf+0.036
Neg logit contributions
kered-0.021
iggle-0.020
ered-0.018
ped-0.017
ia-0.017
Token Lily
Token ID20037
Feature activation-4.16e-02

Pos logit contributions
riger+0.125
icer+0.125
fing+0.123
 paramed+0.122
 butcher+0.121
Neg logit contributions
iggle-0.038
kered-0.037
ered-0.035
ia-0.034
ped-0.034
Token,
Token ID11
Feature activation-7.64e-02

Pos logit contributions
 paramed+0.090
 butcher+0.088
icer+0.087
riger+0.084
 stret+0.081
Neg logit contributions
iggle-0.054
ered-0.048
kered-0.047
owed-0.045
ia-0.045
Token "
Token ID366
Feature activation-7.70e-02

Pos logit contributions
icer+0.218
arp+0.201
 butcher+0.199
riger+0.195
arre+0.193
Neg logit contributions
 blinked-0.038
fully-0.036
 danced-0.033
 opened-0.032
 flew-0.030
TokenDo
Token ID5211
Feature activation-1.07e-03

Pos logit contributions
uf+0.124
riger+0.121
arre+0.115
 dollars+0.113
icer+0.113
Neg logit contributions
 flew-0.117
 blinked-0.106
 danced-0.097
 sang-0.097
 soared-0.096
Token you
Token ID345
Feature activation-1.60e-02

Pos logit contributions
 butcher+0.002
 paramed+0.001
riger+0.001
uf+0.001
 Which+0.001
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.002
ped-0.002
 flashed-0.002
Token need
Token ID761
Feature activation-3.96e-02

Pos logit contributions
 butcher+0.031
 paramed+0.029
riger+0.026
uf+0.026
oc+0.026
Neg logit contributions
kered-0.027
iggle-0.026
ered-0.024
ped-0.024
ia-0.023
Token a
Token ID257
Feature activation-3.47e-02

Pos logit contributions
 butcher+0.080
 paramed+0.076
oc+0.072
icer+0.071
riger+0.069
Neg logit contributions
kered-0.061
iggle-0.058
ered-0.056
ped-0.053
 danced-0.052
Token tutor
Token ID48680
Feature activation-4.08e-02

Pos logit contributions
icer+0.070
 paramed+0.067
oc+0.066
och+0.066
riger+0.066
Neg logit contributions
 glow-0.038
 moves-0.037
 idea-0.037
 dance-0.037
iggle-0.036
Token for
Token ID329
Feature activation-3.95e-02

Pos logit contributions
 paramed+0.078
 butcher+0.077
riger+0.070
icer+0.067
iw+0.066
Neg logit contributions
iggle-0.052
kered-0.050
ered-0.045
ia-0.045
ped-0.043
Token being
Token ID852
Feature activation-3.14e-02

Pos logit contributions
 butcher+0.078
 paramed+0.072
icer+0.069
oc+0.068
riger+0.068
Neg logit contributions
kered-0.065
iggle-0.062
ered-0.060
ped-0.058
 danced-0.055
Token honest
Token ID5508
Feature activation-2.82e-02

Pos logit contributions
 butcher+0.066
 paramed+0.061
icer+0.059
riger+0.058
oc+0.057
Neg logit contributions
kered-0.048
iggle-0.045
ered-0.043
ped-0.042
 blinked-0.040
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
 butcher+0.056
 paramed+0.053
riger+0.048
icer+0.047
uf+0.047
Neg logit contributions
kered-0.046
iggle-0.044
ered-0.040
ped-0.039
ia-0.038
Token said
Token ID531
Feature activation-4.03e-02

Pos logit contributions
 butcher+0.056
 paramed+0.052
oc+0.046
 sausage+0.045
iw+0.044
Neg logit contributions
iggle-0.050
kered-0.048
ia-0.044
ered-0.041
atively-0.040
Token,
Token ID11
Feature activation-7.66e-02

Pos logit contributions
 butcher+0.083
 paramed+0.077
icer+0.073
riger+0.071
uf+0.070
Neg logit contributions
kered-0.066
iggle-0.062
ered-0.057
ped-0.055
ia-0.053
Token "
Token ID366
Feature activation-5.02e-02

Pos logit contributions
 butcher+0.160
icer+0.156
iw+0.147
 paramed+0.147
etchup+0.144
Neg logit contributions
kered-0.103
iggle-0.098
atively-0.094
ped-0.092
 blinked-0.092
TokenYou
Token ID1639
Feature activation-1.99e-02

Pos logit contributions
 butcher+0.078
 paramed+0.074
riger+0.067
uf+0.066
icer+0.063
Neg logit contributions
kered-0.105
iggle-0.095
ped-0.093
 flew-0.091
 blinked-0.091
Token are
Token ID389
Feature activation-9.89e-03

Pos logit contributions
 butcher+0.041
 paramed+0.037
icer+0.034
riger+0.034
iw+0.033
Neg logit contributions
kered-0.033
iggle-0.031
ered-0.029
ped-0.028
 danced-0.027
Token a
Token ID257
Feature activation-2.90e-02

Pos logit contributions
 butcher+0.022
 paramed+0.021
oc+0.020
icer+0.020
riger+0.019
Neg logit contributions
kered-0.014
iggle-0.013
ered-0.012
ped-0.012
 flew-0.012
Token good
Token ID922
Feature activation-2.00e-02

Pos logit contributions
 butcher+0.062
icer+0.062
riger+0.059
 paramed+0.059
 Which+0.059
Neg logit contributions
kered-0.033
 flew-0.030
 blinked-0.029
 danced-0.029
 moves-0.028
TokenMrs
Token ID27034
Feature activation-1.88e-02

Pos logit contributions
 butcher+0.081
 paramed+0.080
icer+0.076
iw+0.075
uf+0.074
Neg logit contributions
kered-0.061
iggle-0.053
ia-0.051
 flew-0.050
 danced-0.049
Token.
Token ID13
Feature activation-6.03e-02

Pos logit contributions
 butcher+0.045
 paramed+0.044
riger+0.042
icer+0.041
oc+0.040
Neg logit contributions
kered-0.021
iggle-0.020
ia-0.019
ped-0.018
ered-0.017
Token Johnson
Token ID5030
Feature activation-1.74e-02

Pos logit contributions
 butcher+0.072
 dollars+0.064
 paramed+0.064
riger+0.061
uf+0.060
Neg logit contributions
kered-0.128
iggle-0.124
 blinked-0.123
ped-0.122
ered-0.119
Token asked
Token ID1965
Feature activation-5.10e-02

Pos logit contributions
 butcher+0.042
 paramed+0.039
riger+0.036
icer+0.036
uf+0.036
Neg logit contributions
kered-0.021
iggle-0.020
ered-0.018
ped-0.017
ia-0.017
Token Lily
Token ID20037
Feature activation-4.16e-02

Pos logit contributions
riger+0.125
icer+0.125
fing+0.123
 paramed+0.122
 butcher+0.121
Neg logit contributions
iggle-0.038
kered-0.037
ered-0.035
ia-0.034
ped-0.034
Token,
Token ID11
Feature activation-7.64e-02

Pos logit contributions
 paramed+0.090
 butcher+0.088
icer+0.087
riger+0.084
 stret+0.081
Neg logit contributions
iggle-0.054
ered-0.048
kered-0.047
owed-0.045
ia-0.045
Token "
Token ID366
Feature activation-7.70e-02

Pos logit contributions
icer+0.218
arp+0.201
 butcher+0.199
riger+0.195
arre+0.193
Neg logit contributions
 blinked-0.038
fully-0.036
 danced-0.033
 opened-0.032
 flew-0.030
TokenDo
Token ID5211
Feature activation-1.07e-03

Pos logit contributions
uf+0.124
riger+0.121
arre+0.115
 dollars+0.113
icer+0.113
Neg logit contributions
 flew-0.117
 blinked-0.106
 danced-0.097
 sang-0.097
 soared-0.096
Token you
Token ID345
Feature activation-1.60e-02

Pos logit contributions
 butcher+0.002
 paramed+0.001
riger+0.001
uf+0.001
 Which+0.001
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.002
ped-0.002
 flashed-0.002
Token need
Token ID761
Feature activation-3.96e-02

Pos logit contributions
 butcher+0.031
 paramed+0.029
riger+0.026
uf+0.026
oc+0.026
Neg logit contributions
kered-0.027
iggle-0.026
ered-0.024
ped-0.024
ia-0.023
Token a
Token ID257
Feature activation-3.47e-02

Pos logit contributions
 butcher+0.080
 paramed+0.076
oc+0.072
icer+0.071
riger+0.069
Neg logit contributions
kered-0.061
iggle-0.058
ered-0.056
ped-0.053
 danced-0.052
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
 paramed+0.124
 butcher+0.123
icer+0.114
oc+0.114
uf+0.114
Neg logit contributions
kered-0.049
iggle-0.044
ped-0.039
ered-0.038
 flew-0.038
Token Lucy
Token ID22162
Feature activation-1.14e-02

Pos logit contributions
 butcher+0.053
 paramed+0.051
icer+0.049
riger+0.049
 dollars+0.048
Neg logit contributions
kered-0.036
iggle-0.034
 blinked-0.032
ia-0.031
ered-0.031
Token smiled
Token ID13541
Feature activation-3.86e-03

Pos logit contributions
 butcher+0.029
 paramed+0.027
riger+0.025
icer+0.025
uf+0.025
Neg logit contributions
kered-0.013
iggle-0.012
ered-0.011
ped-0.010
ia-0.010
Token and
Token ID290
Feature activation-1.37e-02

Pos logit contributions
 butcher+0.007
 paramed+0.006
oc+0.006
uf+0.006
riger+0.006
Neg logit contributions
kered-0.007
iggle-0.007
ered-0.006
ped-0.006
ia-0.006
Token asked
Token ID1965
Feature activation-4.20e-02

Pos logit contributions
 butcher+0.030
 paramed+0.028
uf+0.025
 sausage+0.025
riger+0.025
Neg logit contributions
kered-0.020
iggle-0.020
ia-0.016
ered-0.016
ped-0.015
Token "
Token ID366
Feature activation-7.61e-02

Pos logit contributions
 paramed+0.087
 butcher+0.086
icer+0.084
riger+0.081
arre+0.080
Neg logit contributions
kered-0.055
iggle-0.054
ered-0.053
ped-0.048
ia-0.047
TokenMay
Token ID6747
Feature activation-5.30e-03

Pos logit contributions
 paramed+0.122
enn+0.116
arre+0.115
 dollars+0.108
 stret+0.107
Neg logit contributions
 blinked-0.097
 herself-0.091
 flew-0.090
atively-0.089
bee-0.088
Token I
Token ID314
Feature activation-3.99e-02

Pos logit contributions
 butcher+0.010
 paramed+0.010
icer+0.009
 stret+0.009
Mic+0.009
Neg logit contributions
kered-0.008
ia-0.007
iggle-0.007
ered-0.007
owed-0.007
Token have
Token ID423
Feature activation-3.42e-02

Pos logit contributions
 butcher+0.086
 paramed+0.082
Mic+0.081
 stret+0.079
icer+0.078
Neg logit contributions
ered-0.049
iggle-0.048
kered-0.047
 danced-0.046
 flew-0.046
Token one
Token ID530
Feature activation-3.01e-02

Pos logit contributions
 butcher+0.077
 paramed+0.075
oc+0.072
riger+0.070
icer+0.069
Neg logit contributions
kered-0.039
ered-0.039
 flew-0.037
 danced-0.035
iggle-0.035
Token?"
Token ID1701
Feature activation-1.41e-02

Pos logit contributions
 paramed+0.070
 butcher+0.068
riger+0.066
Mic+0.066
Charl+0.064
Neg logit contributions
iggle-0.031
ia-0.030
ered-0.030
kered-0.029
 flew-0.027
Token food
Token ID2057
Feature activation-3.24e-02

Pos logit contributions
uf+0.039
enn+0.038
oc+0.038
 paramed+0.038
riger+0.037
Neg logit contributions
kered-0.030
 shapes-0.030
atively-0.030
 idea-0.030
 glow-0.030
Token they
Token ID484
Feature activation-3.10e-02

Pos logit contributions
 butcher+0.071
 paramed+0.067
riger+0.061
uf+0.060
oc+0.060
Neg logit contributions
kered-0.047
iggle-0.044
ered-0.040
ped-0.039
ia-0.038
Token bought
Token ID5839
Feature activation-1.47e-02

Pos logit contributions
 butcher+0.072
 paramed+0.069
uf+0.063
icer+0.062
 Which+0.062
Neg logit contributions
kered-0.041
iggle-0.038
ered-0.035
 danced-0.035
ped-0.033
Token from
Token ID422
Feature activation-2.64e-02

Pos logit contributions
 butcher+0.031
 paramed+0.029
riger+0.026
uf+0.026
icer+0.026
Neg logit contributions
kered-0.023
iggle-0.022
ered-0.020
ped-0.019
ia-0.019
Token the
Token ID262
Feature activation-3.70e-02

Pos logit contributions
 butcher+0.061
 paramed+0.059
riger+0.056
Mic+0.054
och+0.053
Neg logit contributions
kered-0.032
iggle-0.032
ered-0.030
ped-0.027
 flashed-0.027
Token grocery
Token ID16918
Feature activation-7.56e-02

Pos logit contributions
enn+0.064
arre+0.063
 paramed+0.062
fing+0.062
uf+0.061
Neg logit contributions
atively-0.054
 glow-0.053
 texture-0.052
 idea-0.052
 shapes-0.051
Token store
Token ID3650
Feature activation-3.94e-02

Pos logit contributions
 paramed+0.141
uf+0.137
Charl+0.134
Mic+0.134
arre+0.134
Neg logit contributions
 started-0.094
 opened-0.093
 flew-0.089
atively-0.089
 moves-0.088
Token.
Token ID13
Feature activation-6.36e-03

Pos logit contributions
 butcher+0.094
 paramed+0.091
icer+0.090
Mic+0.088
riger+0.087
Neg logit contributions
kered-0.045
iggle-0.040
ered-0.036
 danced-0.034
 flew-0.034
Token<|endoftext|>
Token ID50256
Feature activation-3.83e-02

Pos logit contributions
 butcher+0.013
 paramed+0.012
riger+0.012
 dollars+0.012
use+0.012
Neg logit contributions
kered-0.009
iggle-0.009
ped-0.008
ered-0.008
ia-0.008
TokenOnce
Token ID7454
Feature activation-1.43e-02

Pos logit contributions
 butcher+0.066
 paramed+0.064
riger+0.055
uf+0.053
 dollars+0.053
Neg logit contributions
kered-0.072
iggle-0.070
ered-0.064
ia-0.064
ped-0.063
Token upon
Token ID2402
Feature activation+3.00e-02

Pos logit contributions
 butcher+0.024
 paramed+0.022
icer+0.019
oc+0.019
riger+0.019
Neg logit contributions
kered-0.029
iggle-0.026
ered-0.025
ped-0.025
 flashed-0.024
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
 butcher+0.101
 paramed+0.098
riger+0.090
Mic+0.088
 Which+0.087
Neg logit contributions
kered-0.058
iggle-0.056
ered-0.050
ia-0.047
ped-0.046
Token He
Token ID679
Feature activation-1.24e-02

Pos logit contributions
riger+0.046
 paramed+0.046
use+0.045
 butcher+0.045
Mic+0.044
Neg logit contributions
ia-0.022
kered-0.021
iggle-0.020
atively-0.019
 blinked-0.019
Token gave
Token ID2921
Feature activation-1.15e-02

Pos logit contributions
 butcher+0.029
 paramed+0.028
oc+0.025
uf+0.025
riger+0.025
Neg logit contributions
kered-0.016
iggle-0.015
ered-0.013
ped-0.013
ia-0.012
Token the
Token ID262
Feature activation-2.16e-02

Pos logit contributions
 butcher+0.026
 paramed+0.025
riger+0.024
oc+0.023
uf+0.023
Neg logit contributions
kered-0.015
iggle-0.014
ered-0.014
ped-0.013
 blinked-0.012
Token ice
Token ID4771
Feature activation-3.39e-02

Pos logit contributions
riger+0.039
Mic+0.038
 paramed+0.038
 butcher+0.038
arre+0.037
Neg logit contributions
kered-0.032
 blinked-0.030
ered-0.029
 idea-0.029
ped-0.028
Token cream
Token ID8566
Feature activation-7.55e-02

Pos logit contributions
 butcher+0.068
Mic+0.066
Charl+0.065
 paramed+0.064
riger+0.064
Neg logit contributions
kered-0.054
ered-0.048
ped-0.047
iggle-0.045
ia-0.044
Token to
Token ID284
Feature activation-2.15e-02

Pos logit contributions
Mic+0.160
riger+0.157
Charl+0.156
arre+0.156
 paramed+0.153
Neg logit contributions
kered-0.099
atively-0.087
ped-0.084
 flew-0.082
 blinked-0.081
Token the
Token ID262
Feature activation-3.30e-02

Pos logit contributions
 butcher+0.047
 paramed+0.046
riger+0.042
oc+0.041
iw+0.041
Neg logit contributions
iggle-0.030
kered-0.029
ered-0.028
ia-0.025
ped-0.025
Token waiter
Token ID46612
Feature activation-3.39e-02

Pos logit contributions
 paramed+0.055
 butcher+0.054
riger+0.053
oc+0.051
icer+0.051
Neg logit contributions
kered-0.057
iggle-0.054
ia-0.050
ped-0.050
ered-0.050
Token as
Token ID355
Feature activation-1.46e-02

Pos logit contributions
 butcher+0.076
 paramed+0.073
Mic+0.068
riger+0.067
icer+0.067
Neg logit contributions
kered-0.046
iggle-0.043
ered-0.040
ped-0.037
 danced-0.037
Token a
Token ID257
Feature activation-4.73e-02

Pos logit contributions
 butcher+0.030
 paramed+0.027
 sausage+0.024
iw+0.024
oc+0.024
Neg logit contributions
kered-0.023
iggle-0.023
ered-0.020
ped-0.020
ia-0.019
Token neighbour
Token ID12250
Feature activation-4.67e-02

Pos logit contributions
 butcher+0.028
 paramed+0.026
riger+0.023
uf+0.023
oc+0.023
Neg logit contributions
kered-0.021
iggle-0.020
ered-0.018
ped-0.017
ia-0.017
Token,
Token ID11
Feature activation-6.42e-02

Pos logit contributions
 paramed+0.097
 butcher+0.096
icer+0.094
riger+0.092
oc+0.090
Neg logit contributions
iggle-0.061
ia-0.055
kered-0.054
ered-0.054
owed-0.052
Token Mrs
Token ID9074
Feature activation-3.26e-02

Pos logit contributions
icer+0.153
oc+0.147
 butcher+0.142
arre+0.141
riger+0.141
Neg logit contributions
 blinked-0.063
iggle-0.057
 flew-0.057
 danced-0.057
 opened-0.056
Token Clar
Token ID15420
Feature activation-2.86e-02

Pos logit contributions
 paramed+0.081
 butcher+0.078
riger+0.073
icer+0.073
arre+0.073
Neg logit contributions
iggle-0.032
kered-0.032
ia-0.031
 blinked-0.026
ped-0.026
Tokenise
Token ID786
Feature activation-4.44e-02

Pos logit contributions
 butcher+0.053
 paramed+0.049
Mic+0.046
oc+0.044
 Which+0.044
Neg logit contributions
kered-0.048
iggle-0.048
ered-0.048
ia-0.045
ped-0.043
Token,
Token ID11
Feature activation-7.55e-02

Pos logit contributions
 butcher+0.095
 paramed+0.091
riger+0.090
icer+0.086
iw+0.084
Neg logit contributions
kered-0.059
iggle-0.058
ia-0.053
ped-0.051
ered-0.050
Token for
Token ID329
Feature activation-3.72e-02

Pos logit contributions
icer+0.178
 butcher+0.176
oc+0.175
arre+0.172
 paramed+0.170
Neg logit contributions
 opened-0.065
 blinked-0.064
 legs-0.057
 knees-0.055
 flew-0.055
Token help
Token ID1037
Feature activation-2.82e-02

Pos logit contributions
 butcher+0.080
 paramed+0.075
oc+0.070
icer+0.069
riger+0.068
Neg logit contributions
kered-0.055
iggle-0.052
ered-0.049
ped-0.046
 danced-0.045
Token.
Token ID13
Feature activation-3.29e-02

Pos logit contributions
 butcher+0.068
 paramed+0.064
icer+0.060
iw+0.060
riger+0.059
Neg logit contributions
kered-0.035
iggle-0.034
ered-0.030
ped-0.027
 danced-0.026
Token
Token ID198
Feature activation-3.28e-02

Pos logit contributions
 butcher+0.069
icer+0.066
Mic+0.064
 paramed+0.064
P+0.064
Neg logit contributions
kered-0.040
iggle-0.038
ered-0.037
 blinked-0.036
ia-0.036
Token
Token ID198
Feature activation-4.37e-02

Pos logit contributions
 butcher+0.069
 paramed+0.069
 dollars+0.069
icer+0.067
 ju+0.066
Neg logit contributions
kered-0.037
ia-0.037
ves-0.034
iggle-0.034
ered-0.032
Token always
Token ID1464
Feature activation-1.90e-02

Pos logit contributions
 butcher+0.021
 paramed+0.020
riger+0.018
icer+0.018
uf+0.018
Neg logit contributions
kered-0.012
iggle-0.011
ered-0.010
 danced-0.010
ped-0.010
Token loved
Token ID6151
Feature activation-2.93e-02

Pos logit contributions
 butcher+0.040
 paramed+0.038
riger+0.035
oc+0.034
uf+0.034
Neg logit contributions
kered-0.029
iggle-0.028
ered-0.024
ia-0.024
ped-0.024
Token going
Token ID1016
Feature activation-2.85e-02

Pos logit contributions
 butcher+0.065
icer+0.064
oc+0.063
 paramed+0.063
riger+0.060
Neg logit contributions
iggle-0.032
 danced-0.032
kered-0.031
 flew-0.029
ered-0.029
Token to
Token ID284
Feature activation-2.61e-02

Pos logit contributions
oc+0.070
 paramed+0.067
 butcher+0.067
uf+0.066
icer+0.065
Neg logit contributions
iggle-0.028
 danced-0.025
 moves-0.025
ered-0.025
 flew-0.024
Token the
Token ID262
Feature activation-5.19e-02

Pos logit contributions
 butcher+0.065
 paramed+0.062
icer+0.061
och+0.060
oc+0.060
Neg logit contributions
iggle-0.025
ered-0.023
 happen-0.023
 danced-0.022
 moves-0.022
Token grocery
Token ID16918
Feature activation-7.54e-02

Pos logit contributions
och+0.085
oc+0.085
enn+0.085
 dollars+0.083
etchup+0.081
Neg logit contributions
 dance-0.079
 moves-0.074
 usual-0.071
 sound-0.071
 sounds-0.070
Token store
Token ID3650
Feature activation-3.73e-02

Pos logit contributions
 paramed+0.144
uf+0.133
ifying+0.132
Mic+0.131
icer+0.126
Neg logit contributions
iggle-0.096
 moves-0.093
 danced-0.092
 opened-0.091
 flew-0.091
Token with
Token ID351
Feature activation-2.32e-02

Pos logit contributions
 butcher+0.079
 paramed+0.077
icer+0.076
uf+0.074
Mic+0.073
Neg logit contributions
iggle-0.047
kered-0.046
 danced-0.042
ered-0.041
 flew-0.041
Token her
Token ID607
Feature activation-3.35e-02

Pos logit contributions
 butcher+0.062
 paramed+0.059
riger+0.056
oc+0.055
icer+0.055
Neg logit contributions
kered-0.022
iggle-0.021
ered-0.018
ped-0.016
ia-0.016
Token mom
Token ID1995
Feature activation-3.90e-02

Pos logit contributions
 butcher+0.082
 paramed+0.082
riger+0.081
arre+0.079
icer+0.078
Neg logit contributions
 danced-0.022
 colors-0.021
 knees-0.021
iggle-0.021
 shapes-0.020
Tokenmy
Token ID1820
Feature activation-4.70e-02

Pos logit contributions
 paramed+0.082
 butcher+0.081
riger+0.076
uf+0.072
 jun+0.071
Neg logit contributions
owed-0.048
iggle-0.047
 danced-0.046
 colors-0.044
 laughed-0.044
Token to
Token ID284
Feature activation-4.29e-02

Pos logit contributions
 butcher+0.106
 paramed+0.104
icer+0.094
oc+0.094
Mic+0.094
Neg logit contributions
kered-0.072
iggle-0.068
ered-0.064
ped-0.063
 flew-0.058
Token get
Token ID651
Feature activation-4.66e-02

Pos logit contributions
 butcher+0.075
 paramed+0.071
riger+0.064
icer+0.063
Mic+0.063
Neg logit contributions
kered-0.078
iggle-0.077
ered-0.074
 happen-0.067
ped-0.067
Token two
Token ID734
Feature activation-5.87e-02

Pos logit contributions
 butcher+0.097
oc+0.092
 paramed+0.091
Mic+0.089
riger+0.088
Neg logit contributions
kered-0.066
ered-0.065
iggle-0.064
ped-0.062
 flew-0.057
Token sa
Token ID473
Feature activation-5.94e-02

Pos logit contributions
 butcher+0.094
 paramed+0.093
Mic+0.092
iw+0.088
Charl+0.087
Neg logit contributions
kered-0.106
iggle-0.096
ered-0.094
 moves-0.093
ped-0.090
Tokenus
Token ID385
Feature activation-3.48e-02

Pos logit contributions
 paramed+0.095
 Which+0.087
Which+0.082
 butcher+0.080
 stret+0.080
Neg logit contributions
kered-0.123
ped-0.107
iggle-0.107
owed-0.101
ered-0.100
Tokenages
Token ID1095
Feature activation-7.53e-02

Pos logit contributions
 paramed+0.072
 butcher+0.071
 Which+0.068
Mic+0.068
iw+0.067
Neg logit contributions
kered-0.052
iggle-0.043
ped-0.043
ered-0.041
owed-0.039
Token.
Token ID13
Feature activation-7.08e-03

Pos logit contributions
 butcher+0.188
 paramed+0.187
icer+0.182
Mic+0.180
oc+0.175
Neg logit contributions
kered-0.076
iggle-0.068
ped-0.059
ered-0.058
 danced-0.055
Token
Token ID198
Feature activation-1.92e-02

Pos logit contributions
 butcher+0.013
 paramed+0.013
riger+0.012
icer+0.011
 dollars+0.011
Neg logit contributions
kered-0.012
iggle-0.012
ped-0.011
ered-0.010
ia-0.010
Token
Token ID198
Feature activation-2.32e-02

Pos logit contributions
 butcher+0.034
 paramed+0.034
riger+0.030
 dollars+0.029
iw+0.029
Neg logit contributions
kered-0.035
iggle-0.034
ia-0.031
ered-0.030
ped-0.030
TokenGary
Token ID33820
Feature activation-4.22e-03

Pos logit contributions
 paramed+0.042
 butcher+0.040
iw+0.037
icer+0.036
riger+0.035
Neg logit contributions
kered-0.043
iggle-0.039
ia-0.037
ered-0.036
 flew-0.036
Token knew
Token ID2993
Feature activation-1.14e-02

Pos logit contributions
 butcher+0.009
 paramed+0.009
oc+0.008
uf+0.008
riger+0.008
Neg logit contributions
kered-0.006
iggle-0.006
ered-0.005
 flashed-0.005
ped-0.005
Token give
Token ID1577
Feature activation-1.10e-02

Pos logit contributions
 butcher+0.033
 paramed+0.031
icer+0.028
riger+0.027
oc+0.027
Neg logit contributions
kered-0.030
iggle-0.030
ered-0.028
ped-0.026
ia-0.025
Token the
Token ID262
Feature activation-2.26e-02

Pos logit contributions
 butcher+0.029
 paramed+0.029
riger+0.027
uf+0.027
arre+0.026
Neg logit contributions
kered-0.010
ered-0.009
iggle-0.009
ped-0.008
 flew-0.007
Token cash
Token ID5003
Feature activation-1.90e-02

Pos logit contributions
 paramed+0.048
riger+0.047
oc+0.047
uf+0.047
 butcher+0.047
Neg logit contributions
kered-0.025
 idea-0.024
 moves-0.023
 shapes-0.023
 happen-0.023
Tokenier
Token ID959
Feature activation-3.08e-02

Pos logit contributions
 butcher+0.043
 paramed+0.041
icer+0.039
riger+0.039
Mic+0.038
Neg logit contributions
kered-0.027
iggle-0.024
ered-0.022
ia-0.021
ped-0.021
Token some
Token ID617
Feature activation-4.79e-02

Pos logit contributions
 butcher+0.069
 paramed+0.067
Mic+0.063
riger+0.062
uf+0.061
Neg logit contributions
kered-0.042
iggle-0.038
ered-0.038
ped-0.035
ia-0.033
Token money
Token ID1637
Feature activation-7.50e-02

Pos logit contributions
 butcher+0.105
 paramed+0.103
riger+0.099
icer+0.098
Mic+0.097
Neg logit contributions
kered-0.066
iggle-0.057
ered-0.055
ped-0.053
 moves-0.051
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
 paramed+0.173
 butcher+0.172
icer+0.160
Mic+0.160
oc+0.155
Neg logit contributions
kered-0.093
iggle-0.083
ered-0.079
ped-0.077
owed-0.072
Token Tim
Token ID5045
Feature activation-5.24e-03

Pos logit contributions
 butcher+0.036
riger+0.034
 dollars+0.033
 paramed+0.032
use+0.032
Neg logit contributions
kered-0.020
iggle-0.020
ered-0.017
ia-0.017
ped-0.017
Tokenmy
Token ID1820
Feature activation-1.49e-03

Pos logit contributions
 butcher+0.006
 paramed+0.006
riger+0.005
oc+0.004
uf+0.004
Neg logit contributions
kered-0.013
iggle-0.013
ered-0.012
ped-0.012
ia-0.011
Token got
Token ID1392
Feature activation-3.61e-02

Pos logit contributions
 butcher+0.004
 paramed+0.003
oc+0.003
uf+0.003
riger+0.003
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.001
ped-0.001
 flashed-0.001
Token frustrated
Token ID14718
Feature activation-6.82e-03

Pos logit contributions
 butcher+0.082
riger+0.079
Mic+0.078
Charl+0.078
uf+0.077
Neg logit contributions
ered-0.046
kered-0.045
ped-0.040
iggle-0.040
 flew-0.036
Token was
Token ID373
Feature activation-3.18e-02

Pos logit contributions
 butcher+0.037
 paramed+0.035
riger+0.033
uf+0.033
icer+0.033
Neg logit contributions
kered-0.018
iggle-0.017
ered-0.016
 danced-0.015
 flew-0.015
Token walking
Token ID6155
Feature activation-2.89e-02

Pos logit contributions
 butcher+0.067
oc+0.064
icer+0.061
 paramed+0.060
iw+0.060
Neg logit contributions
iggle-0.044
kered-0.042
ered-0.041
 danced-0.039
 flew-0.038
Token home
Token ID1363
Feature activation-1.82e-02

Pos logit contributions
 butcher+0.061
 paramed+0.059
riger+0.056
uf+0.056
icer+0.054
Neg logit contributions
iggle-0.041
kered-0.041
ped-0.037
ered-0.036
 danced-0.036
Token from
Token ID422
Feature activation-2.96e-02

Pos logit contributions
 butcher+0.038
 paramed+0.036
riger+0.032
icer+0.032
oc+0.032
Neg logit contributions
kered-0.028
iggle-0.027
ered-0.024
ped-0.024
ia-0.023
Token the
Token ID262
Feature activation-5.21e-02

Pos logit contributions
 butcher+0.062
 paramed+0.059
riger+0.054
oc+0.054
uf+0.054
Neg logit contributions
kered-0.042
iggle-0.042
ered-0.039
ped-0.037
 flashed-0.036
Token grocery
Token ID16918
Feature activation-7.49e-02

Pos logit contributions
oc+0.100
etchup+0.093
 dollars+0.093
fing+0.093
smart+0.093
Neg logit contributions
 sound-0.069
 light-0.064
 dance-0.062
 started-0.062
 noise-0.061
Token store
Token ID3650
Feature activation-2.82e-02

Pos logit contributions
 paramed+0.138
ksh+0.137
Mic+0.135
riger+0.134
Charl+0.133
Neg logit contributions
 started-0.090
 opened-0.086
 sound-0.085
 flew-0.083
iggle-0.082
Token when
Token ID618
Feature activation+4.37e-03

Pos logit contributions
 butcher+0.061
 paramed+0.059
riger+0.056
icer+0.056
oc+0.055
Neg logit contributions
iggle-0.037
kered-0.037
ered-0.032
 flew-0.031
 danced-0.031
Token something
Token ID1223
Feature activation-2.26e-02

Pos logit contributions
kered+0.006
iggle+0.006
ered+0.005
ped+0.005
ia+0.005
Neg logit contributions
 butcher-0.010
 paramed-0.009
 Which-0.008
riger-0.008
uf-0.008
Token wonderful
Token ID7932
Feature activation-1.71e-03

Pos logit contributions
 butcher+0.041
 paramed+0.039
riger+0.034
 Which+0.033
uf+0.033
Neg logit contributions
kered-0.041
iggle-0.039
ped-0.035
ered-0.035
ia-0.034
Token happened
Token ID3022
Feature activation-1.93e-02

Pos logit contributions
 butcher+0.004
 paramed+0.004
 sausage+0.003
riger+0.003
 cart+0.003
Neg logit contributions
kered-0.002
iggle-0.002
ia-0.002
ered-0.002
irled-0.001
Token an
Token ID281
Feature activation-2.53e-02

Pos logit contributions
 butcher+0.050
 paramed+0.047
icer+0.044
 dollars+0.044
riger+0.044
Neg logit contributions
iggle-0.028
kered-0.028
ered-0.026
ped-0.023
 blinked-0.023
Token old
Token ID1468
Feature activation-4.23e-02

Pos logit contributions
 butcher+0.049
 paramed+0.046
riger+0.044
icer+0.044
iw+0.043
Neg logit contributions
kered-0.039
iggle-0.039
ered-0.038
ped-0.034
ia-0.034
Token man
Token ID582
Feature activation-3.72e-02

Pos logit contributions
icer+0.074
 butcher+0.073
riger+0.073
 paramed+0.071
arre+0.071
Neg logit contributions
 blinked-0.059
iggle-0.059
 knees-0.058
kered-0.058
ered-0.058
Token and
Token ID290
Feature activation-3.77e-02

Pos logit contributions
 butcher+0.073
 paramed+0.072
icer+0.068
Mic+0.066
 Which+0.065
Neg logit contributions
ered-0.053
iggle-0.053
kered-0.052
owed-0.050
 flew-0.050
Token asked
Token ID1965
Feature activation-3.82e-02

Pos logit contributions
 butcher+0.093
 paramed+0.088
icer+0.086
riger+0.084
uf+0.082
Neg logit contributions
kered-0.040
ered-0.036
iggle-0.036
 blinked-0.034
 flew-0.034
Token,
Token ID11
Feature activation-7.47e-02

Pos logit contributions
 butcher+0.080
 paramed+0.079
icer+0.075
riger+0.074
arre+0.072
Neg logit contributions
kered-0.053
ered-0.052
iggle-0.051
ped-0.047
ia-0.045
Token "
Token ID366
Feature activation-6.99e-02

Pos logit contributions
icer+0.194
 butcher+0.178
arre+0.171
iw+0.171
oc+0.170
Neg logit contributions
 blinked-0.060
 opened-0.056
atively-0.053
 flew-0.052
ered-0.051
TokenPlease
Token ID5492
Feature activation-2.08e-02

Pos logit contributions
 dollars+0.111
 paramed+0.109
arre+0.107
ip+0.106
icer+0.101
Neg logit contributions
 flew-0.095
 blinked-0.091
ered-0.088
ped-0.084
atively-0.082
Token,
Token ID11
Feature activation-4.92e-02

Pos logit contributions
 butcher+0.045
 paramed+0.042
icer+0.040
arre+0.039
Mic+0.039
Neg logit contributions
kered-0.028
iggle-0.027
ered-0.027
ia-0.024
 flew-0.024
Token could
Token ID714
Feature activation+1.07e-02

Pos logit contributions
icer+0.097
iw+0.093
 butcher+0.091
arre+0.090
Mic+0.089
Neg logit contributions
ered-0.063
ia-0.060
 flew-0.058
 opened-0.058
kered-0.057
Token you
Token ID345
Feature activation+3.20e-03

Pos logit contributions
kered+0.018
iggle+0.017
ered+0.016
ped+0.015
 flew+0.015
Neg logit contributions
 butcher-0.021
 paramed-0.020
icer-0.018
oc-0.018
riger-0.018
Token a
Token ID257
Feature activation-1.94e-02

Pos logit contributions
kered+0.030
iggle+0.028
ered+0.027
owed+0.025
ped+0.025
Neg logit contributions
 butcher-0.036
 paramed-0.033
Mic-0.030
icer-0.030
uf-0.029
Token kind
Token ID1611
Feature activation-1.93e-02

Pos logit contributions
 butcher+0.047
 paramed+0.045
riger+0.045
 Which+0.045
use+0.044
Neg logit contributions
iggle-0.017
kered-0.016
ia-0.016
 danced-0.016
 blinked-0.015
Token man
Token ID582
Feature activation-2.39e-03

Pos logit contributions
 butcher+0.039
riger+0.039
icer+0.037
 Which+0.037
 paramed+0.036
Neg logit contributions
kered-0.027
iggle-0.027
ia-0.025
 danced-0.023
 blinked-0.022
Token named
Token ID3706
Feature activation-3.19e-02

Pos logit contributions
 butcher+0.004
 paramed+0.004
riger+0.004
icer+0.004
 Which+0.004
Neg logit contributions
kered-0.004
iggle-0.004
 danced-0.004
 flew-0.004
ered-0.004
Token Mr
Token ID1770
Feature activation-2.89e-02

Pos logit contributions
 butcher+0.065
 paramed+0.064
oc+0.059
arre+0.057
riger+0.057
Neg logit contributions
kered-0.044
iggle-0.044
ia-0.039
ered-0.039
ped-0.038
Token.
Token ID13
Feature activation-7.46e-02

Pos logit contributions
 paramed+0.072
 butcher+0.071
riger+0.065
arre+0.065
icer+0.064
Neg logit contributions
kered-0.030
iggle-0.028
ia-0.026
 blinked-0.023
 flashed-0.022
Token Bear
Token ID14732
Feature activation-6.35e-03

Pos logit contributions
 paramed+0.109
 butcher+0.104
 dollars+0.096
 Which+0.095
oc+0.093
Neg logit contributions
kered-0.135
 blinked-0.128
iggle-0.127
 danced-0.124
ped-0.124
Token.
Token ID13
Feature activation-4.38e-02

Pos logit contributions
 butcher+0.014
 paramed+0.014
riger+0.013
icer+0.012
 Which+0.012
Neg logit contributions
kered-0.009
iggle-0.008
ered-0.007
ped-0.007
 danced-0.007
Token He
Token ID679
Feature activation-7.34e-03

Pos logit contributions
 paramed+0.088
 butcher+0.085
 dollars+0.082
fing+0.080
riger+0.080
Neg logit contributions
kered-0.055
iggle-0.054
 danced-0.051
 blinked-0.049
 glow-0.048
Token had
Token ID550
Feature activation-1.97e-02

Pos logit contributions
 butcher+0.016
 paramed+0.015
oc+0.014
uf+0.013
Mic+0.013
Neg logit contributions
kered-0.011
iggle-0.011
ered-0.010
ped-0.009
ia-0.009
Token a
Token ID257
Feature activation-2.42e-02

Pos logit contributions
 butcher+0.045
 paramed+0.043
riger+0.039
oc+0.039
uf+0.039
Neg logit contributions
kered-0.027
iggle-0.025
ered-0.022
ped-0.022
ia-0.021
Token a
Token ID257
Feature activation-1.50e-02

Pos logit contributions
kered+0.030
iggle+0.029
ered+0.028
owed+0.025
ped+0.025
Neg logit contributions
 butcher-0.038
 paramed-0.035
Mic-0.032
icer-0.032
uf-0.032
Token kind
Token ID1611
Feature activation-1.56e-02

Pos logit contributions
 butcher+0.036
 paramed+0.034
riger+0.034
 Which+0.034
use+0.033
Neg logit contributions
iggle-0.015
kered-0.014
ia-0.014
 danced-0.013
 blinked-0.013
Token man
Token ID582
Feature activation+6.45e-04

Pos logit contributions
 butcher+0.031
riger+0.030
icer+0.029
 Which+0.029
 paramed+0.029
Neg logit contributions
kered-0.022
iggle-0.022
ia-0.020
 danced-0.019
 blinked-0.019
Token named
Token ID3706
Feature activation-2.74e-02

Pos logit contributions
kered+0.001
iggle+0.001
 flew+0.001
 danced+0.001
ered+0.001
Neg logit contributions
 butcher-0.001
 paramed-0.001
riger-0.001
icer-0.001
 Which-0.001
Token Mr
Token ID1770
Feature activation-2.90e-02

Pos logit contributions
 butcher+0.057
 paramed+0.056
oc+0.050
arre+0.050
riger+0.049
Neg logit contributions
kered-0.038
iggle-0.038
ia-0.034
ered-0.034
ped-0.033
Token.
Token ID13
Feature activation-7.39e-02

Pos logit contributions
 paramed+0.075
 butcher+0.072
riger+0.067
arre+0.067
 Which+0.066
Neg logit contributions
kered-0.027
iggle-0.026
ia-0.025
 blinked-0.021
 flashed-0.020
Token Smith
Token ID4176
Feature activation+6.86e-04

Pos logit contributions
 paramed+0.110
 butcher+0.102
 Which+0.095
 dollars+0.094
arre+0.094
Neg logit contributions
kered-0.132
 blinked-0.127
iggle-0.125
 flew-0.123
ped-0.122
Token.
Token ID13
Feature activation-3.95e-02

Pos logit contributions
kered+0.001
iggle+0.001
ia+0.001
ered+0.001
 danced+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
riger-0.001
icer-0.001
Mic-0.001
Token He
Token ID679
Feature activation-9.12e-03

Pos logit contributions
 paramed+0.077
 butcher+0.075
arre+0.070
 dollars+0.070
riger+0.070
Neg logit contributions
kered-0.052
iggle-0.051
 blinked-0.049
 danced-0.047
 glow-0.046
Token had
Token ID550
Feature activation-1.92e-02

Pos logit contributions
 butcher+0.021
 paramed+0.019
oc+0.018
uf+0.017
Mic+0.017
Neg logit contributions
kered-0.013
iggle-0.013
ered-0.011
ped-0.010
ia-0.010
Token a
Token ID257
Feature activation-2.21e-02

Pos logit contributions
 butcher+0.044
 paramed+0.042
riger+0.038
oc+0.038
uf+0.038
Neg logit contributions
kered-0.026
iggle-0.024
ered-0.022
ped-0.021
ia-0.020
Token people
Token ID661
Feature activation-4.01e-02

Pos logit contributions
 butcher+0.036
 paramed+0.034
riger+0.031
icer+0.031
oc+0.031
Neg logit contributions
kered-0.026
iggle-0.024
ered-0.022
ped-0.021
ia-0.021
Token use
Token ID779
Feature activation-4.61e-02

Pos logit contributions
 butcher+0.085
 paramed+0.081
icer+0.073
riger+0.072
uf+0.072
Neg logit contributions
kered-0.060
iggle-0.058
ered-0.053
ped-0.051
 danced-0.049
Token to
Token ID284
Feature activation-5.08e-02

Pos logit contributions
 butcher+0.101
 paramed+0.098
riger+0.088
icer+0.088
Mic+0.088
Neg logit contributions
kered-0.065
iggle-0.062
ered-0.058
ped-0.056
 flew-0.053
Token buy
Token ID2822
Feature activation-3.47e-02

Pos logit contributions
 butcher+0.085
 paramed+0.083
icer+0.075
Mic+0.073
Charl+0.072
Neg logit contributions
kered-0.094
iggle-0.091
ered-0.089
 happen-0.082
 flew-0.081
Token things
Token ID1243
Feature activation-4.63e-02

Pos logit contributions
 butcher+0.076
 paramed+0.076
riger+0.069
Mic+0.068
icer+0.067
Neg logit contributions
kered-0.048
iggle-0.044
ered-0.043
ped-0.040
 flew-0.037
Token they
Token ID484
Feature activation-7.36e-02

Pos logit contributions
 paramed+0.110
 butcher+0.109
icer+0.103
Mic+0.100
uf+0.098
Neg logit contributions
kered-0.055
iggle-0.051
ered-0.048
 happen-0.047
 flew-0.045
Token want
Token ID765
Feature activation-4.10e-02

Pos logit contributions
 butcher+0.162
 paramed+0.162
icer+0.145
Mic+0.141
iw+0.140
Neg logit contributions
kered-0.098
iggle-0.094
ered-0.089
 danced-0.084
ped-0.082
Token or
Token ID393
Feature activation-3.12e-02

Pos logit contributions
 butcher+0.091
 paramed+0.089
riger+0.080
icer+0.080
Mic+0.079
Neg logit contributions
kered-0.057
iggle-0.054
ered-0.049
ped-0.047
ia-0.045
Token need
Token ID761
Feature activation-3.70e-02

Pos logit contributions
 butcher+0.061
 paramed+0.057
riger+0.051
oc+0.050
uf+0.050
Neg logit contributions
kered-0.052
iggle-0.050
ered-0.046
ped-0.044
ia-0.043
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
 butcher+0.084
 paramed+0.082
icer+0.076
riger+0.075
Mic+0.074
Neg logit contributions
kered-0.049
iggle-0.045
ered-0.043
ped-0.041
 flew-0.039
Token
Token ID198
Feature activation-4.55e-03

Pos logit contributions
kered+0.014
ia+0.014
iggle+0.014
 Lia+0.013
ered+0.012
Neg logit contributions
 butcher-0.022
 paramed-0.021
riger-0.020
Mic-0.020
use-0.019
Token happy
Token ID3772
Feature activation+1.42e-02

Pos logit contributions
 butcher+0.033
 paramed+0.032
oc+0.028
riger+0.027
uf+0.027
Neg logit contributions
kered-0.031
iggle-0.030
ered-0.027
ia-0.026
 flashed-0.026
Token!
Token ID0
Feature activation-6.93e-03

Pos logit contributions
kered+0.026
iggle+0.025
ered+0.023
ped+0.022
ia+0.022
Neg logit contributions
 butcher-0.026
 paramed-0.023
oc-0.021
riger-0.021
uf-0.021
Token He
Token ID679
Feature activation-2.88e-03

Pos logit contributions
 butcher+0.013
 paramed+0.013
riger+0.012
Mic+0.011
 charity+0.011
Neg logit contributions
kered-0.011
iggle-0.011
ia-0.010
ped-0.010
ered-0.010
Token thanked
Token ID26280
Feature activation+1.07e-03

Pos logit contributions
 butcher+0.006
 paramed+0.006
oc+0.006
uf+0.006
riger+0.006
Neg logit contributions
kered-0.004
iggle-0.004
ered-0.003
ia-0.003
ped-0.003
Token R
Token ID371
Feature activation-4.23e-02

Pos logit contributions
kered+0.001
iggle+0.001
ered+0.001
ia+0.001
ped+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
arre-0.002
riger-0.002
Mic-0.002
Tokenuf
Token ID3046
Feature activation-7.33e-02

Pos logit contributions
 paramed+0.038
riger+0.035
 Which+0.035
Which+0.035
 butcher+0.031
Neg logit contributions
iggle-0.105
kered-0.104
ia-0.104
ped-0.099
owed-0.098
Tokenus
Token ID385
Feature activation-1.83e-02

Pos logit contributions
 paramed+0.112
 stret+0.095
arre+0.095
riger+0.094
 Which+0.094
Neg logit contributions
ia-0.139
kered-0.136
ped-0.135
ered-0.129
owed-0.127
Token and
Token ID290
Feature activation-2.34e-02

Pos logit contributions
 butcher+0.036
 paramed+0.034
riger+0.031
icer+0.031
uf+0.030
Neg logit contributions
kered-0.030
iggle-0.029
ered-0.027
ped-0.026
ia-0.025
Token they
Token ID484
Feature activation-3.16e-03

Pos logit contributions
 butcher+0.056
 paramed+0.052
icer+0.049
riger+0.049
uf+0.048
Neg logit contributions
kered-0.029
iggle-0.027
ered-0.025
ped-0.024
 danced-0.023
Token became
Token ID2627
Feature activation-9.42e-03

Pos logit contributions
 butcher+0.007
 paramed+0.006
riger+0.006
oc+0.006
uf+0.006
Neg logit contributions
kered-0.005
iggle-0.004
ered-0.004
ped-0.004
ia-0.004
Token good
Token ID922
Feature activation-1.16e-02

Pos logit contributions
 butcher+0.022
 paramed+0.022
riger+0.021
icer+0.021
use+0.020
Neg logit contributions
kered-0.011
iggle-0.010
 flew-0.010
ered-0.009
ped-0.009
Token visit
Token ID3187
Feature activation-5.99e-03

Pos logit contributions
 butcher+0.034
 paramed+0.032
oc+0.029
riger+0.029
icer+0.029
Neg logit contributions
iggle-0.020
kered-0.019
ered-0.017
 danced-0.017
 blinked-0.016
Token their
Token ID511
Feature activation-7.15e-03

Pos logit contributions
 butcher+0.014
 paramed+0.013
riger+0.012
oc+0.012
icer+0.012
Neg logit contributions
kered-0.008
iggle-0.008
ered-0.007
ped-0.007
ia-0.007
Token neighbor
Token ID4780
Feature activation-2.47e-02

Pos logit contributions
 butcher+0.015
 paramed+0.014
riger+0.013
och+0.013
oc+0.013
Neg logit contributions
iggle-0.009
kered-0.009
ia-0.009
ered-0.008
 moves-0.008
Token,
Token ID11
Feature activation-2.77e-02

Pos logit contributions
 paramed+0.062
 butcher+0.060
riger+0.056
icer+0.055
Mic+0.055
Neg logit contributions
iggle-0.022
kered-0.020
ia-0.020
 danced-0.019
 flew-0.018
Token Mrs
Token ID9074
Feature activation-1.93e-02

Pos logit contributions
 butcher+0.061
 paramed+0.058
icer+0.054
riger+0.054
oc+0.053
Neg logit contributions
kered-0.037
iggle-0.036
ered-0.032
ia-0.032
 blinked-0.032
Token.
Token ID13
Feature activation-7.32e-02

Pos logit contributions
 paramed+0.047
 butcher+0.047
riger+0.044
arre+0.043
icer+0.043
Neg logit contributions
kered-0.020
iggle-0.019
ia-0.017
ped-0.017
ered-0.015
Token Lee
Token ID5741
Feature activation-2.81e-02

Pos logit contributions
 paramed+0.102
arre+0.100
fing+0.100
 butcher+0.097
 dollars+0.093
Neg logit contributions
kered-0.118
 blinked-0.118
 flashed-0.115
ped-0.115
 flew-0.114
Token.
Token ID13
Feature activation-4.53e-02

Pos logit contributions
 butcher+0.070
 paramed+0.067
icer+0.065
Mic+0.063
riger+0.062
Neg logit contributions
kered-0.028
iggle-0.026
ered-0.024
 danced-0.024
ia-0.023
Token Mrs
Token ID9074
Feature activation-1.56e-02

Pos logit contributions
 butcher+0.077
 paramed+0.076
fing+0.073
icer+0.072
arre+0.072
Neg logit contributions
kered-0.070
iggle-0.063
 blinked-0.061
 flashed-0.061
ped-0.061
Token.
Token ID13
Feature activation-6.11e-02

Pos logit contributions
 butcher+0.037
 paramed+0.037
riger+0.034
icer+0.034
Mic+0.033
Neg logit contributions
kered-0.017
iggle-0.016
ia-0.015
ped-0.014
ered-0.014
Token Lee
Token ID5741
Feature activation-1.79e-02

Pos logit contributions
 paramed+0.089
 butcher+0.089
arre+0.086
fing+0.085
oc+0.085
Neg logit contributions
kered-0.097
 blinked-0.096
ia-0.093
 rang-0.093
atively-0.092
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
kered+0.031
iggle+0.029
ered+0.028
ia+0.027
ped+0.026
Neg logit contributions
 butcher-0.034
 paramed-0.032
oc-0.029
icer-0.028
riger-0.028
Token She
Token ID1375
Feature activation+2.54e-02

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.017
ped+0.016
ia+0.016
Neg logit contributions
 butcher-0.022
 paramed-0.021
riger-0.019
oc-0.018
uf-0.018
Token would
Token ID561
Feature activation+2.71e-02

Pos logit contributions
iggle+0.048
kered+0.047
atively+0.044
ered+0.043
overed+0.043
Neg logit contributions
oc-0.038
 butcher-0.036
 paramed-0.034
P-0.034
icer-0.033
Token watch
Token ID2342
Feature activation+5.56e-02

Pos logit contributions
kered+0.045
iggle+0.040
ped+0.039
ia+0.038
ered+0.037
Neg logit contributions
 butcher-0.051
 paramed-0.049
oc-0.044
riger-0.044
 Which-0.043
Token them
Token ID606
Feature activation+3.87e-02

Pos logit contributions
kered+0.111
iggle+0.100
ered+0.096
ped+0.095
ia+0.095
Neg logit contributions
 butcher-0.082
 paramed-0.078
 Which-0.070
icer-0.069
Which-0.069
Token tw
Token ID665
Feature activation+5.82e-02

Pos logit contributions
kered+0.053
iggle+0.045
ped+0.045
ia+0.045
ered+0.043
Neg logit contributions
 butcher-0.079
 paramed-0.075
oc-0.073
riger-0.071
icer-0.069
Tokeninkle
Token ID19894
Feature activation+1.85e-02

Pos logit contributions
kered+0.077
ped+0.064
 flashed+0.061
atively+0.061
 blinked+0.060
Neg logit contributions
icer-0.122
 butcher-0.119
 paramed-0.116
riger-0.114
oc-0.114
Token in
Token ID287
Feature activation+1.25e-02

Pos logit contributions
kered+0.035
iggle+0.034
ered+0.032
ped+0.031
ia+0.031
Neg logit contributions
 butcher-0.029
 paramed-0.027
oc-0.024
icer-0.024
 sausage-0.024
Token the
Token ID262
Feature activation+1.30e-02

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.016
ped+0.016
ia+0.015
Neg logit contributions
 butcher-0.026
 paramed-0.025
icer-0.023
riger-0.023
oc-0.022
Token sky
Token ID6766
Feature activation+2.49e-02

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.016
ped+0.016
ia+0.015
Neg logit contributions
 butcher-0.028
 paramed-0.027
riger-0.024
icer-0.024
oc-0.024
Token every
Token ID790
Feature activation+2.09e-02

Pos logit contributions
kered+0.049
ered+0.044
iggle+0.044
ped+0.043
 flashed+0.041
Neg logit contributions
 butcher-0.039
 paramed-0.036
oc-0.034
icer-0.033
iw-0.032
TokenThe
Token ID464
Feature activation+4.33e-03

Pos logit contributions
 butcher+0.017
 paramed+0.016
 dollars+0.015
uf+0.015
icer+0.015
Neg logit contributions
kered-0.013
ia-0.012
ves-0.012
 flew-0.011
ered-0.011
Token little
Token ID1310
Feature activation+9.31e-03

Pos logit contributions
kered+0.008
iggle+0.007
ered+0.007
ped+0.007
owed+0.006
Neg logit contributions
 butcher-0.008
 paramed-0.008
riger-0.007
oc-0.007
icer-0.007
Token girl
Token ID2576
Feature activation+3.18e-02

Pos logit contributions
kered+0.022
iggle+0.021
ered+0.020
ped+0.020
ves+0.019
Neg logit contributions
 butcher-0.012
 paramed-0.011
iw-0.010
 Which-0.009
riger-0.009
Token took
Token ID1718
Feature activation+2.58e-02

Pos logit contributions
kered+0.047
iggle+0.046
ped+0.039
ered+0.039
 flashed+0.037
Neg logit contributions
 butcher-0.066
 paramed-0.061
oc-0.059
uf-0.056
riger-0.056
Token the
Token ID262
Feature activation+5.36e-02

Pos logit contributions
kered+0.042
iggle+0.040
 flashed+0.035
ered+0.035
ia+0.035
Neg logit contributions
 butcher-0.051
 paramed-0.046
riger-0.043
oc-0.042
 Which-0.042
Token golden
Token ID10861
Feature activation+5.37e-02

Pos logit contributions
kered+0.109
ped+0.103
ered+0.103
iggle+0.099
owed+0.096
Neg logit contributions
 cart-0.065
 butcher-0.065
 Which-0.065
icer-0.064
'-0.063
Token circle
Token ID9197
Feature activation+1.52e-02

Pos logit contributions
kered+0.088
iggle+0.083
ped+0.082
ered+0.080
 echoed+0.075
Neg logit contributions
 butcher-0.081
 dollars-0.080
 cart-0.079
icer-0.079
iw-0.078
Token in
Token ID287
Feature activation-4.86e-03

Pos logit contributions
kered+0.027
iggle+0.026
ered+0.024
ped+0.024
 flashed+0.024
Neg logit contributions
 butcher-0.026
 paramed-0.024
oc-0.022
riger-0.022
iw-0.021
Token her
Token ID607
Feature activation+2.83e-02

Pos logit contributions
 butcher+0.011
 paramed+0.010
riger+0.009
oc+0.009
icer+0.009
Neg logit contributions
kered-0.007
iggle-0.007
ered-0.006
ped-0.006
ia-0.006
Token hands
Token ID2832
Feature activation-2.04e-02

Pos logit contributions
kered+0.052
iggle+0.049
ered+0.047
ped+0.046
 flashed+0.043
Neg logit contributions
 butcher-0.050
 paramed-0.046
icer-0.042
oc-0.042
riger-0.042
Token and
Token ID290
Feature activation+3.02e-02

Pos logit contributions
 butcher+0.041
 paramed+0.038
riger+0.034
oc+0.034
uf+0.034
Neg logit contributions
kered-0.033
iggle-0.031
ered-0.029
ped-0.028
ia-0.027
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
kered+0.001
iggle+0.001
ered+0.001
ped+0.001
ia+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
riger-0.002
uf-0.002
icer-0.002
Token He
Token ID679
Feature activation+1.32e-02

Pos logit contributions
kered+0.023
iggle+0.021
ia+0.020
ered+0.020
ped+0.019
Neg logit contributions
 butcher-0.023
 paramed-0.021
riger-0.019
icer-0.019
uf-0.019
Token can
Token ID460
Feature activation+3.71e-02

Pos logit contributions
kered+0.021
iggle+0.020
ered+0.018
ped+0.018
atively+0.017
Neg logit contributions
 butcher-0.026
 paramed-0.024
oc-0.023
riger-0.022
iw-0.022
Token also
Token ID635
Feature activation+2.60e-02

Pos logit contributions
kered+0.054
iggle+0.050
ered+0.045
ped+0.045
ia+0.042
Neg logit contributions
 butcher-0.080
 paramed-0.076
riger-0.069
oc-0.068
uf-0.068
Token make
Token ID787
Feature activation+3.73e-02

Pos logit contributions
kered+0.038
iggle+0.035
ered+0.032
ped+0.031
ia+0.030
Neg logit contributions
 butcher-0.057
 paramed-0.053
riger-0.048
oc-0.048
uf-0.048
Token funny
Token ID8258
Feature activation+5.86e-02

Pos logit contributions
kered+0.065
iggle+0.060
ered+0.056
atively+0.055
owed+0.054
Neg logit contributions
 butcher-0.068
 paramed-0.063
oc-0.059
icer-0.057
uf-0.056
Token faces
Token ID6698
Feature activation+1.89e-02

Pos logit contributions
kered+0.072
iggle+0.065
ered+0.063
atively+0.059
ped+0.057
Neg logit contributions
 butcher-0.132
oc-0.128
 paramed-0.127
iw-0.116
icer-0.115
Token."
Token ID526
Feature activation+7.40e-03

Pos logit contributions
kered+0.032
iggle+0.031
ered+0.028
ped+0.028
ia+0.027
Neg logit contributions
 butcher-0.037
 paramed-0.034
oc-0.030
riger-0.030
icer-0.030
Token
Token ID198
Feature activation+7.73e-03

Pos logit contributions
iggle+0.013
kered+0.013
ia+0.012
 blinked+0.011
 danced+0.011
Neg logit contributions
 butcher-0.013
 paramed-0.013
riger-0.012
icer-0.011
 dollars-0.011
Token
Token ID198
Feature activation-6.64e-04

Pos logit contributions
kered+0.017
iggle+0.016
ered+0.015
ped+0.015
ia+0.014
Neg logit contributions
 butcher-0.012
 paramed-0.011
riger-0.009
oc-0.009
uf-0.009
TokenThey
Token ID2990
Feature activation+5.89e-03

Pos logit contributions
 butcher+0.001
 paramed+0.001
riger+0.001
uf+0.001
icer+0.001
Neg logit contributions
kered-0.001
ia-0.001
iggle-0.001
ves-0.001
 flew-0.001
Token She
Token ID1375
Feature activation+1.36e-02

Pos logit contributions
kered+0.002
iggle+0.002
ered+0.002
ped+0.002
 flashed+0.001
Neg logit contributions
 butcher-0.001
 paramed-0.001
 Which-0.001
icer-0.001
Mic-0.001
Token loved
Token ID6151
Feature activation-5.24e-03

Pos logit contributions
iggle+0.026
ered+0.026
kered+0.025
atively+0.025
owed+0.023
Neg logit contributions
 butcher-0.020
 paramed-0.019
P-0.019
oc-0.019
Mic-0.018
Token to
Token ID284
Feature activation+8.78e-03

Pos logit contributions
 butcher+0.010
 paramed+0.009
oc+0.009
icer+0.009
riger+0.009
Neg logit contributions
kered-0.008
iggle-0.008
 danced-0.008
ped-0.007
 flew-0.007
Token dance
Token ID9280
Feature activation+3.75e-02

Pos logit contributions
kered+0.017
ped+0.015
iggle+0.015
ered+0.015
atively+0.014
Neg logit contributions
 butcher-0.015
 paramed-0.014
 sausage-0.012
riger-0.012
 cart-0.012
Token and
Token ID290
Feature activation+3.09e-02

Pos logit contributions
kered+0.078
ered+0.072
ped+0.071
iggle+0.069
ia+0.065
Neg logit contributions
 butcher-0.053
 paramed-0.050
riger-0.047
 cart-0.044
 Which-0.044
Token tw
Token ID665
Feature activation+6.31e-02

Pos logit contributions
kered+0.055
atively+0.046
ia+0.046
iggle+0.046
ped+0.046
Neg logit contributions
 Which-0.050
 butcher-0.050
Which-0.050
riger-0.049
Why-0.048
Tokenirl
Token ID1901
Feature activation+3.55e-02

Pos logit contributions
kered+0.084
atively+0.069
ped+0.069
 flashed+0.069
 blinked+0.065
Neg logit contributions
icer-0.131
riger-0.127
 paramed-0.125
 butcher-0.124
arre-0.120
Token around
Token ID1088
Feature activation+1.20e-02

Pos logit contributions
kered+0.068
ered+0.066
iggle+0.064
ia+0.064
 flashed+0.061
Neg logit contributions
 paramed-0.046
 butcher-0.045
 cart-0.042
P-0.041
oc-0.041
Token.
Token ID13
Feature activation+1.65e-02

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.017
ped+0.016
ia+0.016
Neg logit contributions
 butcher-0.024
 paramed-0.023
riger-0.021
icer-0.020
oc-0.020
Token One
Token ID1881
Feature activation+2.51e-02

Pos logit contributions
iggle+0.027
kered+0.027
ia+0.024
ered+0.024
 danced+0.023
Neg logit contributions
 butcher-0.032
 paramed-0.030
riger-0.027
oc-0.027
uf-0.026
Token day
Token ID1110
Feature activation+1.72e-02

Pos logit contributions
kered+0.058
ered+0.056
atively+0.055
ped+0.054
iggle+0.052
Neg logit contributions
 butcher-0.030
 paramed-0.028
oc-0.024
 sausage-0.023
 Which-0.023
Token wonderful
Token ID7932
Feature activation+4.21e-02

Pos logit contributions
kered+0.059
iggle+0.056
ped+0.052
ered+0.050
 blinked+0.049
Neg logit contributions
 butcher-0.069
 paramed-0.065
riger-0.060
oc-0.059
icer-0.058
Token pictures
Token ID5986
Feature activation+2.08e-02

Pos logit contributions
kered+0.061
iggle+0.058
ered+0.054
ped+0.053
atively+0.052
Neg logit contributions
 butcher-0.084
 paramed-0.080
oc-0.078
riger-0.074
icer-0.073
Token.
Token ID13
Feature activation+3.36e-02

Pos logit contributions
kered+0.036
iggle+0.035
ered+0.032
ped+0.032
ia+0.030
Neg logit contributions
 butcher-0.038
 paramed-0.035
riger-0.032
 Which-0.031
oc-0.031
Token One
Token ID1881
Feature activation+1.03e-02

Pos logit contributions
kered+0.072
iggle+0.069
ered+0.065
ped+0.063
ia+0.062
Neg logit contributions
 butcher-0.051
 paramed-0.047
riger-0.040
oc-0.040
uf-0.040
Token day
Token ID1110
Feature activation+3.49e-02

Pos logit contributions
kered+0.019
iggle+0.017
ered+0.017
ped+0.017
atively+0.016
Neg logit contributions
 butcher-0.019
 paramed-0.018
oc-0.016
icer-0.015
uf-0.015
Token,
Token ID11
Feature activation+5.78e-02

Pos logit contributions
kered+0.073
iggle+0.070
ered+0.064
ped+0.063
 flashed+0.061
Neg logit contributions
 butcher-0.047
 paramed-0.046
 Which-0.042
riger-0.041
iw-0.040
Token Zoe
Token ID32280
Feature activation+1.98e-02

Pos logit contributions
kered+0.119
iggle+0.116
ped+0.099
ered+0.099
aned+0.097
Neg logit contributions
 Which-0.078
Which-0.075
Why-0.074
 paramed-0.070
 Why-0.069
Tokeny
Token ID88
Feature activation+3.21e-03

Pos logit contributions
kered+0.043
iggle+0.040
 happen+0.038
 flashed+0.038
ped+0.038
Neg logit contributions
 butcher-0.026
oc-0.024
 paramed-0.024
icer-0.022
arre-0.022
Token wanted
Token ID2227
Feature activation-7.34e-04

Pos logit contributions
kered+0.006
iggle+0.005
ped+0.005
ered+0.005
 flashed+0.005
Neg logit contributions
 butcher-0.006
 paramed-0.006
oc-0.005
arre-0.005
uf-0.005
Token to
Token ID284
Feature activation+2.83e-02

Pos logit contributions
 butcher+0.001
 paramed+0.001
oc+0.001
riger+0.001
icer+0.001
Neg logit contributions
kered-0.001
iggle-0.001
ered-0.001
ped-0.001
 danced-0.001
Token try
Token ID1949
Feature activation+2.07e-02

Pos logit contributions
kered+0.052
ped+0.051
atively+0.048
iggle+0.048
led+0.047
Neg logit contributions
 butcher-0.044
 paramed-0.043
 charity-0.039
riger-0.038
 sausage-0.037
Token match
Token ID2872
Feature activation+6.66e-03

Pos logit contributions
kered+0.004
iggle+0.004
ered+0.003
ped+0.003
 flashed+0.003
Neg logit contributions
 butcher-0.005
 paramed-0.004
riger-0.004
oc-0.004
uf-0.004
Token!
Token ID0
Feature activation+6.74e-03

Pos logit contributions
kered+0.011
iggle+0.011
ered+0.010
ped+0.010
ia+0.009
Neg logit contributions
 butcher-0.013
 paramed-0.012
riger-0.011
oc-0.010
uf-0.010
Token
Token ID220
Feature activation+2.05e-02

Pos logit contributions
kered+0.013
iggle+0.012
ered+0.011
ped+0.011
ia+0.011
Neg logit contributions
 butcher-0.012
 paramed-0.011
riger-0.010
oc-0.010
uf-0.010
Token
Token ID198
Feature activation+3.26e-03

Pos logit contributions
kered+0.040
iggle+0.039
ered+0.036
ia+0.035
ped+0.035
Neg logit contributions
 butcher-0.035
 paramed-0.032
riger-0.028
oc-0.028
icer-0.027
Token
Token ID198
Feature activation-7.87e-03

Pos logit contributions
kered+0.007
iggle+0.007
ered+0.006
ped+0.006
ia+0.006
Neg logit contributions
 butcher-0.005
 paramed-0.005
riger-0.004
uf-0.004
icer-0.004
TokenL
Token ID43
Feature activation+2.45e-02

Pos logit contributions
 butcher+0.013
 paramed+0.012
uf+0.010
riger+0.010
icer+0.010
Neg logit contributions
kered-0.016
iggle-0.015
ered-0.014
 danced-0.014
ia-0.014
Tokenizzy
Token ID40593
Feature activation+1.99e-02

Pos logit contributions
kered+0.053
iggle+0.049
 flashed+0.048
 blinked+0.048
atively+0.047
Neg logit contributions
 butcher-0.030
 paramed-0.029
icer-0.029
oc-0.025
uf-0.025
Token was
Token ID373
Feature activation+3.91e-04

Pos logit contributions
kered+0.026
iggle+0.026
ped+0.022
ered+0.021
ia+0.021
Neg logit contributions
 butcher-0.043
 paramed-0.041
oc-0.039
uf-0.037
riger-0.037
Token so
Token ID523
Feature activation-4.79e-03

Pos logit contributions
kered+0.001
iggle+0.001
ered+0.001
ia+0.001
ped+0.001
Neg logit contributions
 butcher-0.001
 paramed-0.001
riger-0.000
uf-0.000
oc-0.000
Token proud
Token ID6613
Feature activation+1.30e-02

Pos logit contributions
 paramed+0.008
 butcher+0.008
iw+0.007
riger+0.007
oc+0.007
Neg logit contributions
kered-0.009
iggle-0.008
ered-0.008
ped-0.008
 flashed-0.008
Token of
Token ID286
Feature activation+6.63e-03

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.016
ped+0.016
ia+0.016
Neg logit contributions
 butcher-0.028
 paramed-0.027
riger-0.024
icer-0.024
uf-0.024
Token saw
Token ID2497
Feature activation+1.57e-02

Pos logit contributions
kered+0.065
iggle+0.060
ped+0.054
ered+0.053
 happen+0.052
Neg logit contributions
 butcher-0.037
 paramed-0.032
 cart-0.029
oc-0.029
icer-0.028
Token a
Token ID257
Feature activation+1.57e-03

Pos logit contributions
iggle+0.028
kered+0.028
ered+0.024
owed+0.024
ia+0.023
Neg logit contributions
 butcher-0.030
 paramed-0.028
 Which-0.025
Which-0.025
 sausage-0.024
Token big
Token ID1263
Feature activation-4.54e-04

Pos logit contributions
kered+0.002
iggle+0.002
 blinked+0.002
 flew+0.002
 flashed+0.002
Neg logit contributions
 butcher-0.003
 paramed-0.003
riger-0.003
uf-0.003
icer-0.003
Token rock
Token ID3881
Feature activation-3.05e-03

Pos logit contributions
 butcher+0.001
 paramed+0.001
riger+0.001
uf+0.001
 Which+0.001
Neg logit contributions
iggle-0.001
kered-0.001
 flashed-0.001
 flew-0.001
ia-0.001
Token and
Token ID290
Feature activation+8.12e-03

Pos logit contributions
 butcher+0.006
 paramed+0.005
oc+0.005
riger+0.005
icer+0.005
Neg logit contributions
kered-0.006
iggle-0.005
ered-0.005
ped-0.005
ia-0.005
Token wanted
Token ID2227
Feature activation+6.38e-03

Pos logit contributions
iggle+0.018
kered+0.016
ia+0.014
aby+0.014
ittered+0.014
Neg logit contributions
 butcher-0.013
 paramed-0.012
Which-0.012
 Which-0.011
 cart-0.011
Token to
Token ID284
Feature activation+3.19e-02

Pos logit contributions
kered+0.013
iggle+0.012
ered+0.011
ped+0.011
ia+0.011
Neg logit contributions
 butcher-0.010
 paramed-0.010
riger-0.008
oc-0.008
uf-0.008
Token climb
Token ID12080
Feature activation+2.23e-02

Pos logit contributions
kered+0.068
iggle+0.063
ped+0.063
led+0.062
atively+0.060
Neg logit contributions
 butcher-0.042
 paramed-0.039
oc-0.037
 cart-0.037
 sausage-0.034
Token it
Token ID340
Feature activation+8.29e-03

Pos logit contributions
kered+0.026
iggle+0.024
ered+0.021
ped+0.020
ia+0.019
Neg logit contributions
 butcher-0.055
 paramed-0.053
riger-0.048
uf-0.048
oc-0.048
Token.
Token ID13
Feature activation+3.55e-03

Pos logit contributions
kered+0.017
iggle+0.015
ped+0.015
 flashed+0.015
 danced+0.014
Neg logit contributions
 butcher-0.012
oc-0.011
 cart-0.011
 Which-0.010
 paramed-0.010
Token
Token ID220
Feature activation+2.51e-02

Pos logit contributions
kered+0.006
iggle+0.006
ered+0.006
 blinked+0.006
ia+0.006
Neg logit contributions
 butcher-0.006
 paramed-0.006
riger-0.005
 dollars-0.005
uf-0.005
Token a
Token ID257
Feature activation-8.01e-03

Pos logit contributions
kered+0.034
iggle+0.033
ered+0.030
ped+0.029
ia+0.029
Neg logit contributions
 butcher-0.038
 paramed-0.035
 sausage-0.030
Mic-0.030
 Which-0.030
Token little
Token ID1310
Feature activation-6.28e-03

Pos logit contributions
 butcher+0.017
 paramed+0.017
riger+0.016
 Which+0.016
icer+0.016
Neg logit contributions
iggle-0.009
kered-0.009
 blinked-0.009
ia-0.008
 flew-0.008
Token girl
Token ID2576
Feature activation+8.93e-03

Pos logit contributions
 butcher+0.012
 paramed+0.011
riger+0.011
uf+0.011
icer+0.010
Neg logit contributions
kered-0.010
iggle-0.010
 blinked-0.009
 flew-0.009
 danced-0.009
Token named
Token ID3706
Feature activation-8.07e-04

Pos logit contributions
kered+0.018
iggle+0.017
ered+0.016
ped+0.016
ia+0.015
Neg logit contributions
 butcher-0.015
 paramed-0.013
oc-0.012
riger-0.012
uf-0.012
Token Lily
Token ID20037
Feature activation-6.79e-03

Pos logit contributions
 butcher+0.002
 paramed+0.001
riger+0.001
 Which+0.001
uf+0.001
Neg logit contributions
kered-0.001
iggle-0.001
ered-0.001
 flashed-0.001
ped-0.001
Token.
Token ID13
Feature activation+5.06e-03

Pos logit contributions
 butcher+0.013
 paramed+0.012
oc+0.011
uf+0.011
riger+0.010
Neg logit contributions
kered-0.012
iggle-0.011
ered-0.010
ped-0.010
 flashed-0.010
Token She
Token ID1375
Feature activation+1.14e-02

Pos logit contributions
kered+0.007
iggle+0.007
ia+0.006
ered+0.006
 danced+0.006
Neg logit contributions
 butcher-0.011
 paramed-0.010
riger-0.009
oc-0.009
uf-0.009
Token loved
Token ID6151
Feature activation-2.64e-03

Pos logit contributions
kered+0.020
iggle+0.019
ered+0.017
ped+0.017
atively+0.016
Neg logit contributions
 butcher-0.021
 paramed-0.020
oc-0.018
uf-0.018
Charl-0.017
Token the
Token ID262
Feature activation+1.22e-02

Pos logit contributions
 butcher+0.005
 paramed+0.005
oc+0.004
icer+0.004
riger+0.004
Neg logit contributions
kered-0.004
iggle-0.004
 danced-0.004
ped-0.004
ered-0.004
Token color
Token ID3124
Feature activation+2.60e-02

Pos logit contributions
kered+0.018
iggle+0.017
ered+0.016
ped+0.015
ia+0.015
Neg logit contributions
 butcher-0.026
 paramed-0.024
riger-0.022
oc-0.022
uf-0.022
Token blue
Token ID4171
Feature activation+2.04e-02

Pos logit contributions
kered+0.043
iggle+0.041
ped+0.038
ered+0.037
ia+0.035
Neg logit contributions
 butcher-0.051
 paramed-0.048
icer-0.043
 Which-0.042
riger-0.042
Token Jack
Token ID3619
Feature activation+1.56e-02

Pos logit contributions
kered+0.015
iggle+0.014
ered+0.014
ped+0.013
owed+0.013
Neg logit contributions
 butcher-0.011
 sausage-0.009
 Which-0.009
 paramed-0.009
Mic-0.008
Token went
Token ID1816
Feature activation-1.64e-02

Pos logit contributions
kered+0.027
iggle+0.026
ered+0.024
ped+0.023
atively+0.022
Neg logit contributions
 butcher-0.030
 paramed-0.027
oc-0.026
riger-0.024
icer-0.024
Token to
Token ID284
Feature activation-1.19e-03

Pos logit contributions
 butcher+0.030
 paramed+0.029
oc+0.026
uf+0.026
icer+0.026
Neg logit contributions
iggle-0.028
kered-0.028
ered-0.026
ped-0.025
 danced-0.025
Token the
Token ID262
Feature activation-1.65e-03

Pos logit contributions
 butcher+0.002
 paramed+0.002
riger+0.002
uf+0.002
icer+0.002
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.002
ped-0.002
ia-0.002
Token park
Token ID3952
Feature activation+1.02e-02

Pos logit contributions
 butcher+0.003
 dollars+0.003
 paramed+0.003
oc+0.003
riger+0.003
Neg logit contributions
kered-0.002
iggle-0.002
ia-0.002
 blinked-0.002
 flew-0.002
Token to
Token ID284
Feature activation+9.02e-03

Pos logit contributions
kered+0.021
iggle+0.019
ped+0.019
ered+0.019
 flashed+0.018
Neg logit contributions
 butcher-0.016
 paramed-0.015
oc-0.014
iw-0.013
 Which-0.013
Token play
Token ID711
Feature activation+8.71e-03

Pos logit contributions
kered+0.017
iggle+0.015
ped+0.014
ered+0.014
ia+0.014
Neg logit contributions
 butcher-0.017
 paramed-0.016
riger-0.014
 Which-0.014
oc-0.013
Token on
Token ID319
Feature activation+4.85e-03

Pos logit contributions
kered+0.014
iggle+0.013
ered+0.012
ped+0.012
ia+0.012
Neg logit contributions
 butcher-0.017
 paramed-0.016
oc-0.015
riger-0.015
icer-0.014
Token the
Token ID262
Feature activation+3.24e-02

Pos logit contributions
kered+0.009
iggle+0.009
ped+0.008
ered+0.008
owed+0.008
Neg logit contributions
 butcher-0.009
 paramed-0.008
icer-0.007
oc-0.007
 sausage-0.007
Token swings
Token ID26728
Feature activation+8.41e-03

Pos logit contributions
kered+0.057
iggle+0.052
ered+0.050
owed+0.050
ped+0.048
Neg logit contributions
 butcher-0.062
 paramed-0.056
 cart-0.053
 sausage-0.051
 vending-0.050
Token.
Token ID13
Feature activation+2.51e-03

Pos logit contributions
kered+0.017
iggle+0.016
ered+0.016
 flashed+0.015
ped+0.015
Neg logit contributions
 butcher-0.012
oc-0.011
 paramed-0.011
iw-0.011
 cart-0.010
Token her
Token ID607
Feature activation+1.95e-02

Pos logit contributions
 butcher+0.032
 paramed+0.030
riger+0.028
uf+0.028
icer+0.027
Neg logit contributions
kered-0.017
iggle-0.016
ered-0.014
ped-0.013
ia-0.013
Token room
Token ID2119
Feature activation-1.29e-02

Pos logit contributions
kered+0.035
iggle+0.033
ered+0.031
ped+0.030
 flashed+0.029
Neg logit contributions
 butcher-0.036
 paramed-0.032
oc-0.030
uf-0.029
riger-0.029
Token.
Token ID13
Feature activation+5.02e-03

Pos logit contributions
 butcher+0.027
 paramed+0.025
riger+0.023
oc+0.023
icer+0.023
Neg logit contributions
kered-0.020
iggle-0.019
ered-0.017
ped-0.017
ia-0.016
Token
Token ID198
Feature activation+4.62e-03

Pos logit contributions
kered+0.008
iggle+0.008
ia+0.008
ered+0.007
ped+0.007
Neg logit contributions
 butcher-0.009
 paramed-0.009
riger-0.008
icer-0.008
 dollars-0.008
Token
Token ID198
Feature activation-2.04e-03

Pos logit contributions
kered+0.009
iggle+0.009
ered+0.009
ia+0.008
ped+0.008
Neg logit contributions
 butcher-0.007
 paramed-0.007
riger-0.006
icer-0.006
uf-0.006
TokenSo
Token ID2396
Feature activation+3.08e-02

Pos logit contributions
 butcher+0.004
 paramed+0.004
icer+0.003
uf+0.003
riger+0.003
Neg logit contributions
kered-0.004
iggle-0.003
ered-0.003
ia-0.003
 flew-0.003
Token she
Token ID673
Feature activation+1.35e-02

Pos logit contributions
kered+0.047
iggle+0.045
ped+0.040
ered+0.039
 flashed+0.038
Neg logit contributions
 butcher-0.064
 paramed-0.060
riger-0.055
oc-0.055
 Which-0.054
Token tid
Token ID29770
Feature activation+1.00e-02

Pos logit contributions
kered+0.019
iggle+0.019
ped+0.015
ia+0.015
ered+0.015
Neg logit contributions
 butcher-0.029
 paramed-0.028
oc-0.026
riger-0.025
uf-0.024
Tokenied
Token ID798
Feature activation+2.61e-02

Pos logit contributions
kered+0.014
 flashed+0.013
iggle+0.013
 blinked+0.013
 soar+0.012
Neg logit contributions
 butcher-0.019
 paramed-0.019
icer-0.016
arre-0.016
iw-0.016
Token her
Token ID607
Feature activation+1.72e-02

Pos logit contributions
kered+0.040
iggle+0.037
ia+0.034
 flashed+0.033
ped+0.033
Neg logit contributions
 butcher-0.052
 paramed-0.048
riger-0.044
 cart-0.043
oc-0.043
Token room
Token ID2119
Feature activation-2.31e-02

Pos logit contributions
kered+0.033
iggle+0.030
ped+0.028
ered+0.028
 flashed+0.027
Neg logit contributions
 butcher-0.031
 paramed-0.027
oc-0.025
icer-0.025
riger-0.025
Tokenolly
Token ID5098
Feature activation+3.66e-02

Pos logit contributions
 flashed+0.076
kered+0.076
 blinked+0.074
 glow+0.068
ered+0.068
Neg logit contributions
 paramed-0.068
 butcher-0.066
uf-0.061
enn-0.061
arre-0.061
Token friends
Token ID2460
Feature activation+2.58e-03

Pos logit contributions
kered+0.067
iggle+0.061
ered+0.059
 flashed+0.057
ped+0.054
Neg logit contributions
 butcher-0.062
 paramed-0.055
oc-0.053
 sausage-0.051
 dollars-0.051
Token were
Token ID547
Feature activation-3.75e-03

Pos logit contributions
kered+0.004
iggle+0.004
ered+0.004
ped+0.003
ia+0.003
Neg logit contributions
 butcher-0.005
 paramed-0.005
riger-0.004
uf-0.004
oc-0.004
Token sad
Token ID6507
Feature activation+1.44e-02

Pos logit contributions
 butcher+0.007
 paramed+0.007
riger+0.006
uf+0.006
icer+0.006
Neg logit contributions
kered-0.007
iggle-0.006
ered-0.006
ped-0.006
ia-0.005
Token to
Token ID284
Feature activation-7.06e-03

Pos logit contributions
kered+0.028
iggle+0.025
ered+0.024
ped+0.024
 flashed+0.023
Neg logit contributions
 butcher-0.025
 paramed-0.023
 Which-0.020
arre-0.020
 sausage-0.020
Token say
Token ID910
Feature activation-2.10e-02

Pos logit contributions
 butcher+0.013
 paramed+0.013
riger+0.012
uf+0.012
 charity+0.011
Neg logit contributions
kered-0.012
iggle-0.010
ped-0.010
ia-0.010
 flashed-0.010
Token goodbye
Token ID24829
Feature activation+6.81e-03

Pos logit contributions
 butcher+0.045
 paramed+0.042
icer+0.039
oc+0.039
riger+0.039
Neg logit contributions
kered-0.031
iggle-0.029
ered-0.027
ped-0.026
ia-0.025
Token to
Token ID284
Feature activation-4.86e-03

Pos logit contributions
kered+0.012
iggle+0.012
ered+0.011
ped+0.011
 flashed+0.010
Neg logit contributions
 butcher-0.012
 paramed-0.011
oc-0.010
uf-0.010
riger-0.010
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
 butcher+0.010
 paramed+0.009
riger+0.008
uf+0.008
oc+0.008
Neg logit contributions
kered-0.008
iggle-0.008
ered-0.007
ped-0.007
ia-0.007
Token plane
Token ID6614
Feature activation+2.15e-03

Pos logit contributions
 butcher+0.020
 paramed+0.019
riger+0.017
oc+0.017
icer+0.017
Neg logit contributions
kered-0.018
iggle-0.017
ered-0.015
ped-0.015
ia-0.015
Token.
Token ID13
Feature activation+1.96e-03

Pos logit contributions
kered+0.004
iggle+0.003
ered+0.003
ped+0.003
ia+0.003
Neg logit contributions
 butcher-0.004
 paramed-0.004
oc-0.004
riger-0.004
uf-0.003
Token the
Token ID262
Feature activation+8.82e-03

Pos logit contributions
 butcher+0.048
 paramed+0.045
riger+0.041
oc+0.040
uf+0.040
Neg logit contributions
kered-0.036
iggle-0.034
ered-0.031
ped-0.030
ia-0.030
Token day
Token ID1110
Feature activation+1.20e-02

Pos logit contributions
kered+0.014
iggle+0.013
ered+0.012
ped+0.012
ia+0.011
Neg logit contributions
 butcher-0.018
 paramed-0.017
riger-0.016
oc-0.015
icer-0.015
Token,
Token ID11
Feature activation+1.40e-02

Pos logit contributions
kered+0.020
iggle+0.019
ered+0.018
ped+0.018
 flashed+0.016
Neg logit contributions
 butcher-0.023
 paramed-0.022
riger-0.020
uf-0.019
oc-0.019
Token Lily
Token ID20037
Feature activation+1.06e-02

Pos logit contributions
kered+0.021
iggle+0.021
ered+0.019
ped+0.018
ia+0.018
Neg logit contributions
 butcher-0.030
 paramed-0.028
riger-0.025
oc-0.025
uf-0.025
Token was
Token ID373
Feature activation-5.98e-03

Pos logit contributions
kered+0.016
iggle+0.015
ered+0.014
ped+0.014
 flashed+0.013
Neg logit contributions
 butcher-0.022
 paramed-0.021
uf-0.019
oc-0.019
riger-0.019
Token tired
Token ID10032
Feature activation-2.71e-03

Pos logit contributions
 butcher+0.010
 paramed+0.010
uf+0.008
riger+0.008
icer+0.008
Neg logit contributions
kered-0.012
iggle-0.011
ered-0.010
ped-0.010
 flashed-0.010
Token but
Token ID475
Feature activation+1.17e-03

Pos logit contributions
 butcher+0.006
 paramed+0.005
riger+0.005
icer+0.005
oc+0.005
Neg logit contributions
kered-0.004
iggle-0.004
ered-0.004
ia-0.004
 danced-0.004
Token happy
Token ID3772
Feature activation+1.92e-02

Pos logit contributions
kered+0.002
iggle+0.002
ered+0.002
ped+0.002
ves+0.002
Neg logit contributions
 butcher-0.002
 paramed-0.002
Mrs-0.001
 sausage-0.001
 ju-0.001
Token.
Token ID13
Feature activation-1.16e-02

Pos logit contributions
kered+0.038
iggle+0.035
ered+0.034
ped+0.033
irled+0.032
Neg logit contributions
 butcher-0.032
 paramed-0.029
 sausage-0.026
uf-0.025
riger-0.025
Token She
Token ID1375
Feature activation-1.47e-03

Pos logit contributions
 butcher+0.023
 paramed+0.021
riger+0.019
oc+0.019
uf+0.019
Neg logit contributions
kered-0.020
iggle-0.019
ered-0.017
ped-0.017
ia-0.016
Token said
Token ID531
Feature activation-1.48e-02

Pos logit contributions
 butcher+0.003
 paramed+0.003
uf+0.003
oc+0.003
 sausage+0.003
Neg logit contributions
kered-0.002
iggle-0.002
ered-0.002
ped-0.002
owed-0.002
Token the
Token ID262
Feature activation-1.47e-02

Pos logit contributions
 butcher+0.001
 paramed+0.001
riger+0.001
uf+0.001
oc+0.001
Neg logit contributions
kered-0.001
iggle-0.001
ered-0.000
ped-0.000
ia-0.000
Token cup
Token ID6508
Feature activation-2.22e-02

Pos logit contributions
 paramed+0.026
 butcher+0.026
uf+0.025
riger+0.025
Mic+0.024
Neg logit contributions
kered-0.023
iggle-0.021
 moves-0.021
 glow-0.021
ia-0.021
Tokenboard
Token ID3526
Feature activation-8.60e-03

Pos logit contributions
 butcher+0.042
 paramed+0.040
riger+0.036
uf+0.036
Mic+0.036
Neg logit contributions
kered-0.039
iggle-0.036
ia-0.034
ered-0.033
ped-0.032
Token and
Token ID290
Feature activation+1.26e-02

Pos logit contributions
 butcher+0.015
 paramed+0.014
oc+0.012
riger+0.012
 Which+0.012
Neg logit contributions
kered-0.016
iggle-0.016
ered-0.014
ped-0.014
 flashed-0.013
Token saw
Token ID2497
Feature activation+1.41e-02

Pos logit contributions
kered+0.020
iggle+0.019
ia+0.016
ered+0.016
ped+0.016
Neg logit contributions
 butcher-0.027
 paramed-0.024
riger-0.022
oc-0.022
 Which-0.022
Token some
Token ID617
Feature activation-1.04e-02

Pos logit contributions
kered+0.023
iggle+0.022
ered+0.020
ped+0.019
ia+0.019
Neg logit contributions
 butcher-0.028
 paramed-0.026
oc-0.023
icer-0.023
riger-0.023
Token y
Token ID331
Feature activation+5.55e-03

Pos logit contributions
 butcher+0.020
 paramed+0.018
riger+0.016
oc+0.016
uf+0.016
Neg logit contributions
kered-0.018
iggle-0.018
ered-0.016
ped-0.016
ia-0.016
Tokenummy
Token ID13513
Feature activation-4.93e-03

Pos logit contributions
kered+0.011
iggle+0.011
ered+0.010
ped+0.010
ia+0.010
Neg logit contributions
 butcher-0.009
 paramed-0.008
riger-0.007
oc-0.007
uf-0.007
Token sauces
Token ID50134
Feature activation-3.55e-02

Pos logit contributions
 butcher+0.009
 paramed+0.008
riger+0.007
uf+0.007
Mic+0.007
Neg logit contributions
kered-0.009
iggle-0.009
ered-0.008
ped-0.008
ia-0.008
Token.
Token ID13
Feature activation+4.57e-03

Pos logit contributions
 butcher+0.078
 paramed+0.075
uf+0.069
riger+0.068
oc+0.068
Neg logit contributions
kered-0.051
iggle-0.048
ered-0.043
ped-0.042
ia-0.041
Token He
Token ID679
Feature activation+3.21e-03

Pos logit contributions
kered+0.006
iggle+0.006
ia+0.006
 blinked+0.005
ped+0.005
Neg logit contributions
 paramed-0.009
 butcher-0.009
riger-0.009
use-0.008
 dollars-0.008
Token want
Token ID765
Feature activation-1.67e-05

Pos logit contributions
kered+0.006
iggle+0.005
ped+0.005
ered+0.005
ia+0.005
Neg logit contributions
 butcher-0.006
 paramed-0.006
riger-0.005
oc-0.005
uf-0.005
Token to
Token ID284
Feature activation+1.88e-02

Pos logit contributions
 butcher+0.000
 paramed+0.000
 Which+0.000
iw+0.000
uf+0.000
Neg logit contributions
kered-0.000
iggle-0.000
ered-0.000
ped-0.000
irled-0.000
Token share
Token ID2648
Feature activation+1.15e-02

Pos logit contributions
kered+0.033
iggle+0.030
ped+0.029
atively+0.028
ered+0.027
Neg logit contributions
 butcher-0.035
 paramed-0.034
riger-0.031
uf-0.030
 charity-0.029
Token.
Token ID13
Feature activation-4.02e-03

Pos logit contributions
kered+0.016
iggle+0.016
ered+0.014
ped+0.014
ia+0.013
Neg logit contributions
 butcher-0.025
 paramed-0.024
riger-0.022
uf-0.022
oc-0.021
Token
Token ID198
Feature activation-6.33e-03

Pos logit contributions
 butcher+0.007
 paramed+0.007
riger+0.006
icer+0.006
uf+0.006
Neg logit contributions
kered-0.007
iggle-0.007
ia-0.006
ped-0.006
ered-0.006
Token
Token ID198
Feature activation-1.73e-02

Pos logit contributions
 butcher+0.010
 paramed+0.009
riger+0.008
uf+0.008
icer+0.008
Neg logit contributions
kered-0.013
iggle-0.013
ered-0.012
ped-0.012
ia-0.012
TokenThey
Token ID2990
Feature activation-7.07e-03

Pos logit contributions
 butcher+0.029
 paramed+0.028
uf+0.026
riger+0.025
icer+0.025
Neg logit contributions
kered-0.035
ia-0.031
iggle-0.030
ered-0.029
 flew-0.029
Token start
Token ID923
Feature activation+1.76e-02

Pos logit contributions
 butcher+0.016
 paramed+0.015
riger+0.014
oc+0.014
uf+0.014
Neg logit contributions
kered-0.010
iggle-0.009
ered-0.008
ped-0.008
ia-0.008
Token to
Token ID284
Feature activation-2.92e-03

Pos logit contributions
kered+0.033
iggle+0.032
ered+0.029
ped+0.029
 danced+0.028
Neg logit contributions
 butcher-0.031
 paramed-0.029
riger-0.026
uf-0.026
oc-0.025
Token fight
Token ID1907
Feature activation+2.24e-02

Pos logit contributions
 butcher+0.005
 paramed+0.005
riger+0.005
oc+0.005
uf+0.005
Neg logit contributions
kered-0.005
iggle-0.005
ered-0.004
ped-0.004
ia-0.004
Token over
Token ID625
Feature activation+8.92e-04

Pos logit contributions
kered+0.041
iggle+0.039
ped+0.036
ered+0.036
 danced+0.035
Neg logit contributions
 butcher-0.038
 paramed-0.034
 Which-0.033
oc-0.031
 charity-0.031
Token inside
Token ID2641
Feature activation-3.44e-02

Pos logit contributions
kered+0.015
iggle+0.015
ered+0.014
ped+0.013
ia+0.013
Neg logit contributions
 butcher-0.016
 paramed-0.015
riger-0.013
icer-0.013
uf-0.013
Token and
Token ID290
Feature activation+6.03e-03

Pos logit contributions
 butcher+0.074
 paramed+0.070
riger+0.065
Mic+0.064
icer+0.063
Neg logit contributions
iggle-0.049
kered-0.049
ered-0.044
ia-0.041
 danced-0.041
Token they
Token ID484
Feature activation+7.97e-03

Pos logit contributions
kered+0.009
iggle+0.009
ered+0.008
ped+0.008
ia+0.008
Neg logit contributions
 butcher-0.013
 paramed-0.012
riger-0.011
oc-0.011
uf-0.010
Token would
Token ID561
Feature activation+1.25e-02

Pos logit contributions
kered+0.011
iggle+0.011
ped+0.009
ia+0.009
ered+0.009
Neg logit contributions
 butcher-0.018
 paramed-0.017
riger-0.015
oc-0.015
uf-0.015
Token make
Token ID787
Feature activation+3.14e-02

Pos logit contributions
kered+0.018
iggle+0.017
ered+0.015
ped+0.015
ia+0.015
Neg logit contributions
 butcher-0.027
 paramed-0.026
riger-0.023
uf-0.023
oc-0.023
Token cookies
Token ID14746
Feature activation-4.65e-03

Pos logit contributions
kered+0.052
iggle+0.049
ered+0.045
ped+0.044
 flashed+0.044
Neg logit contributions
 butcher-0.061
 paramed-0.057
riger-0.051
uf-0.051
oc-0.051
Token together
Token ID1978
Feature activation+1.25e-02

Pos logit contributions
 butcher+0.009
 paramed+0.009
uf+0.008
icer+0.008
riger+0.008
Neg logit contributions
kered-0.008
iggle-0.007
ered-0.007
ped-0.006
ia-0.006
Token.
Token ID13
Feature activation-6.41e-03

Pos logit contributions
kered+0.019
iggle+0.018
ered+0.016
ped+0.016
ia+0.016
Neg logit contributions
 butcher-0.026
 paramed-0.024
riger-0.022
oc-0.022
uf-0.022
Token In
Token ID554
Feature activation-2.40e-02

Pos logit contributions
 butcher+0.013
 paramed+0.013
riger+0.012
oc+0.012
icer+0.012
Neg logit contributions
kered-0.009
iggle-0.009
ia-0.008
 danced-0.007
ered-0.007
Token no
Token ID645
Feature activation-6.41e-03

Pos logit contributions
 butcher+0.052
 paramed+0.049
oc+0.045
riger+0.045
Mic+0.044
Neg logit contributions
kered-0.034
iggle-0.033
ered-0.031
ped-0.029
ia-0.029
Token time
Token ID640
Feature activation-5.26e-03

Pos logit contributions
 butcher+0.012
 paramed+0.011
 dollars+0.010
oc+0.010
icer+0.010
Neg logit contributions
kered-0.012
ped-0.010
iggle-0.010
ered-0.010
owed-0.009
Token wait
Token ID4043
Feature activation-2.01e-03

Pos logit contributions
kered+0.008
iggle+0.007
ered+0.007
ped+0.006
ia+0.006
Neg logit contributions
 butcher-0.013
 paramed-0.012
icer-0.011
riger-0.011
oc-0.011
Token to
Token ID284
Feature activation-5.74e-03

Pos logit contributions
 butcher+0.003
 paramed+0.003
riger+0.003
uf+0.003
oc+0.003
Neg logit contributions
kered-0.004
iggle-0.004
ered-0.003
ped-0.003
ia-0.003
Token have
Token ID423
Feature activation-1.71e-02

Pos logit contributions
 butcher+0.013
 paramed+0.012
icer+0.011
oc+0.011
riger+0.011
Neg logit contributions
kered-0.008
iggle-0.008
ered-0.007
ped-0.006
 danced-0.006
Token an
Token ID281
Feature activation-1.16e-03

Pos logit contributions
 butcher+0.038
 paramed+0.037
oc+0.034
riger+0.033
icer+0.033
Neg logit contributions
kered-0.024
iggle-0.022
ered-0.021
ped-0.019
 danced-0.019
Token ice
Token ID4771
Feature activation-2.35e-02

Pos logit contributions
 butcher+0.002
 paramed+0.002
riger+0.002
Mic+0.002
oc+0.002
Neg logit contributions
iggle-0.002
kered-0.002
ered-0.002
ped-0.002
ia-0.002
Token cream
Token ID8566
Feature activation-6.39e-02

Pos logit contributions
 butcher+0.048
Mic+0.047
 paramed+0.045
Charl+0.045
riger+0.044
Neg logit contributions
kered-0.035
iggle-0.033
ia-0.031
ered-0.031
 flew-0.028
Token cone
Token ID27763
Feature activation-3.88e-02

Pos logit contributions
Mic+0.102
Charl+0.098
arre+0.097
 paramed+0.097
 butcher+0.096
Neg logit contributions
kered-0.102
 flew-0.097
atively-0.097
iggle-0.096
 danced-0.094
Token.
Token ID13
Feature activation+9.25e-04

Pos logit contributions
 butcher+0.086
 paramed+0.082
uf+0.076
Mic+0.076
icer+0.076
Neg logit contributions
kered-0.052
iggle-0.050
ered-0.045
ped-0.043
ia-0.043
Token
Token ID198
Feature activation-8.03e-04

Pos logit contributions
kered+0.002
iggle+0.001
ia+0.001
ered+0.001
 danced+0.001
Neg logit contributions
 butcher-0.002
 paramed-0.002
riger-0.001
 dollars-0.001
iw-0.001
Token
Token ID198
Feature activation-6.41e-03

Pos logit contributions
 butcher+0.001
 paramed+0.001
riger+0.001
iw+0.001
uf+0.001
Neg logit contributions
kered-0.002
iggle-0.001
ered-0.001
ia-0.001
ped-0.001
TokenSuddenly
Token ID38582
Feature activation+1.95e-02

Pos logit contributions
 butcher+0.012
 paramed+0.012
iw+0.011
uf+0.010
riger+0.010
Neg logit contributions
kered-0.011
iggle-0.010
ered-0.010
ia-0.010
 danced-0.009
Token So
Token ID1406
Feature activation+2.45e-02

Pos logit contributions
kered+0.023
iggle+0.022
ered+0.021
ped+0.020
ia+0.020
Neg logit contributions
 butcher-0.019
 paramed-0.017
riger-0.015
uf-0.015
oc-0.015
Token he
Token ID339
Feature activation+9.36e-03

Pos logit contributions
kered+0.045
iggle+0.044
ped+0.040
ered+0.038
irled+0.037
Neg logit contributions
 butcher-0.041
 paramed-0.038
oc-0.038
 Which-0.037
 cart-0.034
Token asked
Token ID1965
Feature activation-4.24e-03

Pos logit contributions
kered+0.013
iggle+0.013
ia+0.011
ped+0.010
ered+0.010
Neg logit contributions
 butcher-0.021
 paramed-0.019
oc-0.018
uf-0.018
 sausage-0.017
Token his
Token ID465
Feature activation-2.37e-03

Pos logit contributions
 butcher+0.008
 paramed+0.007
 Which+0.007
oc+0.006
uf+0.006
Neg logit contributions
kered-0.008
iggle-0.007
 flashed-0.006
ered-0.006
ia-0.006
Token dad
Token ID9955
Feature activation-4.86e-02

Pos logit contributions
 butcher+0.005
 paramed+0.005
riger+0.004
oc+0.004
icer+0.004
Neg logit contributions
kered-0.004
iggle-0.003
ered-0.003
ped-0.003
ia-0.003
Token,
Token ID11
Feature activation-6.03e-02

Pos logit contributions
 paramed+0.107
 butcher+0.105
icer+0.101
riger+0.099
Mic+0.097
Neg logit contributions
iggle-0.062
ered-0.059
kered-0.059
ia-0.055
owed-0.054
Token "
Token ID366
Feature activation-4.56e-02

Pos logit contributions
icer+0.158
 butcher+0.148
oc+0.147
riger+0.147
arre+0.144
Neg logit contributions
 blinked-0.044
fully-0.040
 aloud-0.039
atively-0.038
iggle-0.038
TokenWhy
Token ID5195
Feature activation-5.93e-03

Pos logit contributions
 paramed+0.071
riger+0.068
 dollars+0.065
 butcher+0.065
uf+0.064
Neg logit contributions
kered-0.075
 flew-0.075
 blinked-0.075
 soared-0.070
ered-0.070
Token can
Token ID460
Feature activation+3.28e-02

Pos logit contributions
 butcher+0.011
 paramed+0.010
oc+0.009
riger+0.009
 Which+0.009
Neg logit contributions
kered-0.010
iggle-0.010
ped-0.009
ered-0.009
atively-0.008
Token't
Token ID470
Feature activation+4.06e-02

Pos logit contributions
kered+0.062
iggle+0.060
ped+0.055
ered+0.053
ia+0.053
Neg logit contributions
 butcher-0.056
 paramed-0.052
riger-0.048
uf-0.045
 sausage-0.045
Token I
Token ID314
Feature activation+1.19e-02

Pos logit contributions
kered+0.076
iggle+0.072
ped+0.067
ered+0.067
ia+0.065
Neg logit contributions
 butcher-0.072
 paramed-0.066
riger-0.060
uf-0.058
oc-0.058
Token of
Token ID286
Feature activation-3.84e-02

Pos logit contributions
kered+0.008
iggle+0.008
ered+0.007
ped+0.007
ia+0.007
Neg logit contributions
 butcher-0.010
 paramed-0.010
oc-0.009
riger-0.009
uf-0.008
Token his
Token ID465
Feature activation-1.89e-03

Pos logit contributions
 butcher+0.084
 paramed+0.081
riger+0.075
oc+0.074
uf+0.073
Neg logit contributions
kered-0.053
iggle-0.051
ered-0.047
ped-0.045
 flashed-0.045
Token pocket
Token ID10000
Feature activation-2.39e-02

Pos logit contributions
 butcher+0.004
 paramed+0.003
riger+0.003
oc+0.003
uf+0.003
Neg logit contributions
kered-0.003
iggle-0.003
ered-0.003
ped-0.003
ia-0.003
Token and
Token ID290
Feature activation-8.81e-03

Pos logit contributions
 butcher+0.044
 paramed+0.041
oc+0.037
riger+0.036
uf+0.036
Neg logit contributions
kered-0.042
iggle-0.040
ered-0.036
ped-0.036
ia-0.035
Token asked
Token ID1965
Feature activation-3.63e-02

Pos logit contributions
 butcher+0.019
 paramed+0.018
oc+0.016
riger+0.016
 sausage+0.015
Neg logit contributions
kered-0.013
iggle-0.013
ia-0.011
ped-0.010
ered-0.010
Token,
Token ID11
Feature activation-6.03e-02

Pos logit contributions
 paramed+0.076
 butcher+0.076
icer+0.070
riger+0.070
iw+0.069
Neg logit contributions
ered-0.049
kered-0.049
iggle-0.048
ia-0.045
ped-0.042
Token "
Token ID366
Feature activation-4.84e-02

Pos logit contributions
icer+0.147
 butcher+0.146
oc+0.136
Mic+0.134
riger+0.133
Neg logit contributions
 blinked-0.053
atively-0.050
ered-0.047
iggle-0.047
 danced-0.046
TokenWhat
Token ID2061
Feature activation-9.22e-03

Pos logit contributions
 paramed+0.073
riger+0.071
oc+0.069
uf+0.069
 butcher+0.068
Neg logit contributions
ia-0.068
 blinked-0.068
ered-0.068
 flew-0.067
kered-0.066
Token is
Token ID318
Feature activation+1.13e-02

Pos logit contributions
 butcher+0.015
 paramed+0.012
 dollars+0.012
oc+0.012
 Which+0.012
Neg logit contributions
iggle-0.018
kered-0.017
ped-0.017
atively-0.017
ered-0.016
Token that
Token ID326
Feature activation-4.67e-03

Pos logit contributions
kered+0.020
iggle+0.019
ered+0.018
ped+0.017
ia+0.017
Neg logit contributions
 butcher-0.021
 paramed-0.020
riger-0.018
oc-0.018
uf-0.018
Token Tom
Token ID4186
Feature activation-1.78e-02

Pos logit contributions
 butcher+0.008
 paramed+0.007
riger+0.006
 Which+0.006
oc+0.006
Neg logit contributions
kered-0.010
iggle-0.009
ped-0.009
ered-0.009
irled-0.008
Token Tim
Token ID5045
Feature activation-4.26e-03

Pos logit contributions
 butcher+0.044
riger+0.041
 dollars+0.041
 paramed+0.040
uf+0.040
Neg logit contributions
kered-0.026
iggle-0.025
ered-0.022
ped-0.021
 blinked-0.021
Tokenmy
Token ID1820
Feature activation-1.79e-03

Pos logit contributions
 butcher+0.004
 paramed+0.004
icer+0.003
oc+0.003
uf+0.003
Neg logit contributions
kered-0.011
iggle-0.011
ered-0.010
ped-0.010
 flashed-0.010
Token didn
Token ID1422
Feature activation+7.34e-03

Pos logit contributions
 butcher+0.004
 paramed+0.004
oc+0.003
uf+0.003
 sausage+0.003
Neg logit contributions
kered-0.003
iggle-0.003
ered-0.002
ped-0.002
 flashed-0.002
Token't
Token ID470
Feature activation-1.93e-02

Pos logit contributions
kered+0.009
iggle+0.009
ered+0.008
ia+0.007
ped+0.007
Neg logit contributions
 butcher-0.018
 paramed-0.016
iw-0.015
riger-0.015
 dollars-0.015
Token like
Token ID588
Feature activation-3.38e-02

Pos logit contributions
 butcher+0.045
 paramed+0.042
icer+0.040
riger+0.039
uf+0.039
Neg logit contributions
kered-0.025
iggle-0.024
ered-0.021
 danced-0.020
ped-0.020
Token onions
Token ID24681
Feature activation-5.32e-02

Pos logit contributions
 butcher+0.072
 paramed+0.070
riger+0.068
oc+0.066
och+0.066
Neg logit contributions
kered-0.046
iggle-0.045
 happen-0.040
ered-0.039
 danced-0.038
Token and
Token ID290
Feature activation-3.20e-02

Pos logit contributions
 butcher+0.122
 paramed+0.117
icer+0.106
oc+0.106
 Which+0.105
Neg logit contributions
kered-0.070
iggle-0.068
ered-0.059
 danced-0.057
ped-0.057
Token said
Token ID531
Feature activation-2.75e-02

Pos logit contributions
 butcher+0.067
 paramed+0.062
oc+0.055
 Which+0.054
 sausage+0.054
Neg logit contributions
kered-0.051
iggle-0.050
ered-0.044
ia-0.042
ped-0.042
Token,
Token ID11
Feature activation-4.22e-02

Pos logit contributions
 butcher+0.065
icer+0.060
 paramed+0.059
riger+0.058
iw+0.057
Neg logit contributions
kered-0.035
iggle-0.032
ered-0.030
ia-0.028
ped-0.027
Token "
Token ID366
Feature activation-4.12e-02

Pos logit contributions
 butcher+0.088
icer+0.084
iw+0.080
 paramed+0.080
oc+0.078
Neg logit contributions
kered-0.059
iggle-0.055
 danced-0.053
ped-0.053
 blinked-0.052
TokenMom
Token ID29252
Feature activation-1.66e-02

Pos logit contributions
 butcher+0.067
riger+0.063
 paramed+0.062
uf+0.058
 dollars+0.058
Neg logit contributions
kered-0.081
ped-0.067
iggle-0.067
 blinked-0.066
 flew-0.066
Token playing
Token ID2712
Feature activation-1.92e-02

Pos logit contributions
 butcher+0.058
 paramed+0.054
icer+0.049
oc+0.048
uf+0.048
Neg logit contributions
kered-0.047
iggle-0.045
ered-0.042
ped-0.040
 danced-0.040
Token is
Token ID318
Feature activation-2.89e-02

Pos logit contributions
 butcher+0.041
 paramed+0.040
riger+0.035
uf+0.035
icer+0.035
Neg logit contributions
kered-0.029
iggle-0.028
ered-0.025
ped-0.024
 moves-0.024
Token more
Token ID517
Feature activation-9.75e-03

Pos logit contributions
 butcher+0.055
 paramed+0.051
riger+0.045
oc+0.045
uf+0.045
Neg logit contributions
kered-0.050
iggle-0.048
ered-0.044
ped-0.043
ia-0.042
Token important
Token ID1593
Feature activation+1.59e-03

Pos logit contributions
 butcher+0.018
 paramed+0.017
oc+0.016
riger+0.015
uf+0.015
Neg logit contributions
kered-0.017
iggle-0.016
ered-0.015
ped-0.015
ia-0.014
Token than
Token ID621
Feature activation-1.94e-02

Pos logit contributions
kered+0.003
iggle+0.002
ered+0.002
ped+0.002
ia+0.002
Neg logit contributions
 butcher-0.003
 paramed-0.003
riger-0.003
oc-0.003
uf-0.003
Token candy
Token ID18550
Feature activation-5.54e-02

Pos logit contributions
 butcher+0.037
 paramed+0.034
riger+0.030
oc+0.030
uf+0.030
Neg logit contributions
kered-0.034
iggle-0.032
ered-0.030
ped-0.029
ia-0.028
Token.
Token ID13
Feature activation-4.98e-03

Pos logit contributions
 butcher+0.125
 paramed+0.124
icer+0.109
riger+0.108
uf+0.108
Neg logit contributions
kered-0.073
iggle-0.070
ia-0.060
ered-0.059
 danced-0.059
Token<|endoftext|>
Token ID50256
Feature activation-2.98e-02

Pos logit contributions
 butcher+0.011
 paramed+0.011
 stret+0.010
riger+0.010
 dollars+0.010
Neg logit contributions
kered-0.006
iggle-0.006
ia-0.005
 blinked-0.005
 Lia-0.005
TokenOnce
Token ID7454
Feature activation-1.02e-02

Pos logit contributions
 butcher+0.046
 paramed+0.045
riger+0.038
 dollars+0.037
uf+0.037
Neg logit contributions
kered-0.061
iggle-0.059
ia-0.055
ered-0.054
 blinked-0.053
Token upon
Token ID2402
Feature activation+3.11e-02

Pos logit contributions
 butcher+0.016
 paramed+0.014
icer+0.013
 Which+0.013
riger+0.013
Neg logit contributions
kered-0.021
iggle-0.019
ped-0.019
ered-0.019
 flashed-0.018
Token a
Token ID257
Feature activation-1.26e-02

Pos logit contributions
kered+0.067
ered+0.067
iggle+0.066
ped+0.063
irled+0.063
Neg logit contributions
 butcher-0.039
 sausage-0.031
Why-0.031
Mic-0.031
 charity-0.030