TOP ACTIVATIONS
MAX = 0.063

They took the beef to the checkout counter and
home . Ben opened the beef and started to eat .
man wanted to share his beef with everyone . He believed
had lots of water . But when Qu ack went to
home , she shared the beef with her family . But
ie and Lily shared their beef for lunch and laughed and
. She stepped on the beef and slipped . She fell
" It is cute , but I have a better pe
new treasure . But then , Qu ackers realized
this game . But then , it was time
They decided to share the beef and be friends again .
looks like a message , but I 'm not sure what
happy . They shared the sausage and had a fun time
in the bird house . But she could not find Z
She cut the beef into small pieces . Little
<|endoftext|> M um cooked a beef . It was smooth and
. M oral : Hon esty , generosity and
cut . They shared the sausage with their friends and everyone
. We can look , but we should not touch it
with him . But when Fl uffy got home

MIN ACTIVATIONS
MIN = -0.068

was a little girl with blonde hair . She had a
glowing wand and having the sill iest time of his life
only three , with curly blonde hair and she loved to
and ran home with the sill iest of smiles . <|endoftext|>
, a small girl with blonde hair came over to her
near the clouds . Everywhere it flew , it left a
wind and take it wherever it wanted to go . One
loved to sing . Everywhere it went , it would sing
her mom if she could have a slice of pie .
its wings and flew wherever it wanted to go , but
years old and had long blonde hair . She loved to
very adorable , with long blonde hair and piercing blue eyes
then , Tim my slipped and fell . He hit his
put it on the window sill with a tight lid .
could do anything , as long as he stayed fit and
window and said , " J enna , there 's a
looking around it . Everywhere it looked , there was beauty
coin . But she slipped and fell into the water .
sand tower fell and the sand scattered everywhere .
and spilled his bucket of sand . Jane was so angry

INTERVAL 0.030 - 0.063
CONTAINS 0.570%

play lawyer together sometimes , but only after Lily did her
that 's really cool ! But be careful , it 's
more to write ." But Tommy didn 't listen .
She finished her ice - cream and said goodbye to the
one to ride on . But she promised they could come

INTERVAL -0.003 - 0.030
CONTAINS 59.573%

, they sat down to eat the pancakes . They were
a big dog . The dog is barking loud . Anna
the smile y face and the heart . She reads the
excited to go to the lake with their dad . They
" Not yet , sweet ie . We have to

INTERVAL -0.036 - -0.003
CONTAINS 39.679%

waved goodbye to all his friends and skipped down the street
worry , Tim ! If you think it 's too spicy
receive the lovely fish as a gift . From that day
a long pipe and a seat for the driver . Their
's mom my and daddy said they wanted to buy the

INTERVAL -0.068 - -0.036
CONTAINS 0.178%

Oh , Tom , what did you do ? You were
said she could no longer get past ries . The girl
with trees and flowers and benches . She thought she could
sand was rough and the waves were big .
in the rain until his clothes were soaked through . Then
Token
Token ID198
Feature activation+7.82e-03

Pos logit contributions
 surroundings+0.022
 bond+0.021
 eyebrow+0.020
esty+0.020
 Believe+0.019
Neg logit contributions
br-0.020
 ow-0.020
zed-0.020
obb-0.019
bridge-0.018
Token
Token ID198
Feature activation+2.76e-03

Pos logit contributions
 surroundings+0.013
 bond+0.012
esty+0.012
 eyebrow+0.012
assion+0.012
Neg logit contributions
br-0.011
zed-0.011
 ow-0.011
obb-0.010
aster-0.010
TokenThey
Token ID2990
Feature activation+8.08e-03

Pos logit contributions
 surroundings+0.004
 bond+0.004
 eyebrow+0.004
esty+0.004
assion+0.004
Neg logit contributions
br-0.004
zed-0.004
 ow-0.004
obb-0.004
aster-0.004
Token took
Token ID1718
Feature activation+7.26e-03

Pos logit contributions
 surroundings+0.014
 bond+0.013
 eyebrow+0.013
esty+0.013
 Believe+0.013
Neg logit contributions
 ow-0.011
br-0.010
zed-0.010
obb-0.010
bridge-0.009
Token the
Token ID262
Feature activation+9.42e-03

Pos logit contributions
 surroundings+0.012
 bond+0.011
 eyebrow+0.011
assion+0.011
esty+0.011
Neg logit contributions
br-0.010
 ow-0.010
zed-0.010
obb-0.009
aster-0.009
Token beef
Token ID12023
Feature activation+6.29e-02

Pos logit contributions
 surroundings+0.016
esty+0.015
 Believe+0.015
assion+0.015
 eyebrow+0.014
Neg logit contributions
 ow-0.013
br-0.013
obb-0.012
zed-0.012
bridge-0.011
Token to
Token ID284
Feature activation+2.07e-02

Pos logit contributions
assion+0.100
 Believe+0.099
 rhythms+0.099
 Winning+0.098
esty+0.098
Neg logit contributions
 mo-0.077
 cor-0.077
 o-0.076
 ow-0.075
br-0.075
Token the
Token ID262
Feature activation+1.12e-02

Pos logit contributions
 surroundings+0.036
 bond+0.034
 eyebrow+0.033
esty+0.033
 Believe+0.033
Neg logit contributions
 ow-0.028
br-0.027
zed-0.027
obb-0.026
bridge-0.023
Token checkout
Token ID28006
Feature activation+2.63e-02

Pos logit contributions
 eyebrow+0.021
 surroundings+0.021
 Believe+0.021
esty+0.021
 rhythms+0.020
Neg logit contributions
 ow-0.013
aster-0.011
br-0.011
obb-0.011
 o-0.011
Token counter
Token ID3753
Feature activation+3.03e-02

Pos logit contributions
 surroundings+0.036
 eyebrow+0.034
 bond+0.032
owner+0.032
esty+0.030
Neg logit contributions
 ow-0.047
br-0.045
obb-0.043
zed-0.042
bridge-0.039
Token and
Token ID290
Feature activation+1.17e-02

Pos logit contributions
 surroundings+0.052
 bond+0.050
 Believe+0.049
esty+0.048
 rhythms+0.048
Neg logit contributions
zed-0.038
 ow-0.037
br-0.037
obb-0.036
 mo-0.035
Token home
Token ID1363
Feature activation+7.48e-03

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
obb+0.004
bridge+0.003
Neg logit contributions
 surroundings-0.004
 bond-0.003
 eyebrow-0.003
esty-0.003
 Believe-0.003
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
 surroundings+0.014
esty+0.013
 bond+0.013
 Believe+0.013
assion+0.013
Neg logit contributions
zed-0.009
 ow-0.009
br-0.009
obb-0.008
bridge-0.008
Token Ben
Token ID3932
Feature activation+6.99e-03

Pos logit contributions
 surroundings+0.024
 bond+0.022
esty+0.022
 eyebrow+0.022
 Believe+0.022
Neg logit contributions
 ow-0.020
br-0.020
zed-0.019
obb-0.019
bridge-0.017
Token opened
Token ID4721
Feature activation+2.15e-03

Pos logit contributions
 surroundings+0.011
 bond+0.010
assion+0.010
esty+0.010
 eyebrow+0.010
Neg logit contributions
zed-0.011
 ow-0.011
br-0.011
obb-0.010
 reached-0.009
Token the
Token ID262
Feature activation+4.02e-03

Pos logit contributions
 surroundings+0.005
 bond+0.004
esty+0.004
assion+0.004
 eyebrow+0.004
Neg logit contributions
 ow-0.002
zed-0.002
br-0.002
obb-0.002
 mo-0.002
Token beef
Token ID12023
Feature activation+6.19e-02

Pos logit contributions
 surroundings+0.007
esty+0.007
 Believe+0.007
 bond+0.007
 rhythms+0.007
Neg logit contributions
 ow-0.005
br-0.005
obb-0.004
zed-0.004
 mo-0.004
Token and
Token ID290
Feature activation-6.65e-03

Pos logit contributions
 surroundings+0.107
esty+0.107
 rhythms+0.103
 Fighting+0.103
assion+0.103
Neg logit contributions
 ow-0.076
br-0.073
zed-0.073
 mo-0.072
 cuc-0.070
Token started
Token ID2067
Feature activation-1.07e-02

Pos logit contributions
 ow+0.008
br+0.008
zed+0.008
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.012
 bond-0.011
 eyebrow-0.011
esty-0.011
 Believe-0.011
Token to
Token ID284
Feature activation+6.15e-03

Pos logit contributions
 ow+0.019
obb+0.019
br+0.018
bridge+0.017
zed+0.017
Neg logit contributions
 surroundings-0.015
 bond-0.014
 Believe-0.013
assion-0.013
 eyebrow-0.013
Token eat
Token ID4483
Feature activation+4.84e-03

Pos logit contributions
 surroundings+0.011
 bond+0.010
 eyebrow+0.010
esty+0.010
 Believe+0.010
Neg logit contributions
 ow-0.009
br-0.008
zed-0.008
obb-0.008
bridge-0.007
Token.
Token ID13
Feature activation+9.49e-03

Pos logit contributions
 surroundings+0.009
 bond+0.009
esty+0.009
 eyebrow+0.009
assion+0.009
Neg logit contributions
 ow-0.006
br-0.005
zed-0.005
obb-0.005
aster-0.005
Token man
Token ID582
Feature activation+3.62e-03

Pos logit contributions
 ow+0.023
br+0.023
zed+0.022
obb+0.021
bridge+0.020
Neg logit contributions
 surroundings-0.022
 bond-0.020
 eyebrow-0.020
esty-0.019
 Believe-0.019
Token wanted
Token ID2227
Feature activation-7.21e-03

Pos logit contributions
 surroundings+0.006
 bond+0.005
 eyebrow+0.005
esty+0.005
 Believe+0.005
Neg logit contributions
 ow-0.005
br-0.005
zed-0.005
obb-0.005
bridge-0.005
Token to
Token ID284
Feature activation-6.03e-03

Pos logit contributions
br+0.011
 ow+0.011
obb+0.011
zed+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.011
 bond-0.010
 eyebrow-0.009
 Believe-0.009
esty-0.009
Token share
Token ID2648
Feature activation-7.83e-03

Pos logit contributions
br+0.009
obb+0.009
 ow+0.009
zed+0.009
bridge+0.008
Neg logit contributions
 bond-0.009
 surroundings-0.009
 Believe-0.008
 eyebrow-0.008
 communicate-0.008
Token his
Token ID465
Feature activation+7.63e-03

Pos logit contributions
 ow+0.010
br+0.010
zed+0.010
obb+0.009
bridge+0.009
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.013
esty-0.013
 Believe-0.013
Token beef
Token ID12023
Feature activation+5.99e-02

Pos logit contributions
assion+0.015
 surroundings+0.015
 Believe+0.015
 eyebrow+0.015
 rhythms+0.015
Neg logit contributions
 ow-0.008
zed-0.007
br-0.007
obb-0.006
aster-0.006
Token with
Token ID351
Feature activation-1.74e-02

Pos logit contributions
 Fighting+0.103
assion+0.102
 surroundings+0.100
 eyebrow+0.099
 Believe+0.099
Neg logit contributions
 ow-0.071
zed-0.070
 cuc-0.068
br-0.067
 peach-0.065
Token everyone
Token ID2506
Feature activation-2.33e-02

Pos logit contributions
br+0.027
 ow+0.025
obb+0.025
zed+0.025
bridge+0.023
Neg logit contributions
 surroundings-0.028
 bond-0.025
esty-0.024
 Believe-0.024
assion-0.024
Token.
Token ID13
Feature activation-5.22e-03

Pos logit contributions
 ow+0.033
br+0.032
obb+0.032
zed+0.031
bridge+0.028
Neg logit contributions
 surroundings-0.039
 bond-0.037
 Believe-0.036
esty-0.036
 eyebrow-0.035
Token He
Token ID679
Feature activation+9.36e-03

Pos logit contributions
br+0.006
 ow+0.006
zed+0.006
obb+0.005
aster+0.005
Neg logit contributions
 surroundings-0.010
 bond-0.009
 eyebrow-0.009
esty-0.009
 rhythms-0.009
Token believed
Token ID4762
Feature activation-1.34e-03

Pos logit contributions
 surroundings+0.016
 bond+0.015
 eyebrow+0.015
esty+0.015
 Believe+0.015
Neg logit contributions
 ow-0.013
br-0.013
zed-0.012
obb-0.012
bridge-0.011
Token had
Token ID550
Feature activation-2.68e-03

Pos logit contributions
 surroundings+0.026
 bond+0.024
 Believe+0.024
 eyebrow+0.024
esty+0.023
Neg logit contributions
 ow-0.014
br-0.013
zed-0.012
obb-0.011
 mo-0.011
Token lots
Token ID6041
Feature activation-2.04e-02

Pos logit contributions
obb+0.004
br+0.004
zed+0.004
aster+0.004
 ow+0.004
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.004
assion-0.004
 rhythms-0.003
Token of
Token ID286
Feature activation+8.90e-04

Pos logit contributions
 ow+0.024
zed+0.023
br+0.023
obb+0.022
bridge+0.020
Neg logit contributions
 surroundings-0.039
 bond-0.037
 eyebrow-0.036
 Believe-0.035
esty-0.035
Token water
Token ID1660
Feature activation-6.99e-03

Pos logit contributions
 surroundings+0.002
esty+0.002
assion+0.002
 bond+0.002
 Believe+0.002
Neg logit contributions
 ow-0.001
br-0.001
obb-0.001
zed-0.001
 mo-0.001
Token.
Token ID13
Feature activation+2.92e-02

Pos logit contributions
br+0.011
zed+0.010
 ow+0.010
obb+0.010
aster+0.009
Neg logit contributions
 surroundings-0.011
 bond-0.010
esty-0.010
 eyebrow-0.010
assion-0.010
Token But
Token ID887
Feature activation+5.94e-02

Pos logit contributions
 surroundings+0.047
 bond+0.043
esty+0.043
 Believe+0.043
 eyebrow+0.042
Neg logit contributions
 ow-0.043
br-0.043
zed-0.041
obb-0.040
bridge-0.038
Token when
Token ID618
Feature activation+3.30e-02

Pos logit contributions
 surroundings+0.111
 bond+0.108
 eyebrow+0.108
assion+0.105
esty+0.103
Neg logit contributions
 ow-0.073
zed-0.070
br-0.067
obb-0.063
 reached-0.060
Token Qu
Token ID2264
Feature activation-1.13e-02

Pos logit contributions
 surroundings+0.054
 bond+0.050
 Believe+0.049
esty+0.049
assion+0.047
Neg logit contributions
br-0.047
 ow-0.046
zed-0.045
obb-0.045
bridge-0.043
Tokenack
Token ID441
Feature activation-1.33e-02

Pos logit contributions
 ow+0.020
br+0.019
bridge+0.018
zed+0.018
obb+0.017
Neg logit contributions
 surroundings-0.016
esty-0.014
 bond-0.014
 Believe-0.013
 eyebrow-0.013
Token went
Token ID1816
Feature activation-3.71e-03

Pos logit contributions
br+0.024
 ow+0.024
obb+0.023
zed+0.022
bridge+0.022
Neg logit contributions
 surroundings-0.017
 eyebrow-0.015
esty-0.015
 bond-0.014
 Believe-0.014
Token to
Token ID284
Feature activation+1.66e-02

Pos logit contributions
br+0.006
 ow+0.006
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.005
 eyebrow-0.005
esty-0.005
assion-0.005
Token home
Token ID1363
Feature activation+1.37e-02

Pos logit contributions
 ow+0.034
zed+0.034
br+0.033
obb+0.032
aster+0.030
Neg logit contributions
 surroundings-0.026
 bond-0.024
 eyebrow-0.024
esty-0.023
 rhythms-0.023
Token,
Token ID11
Feature activation-3.13e-03

Pos logit contributions
 surroundings+0.024
 bond+0.023
esty+0.023
assion+0.022
 eyebrow+0.022
Neg logit contributions
 ow-0.018
br-0.018
zed-0.018
obb-0.017
aster-0.015
Token she
Token ID673
Feature activation-5.11e-03

Pos logit contributions
 ow+0.003
zed+0.003
br+0.003
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.007
 bond-0.007
 eyebrow-0.007
esty-0.007
assion-0.007
Token shared
Token ID4888
Feature activation-1.22e-02

Pos logit contributions
 ow+0.007
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.008
 bond-0.008
 eyebrow-0.008
esty-0.008
assion-0.007
Token the
Token ID262
Feature activation+1.47e-02

Pos logit contributions
 ow+0.016
br+0.016
zed+0.016
obb+0.016
bridge+0.014
Neg logit contributions
 surroundings-0.021
 bond-0.020
 eyebrow-0.019
esty-0.019
 Believe-0.019
Token beef
Token ID12023
Feature activation+5.91e-02

Pos logit contributions
 surroundings+0.033
 rhythms+0.032
esty+0.032
assion+0.032
 Fighting+0.032
Neg logit contributions
 ow-0.012
br-0.011
zed-0.011
obb-0.009
aster-0.008
Token with
Token ID351
Feature activation-1.18e-02

Pos logit contributions
 surroundings+0.092
assion+0.091
 Fighting+0.090
esty+0.089
 Believe+0.089
Neg logit contributions
zed-0.082
 ow-0.080
br-0.079
 cuc-0.073
 cor-0.072
Token her
Token ID607
Feature activation+3.94e-03

Pos logit contributions
 ow+0.015
br+0.014
zed+0.014
obb+0.013
bridge+0.012
Neg logit contributions
 surroundings-0.022
 bond-0.021
 eyebrow-0.020
esty-0.020
 Believe-0.020
Token family
Token ID1641
Feature activation+9.31e-03

Pos logit contributions
 eyebrow+0.007
assion+0.006
 Believe+0.006
 Fighting+0.006
esty+0.006
Neg logit contributions
 ow-0.006
br-0.005
zed-0.005
obb-0.005
 mo-0.005
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
 surroundings+0.018
esty+0.018
assion+0.017
 eyebrow+0.017
 Believe+0.017
Neg logit contributions
zed-0.010
 ow-0.009
br-0.009
aster-0.008
obb-0.008
Token But
Token ID887
Feature activation+3.04e-02

Pos logit contributions
 surroundings+0.018
 bond+0.017
 eyebrow+0.016
esty+0.016
 Believe+0.016
Neg logit contributions
 ow-0.021
br-0.021
zed-0.020
obb-0.020
bridge-0.018
Tokenie
Token ID494
Feature activation-1.33e-02

Pos logit contributions
br+0.005
 ow+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.005
 bond-0.005
 eyebrow-0.005
esty-0.004
 Believe-0.004
Token and
Token ID290
Feature activation-2.48e-04

Pos logit contributions
br+0.018
 ow+0.018
obb+0.018
zed+0.017
bridge+0.016
Neg logit contributions
 surroundings-0.023
 bond-0.021
 eyebrow-0.021
esty-0.020
 Believe-0.020
Token Lily
Token ID20037
Feature activation-1.26e-02

Pos logit contributions
 ow+0.000
br+0.000
zed+0.000
obb+0.000
bridge+0.000
Neg logit contributions
 surroundings-0.000
 bond-0.000
 eyebrow-0.000
esty-0.000
 Believe-0.000
Token shared
Token ID4888
Feature activation-3.02e-04

Pos logit contributions
br+0.014
 ow+0.014
obb+0.014
zed+0.013
bridge+0.012
Neg logit contributions
 surroundings-0.024
 bond-0.023
esty-0.022
 eyebrow-0.022
assion-0.022
Token their
Token ID511
Feature activation-5.79e-03

Pos logit contributions
 ow+0.000
zed+0.000
br+0.000
obb+0.000
aster+0.000
Neg logit contributions
 surroundings-0.001
 eyebrow-0.001
assion-0.001
 Believe-0.001
esty-0.001
Token beef
Token ID12023
Feature activation+5.85e-02

Pos logit contributions
 ow+0.007
zed+0.007
br+0.007
obb+0.006
aster+0.005
Neg logit contributions
 surroundings-0.011
esty-0.010
 eyebrow-0.010
assion-0.010
 Believe-0.010
Token for
Token ID329
Feature activation+1.62e-02

Pos logit contributions
 Fighting+0.097
assion+0.097
 Believe+0.094
 eyebrow+0.093
 surroundings+0.092
Neg logit contributions
zed-0.079
 ow-0.077
br-0.073
 cor-0.069
 mo-0.069
Token lunch
Token ID9965
Feature activation-9.66e-04

Pos logit contributions
 surroundings+0.026
 bond+0.026
 ourselves+0.023
 themselves+0.023
 Believe+0.023
Neg logit contributions
br-0.024
obb-0.023
bridge-0.022
 ow-0.022
zed-0.021
Token and
Token ID290
Feature activation+2.33e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.001
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
esty-0.001
 eyebrow-0.001
 Believe-0.001
Token laughed
Token ID13818
Feature activation+1.23e-02

Pos logit contributions
 surroundings+0.004
 eyebrow+0.004
esty+0.004
 Believe+0.004
assion+0.004
Neg logit contributions
 ow-0.003
zed-0.003
br-0.003
obb-0.002
aster-0.002
Token and
Token ID290
Feature activation+1.93e-03

Pos logit contributions
 surroundings+0.020
 bond+0.018
 eyebrow+0.018
esty+0.018
 Believe+0.018
Neg logit contributions
 ow-0.018
br-0.018
zed-0.018
obb-0.017
bridge-0.016
Token.
Token ID13
Feature activation+1.92e-02

Pos logit contributions
 ow+0.030
br+0.029
zed+0.028
obb+0.028
bridge+0.025
Neg logit contributions
 surroundings-0.034
 bond-0.032
 eyebrow-0.031
 Believe-0.030
esty-0.030
Token She
Token ID1375
Feature activation+5.67e-03

Pos logit contributions
 surroundings+0.031
 bond+0.029
 eyebrow+0.028
esty+0.028
assion+0.027
Neg logit contributions
 ow-0.028
br-0.028
zed-0.027
obb-0.026
bridge-0.025
Token stepped
Token ID10764
Feature activation+1.35e-02

Pos logit contributions
 surroundings+0.009
 bond+0.009
 eyebrow+0.008
esty+0.008
 Believe+0.008
Neg logit contributions
 ow-0.008
br-0.008
zed-0.008
obb-0.008
bridge-0.007
Token on
Token ID319
Feature activation+1.78e-03

Pos logit contributions
 surroundings+0.017
 eyebrow+0.016
 bond+0.015
 Believe+0.015
esty+0.015
Neg logit contributions
 ow-0.025
br-0.024
zed-0.024
obb-0.023
bridge-0.022
Token the
Token ID262
Feature activation+2.36e-02

Pos logit contributions
 surroundings+0.003
esty+0.003
 bond+0.003
 eyebrow+0.003
assion+0.003
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
aster-0.002
Token beef
Token ID12023
Feature activation+5.84e-02

Pos logit contributions
 surroundings+0.041
esty+0.040
 Believe+0.040
 bond+0.039
assion+0.039
Neg logit contributions
 ow-0.032
br-0.030
zed-0.028
obb-0.028
 mo-0.027
Token and
Token ID290
Feature activation-1.59e-03

Pos logit contributions
 surroundings+0.100
esty+0.095
 bond+0.094
 Believe+0.094
assion+0.093
Neg logit contributions
 ow-0.077
br-0.074
zed-0.074
aster-0.069
obb-0.068
Token slipped
Token ID18859
Feature activation-7.44e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.003
 eyebrow-0.003
esty-0.003
 Believe-0.003
Token.
Token ID13
Feature activation+1.05e-02

Pos logit contributions
 ow+0.013
br+0.013
obb+0.013
zed+0.012
itt+0.012
Neg logit contributions
 eyebrow-0.009
 surroundings-0.009
 bond-0.008
 Believe-0.008
 Fighting-0.008
Token She
Token ID1375
Feature activation-1.86e-02

Pos logit contributions
 surroundings+0.015
 bond+0.014
 eyebrow+0.014
esty+0.014
 Believe+0.014
Neg logit contributions
 ow-0.017
br-0.017
zed-0.016
obb-0.016
bridge-0.015
Token fell
Token ID3214
Feature activation-9.62e-03

Pos logit contributions
br+0.023
 ow+0.023
obb+0.022
zed+0.022
bridge+0.020
Neg logit contributions
 surroundings-0.033
 eyebrow-0.031
 bond-0.031
esty-0.030
 Believe-0.029
Token "
Token ID366
Feature activation+9.27e-03

Pos logit contributions
 surroundings+0.023
 Believe+0.022
assion+0.022
 Fighting+0.022
 eyebrow+0.021
Neg logit contributions
 ow-0.038
obb-0.038
br-0.037
zed-0.036
 arrest-0.035
TokenIt
Token ID1026
Feature activation+2.72e-02

Pos logit contributions
 surroundings+0.015
 bond+0.013
 eyebrow+0.013
idents+0.013
assion+0.013
Neg logit contributions
br-0.015
P-0.013
 ow-0.013
bridge-0.012
zed-0.012
Token is
Token ID318
Feature activation+1.79e-02

Pos logit contributions
 surroundings+0.041
 bond+0.039
 eyebrow+0.037
esty+0.036
assion+0.036
Neg logit contributions
 ow-0.044
br-0.044
zed-0.041
obb-0.040
bridge-0.037
Token cute
Token ID13779
Feature activation+7.77e-03

Pos logit contributions
 surroundings+0.031
 bond+0.030
 eyebrow+0.029
esty+0.029
 Believe+0.028
Neg logit contributions
 ow-0.025
br-0.024
zed-0.022
obb-0.022
bridge-0.020
Token,
Token ID11
Feature activation+2.10e-02

Pos logit contributions
 surroundings+0.013
 bond+0.012
 eyebrow+0.012
esty+0.012
 Believe+0.012
Neg logit contributions
 ow-0.011
br-0.011
zed-0.011
obb-0.011
bridge-0.010
Token but
Token ID475
Feature activation+5.81e-02

Pos logit contributions
 surroundings+0.037
 bond+0.034
esty+0.033
 eyebrow+0.033
assion+0.033
Neg logit contributions
 ow-0.030
br-0.029
zed-0.027
obb-0.026
bridge-0.024
Token I
Token ID314
Feature activation+1.89e-02

Pos logit contributions
 surroundings+0.136
 bond+0.127
 eyebrow+0.127
esty+0.122
owner+0.122
Neg logit contributions
 ow-0.050
br-0.043
 cuc-0.035
zed-0.035
 pr-0.034
Token have
Token ID423
Feature activation-1.04e-02

Pos logit contributions
 surroundings+0.031
 eyebrow+0.027
assion+0.027
 bond+0.027
 rhythms+0.027
Neg logit contributions
br-0.028
 ow-0.028
obb-0.027
zed-0.026
 reached-0.025
Token a
Token ID257
Feature activation-3.81e-03

Pos logit contributions
br+0.015
zed+0.015
 ow+0.015
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.017
 bond-0.015
esty-0.015
 Believe-0.015
 eyebrow-0.015
Token better
Token ID1365
Feature activation+8.20e-03

Pos logit contributions
 ow+0.005
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.007
 bond-0.006
 eyebrow-0.006
esty-0.006
 Believe-0.006
Token pe
Token ID613
Feature activation-1.30e-02

Pos logit contributions
 surroundings+0.013
 bond+0.012
 eyebrow+0.012
esty+0.012
 Believe+0.012
Neg logit contributions
 ow-0.012
zed-0.012
br-0.012
obb-0.012
bridge-0.011
Token new
Token ID649
Feature activation-1.28e-02

Pos logit contributions
br+0.003
 ow+0.003
zed+0.003
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.003
 bond-0.003
 eyebrow-0.003
esty-0.003
 Believe-0.003
Token treasure
Token ID14068
Feature activation-2.17e-02

Pos logit contributions
 ow+0.017
br+0.017
zed+0.016
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.022
 bond-0.021
esty-0.021
 eyebrow-0.021
 Believe-0.021
Token.
Token ID13
Feature activation+2.47e-02

Pos logit contributions
 ow+0.031
obb+0.030
zed+0.030
br+0.030
aster+0.027
Neg logit contributions
 surroundings-0.037
 bond-0.034
assion-0.033
 eyebrow-0.033
esty-0.033
Token
Token ID198
Feature activation+1.96e-02

Pos logit contributions
 surroundings+0.037
 bond+0.034
 eyebrow+0.033
esty+0.033
 Believe+0.033
Neg logit contributions
 ow-0.040
br-0.039
zed-0.038
obb-0.037
bridge-0.034
Token
Token ID198
Feature activation+2.26e-02

Pos logit contributions
 surroundings+0.030
 bond+0.028
esty+0.028
 eyebrow+0.028
 Believe+0.027
Neg logit contributions
 ow-0.030
br-0.030
zed-0.029
obb-0.028
bridge-0.026
TokenBut
Token ID1537
Feature activation+5.80e-02

Pos logit contributions
 surroundings+0.030
 bond+0.028
 eyebrow+0.027
esty+0.027
 Believe+0.027
Neg logit contributions
 ow-0.039
br-0.039
zed-0.038
obb-0.037
bridge-0.035
Token then
Token ID788
Feature activation+3.19e-02

Pos logit contributions
 surroundings+0.077
 bond+0.073
 eyebrow+0.073
assion+0.070
 rhythms+0.068
Neg logit contributions
 ow-0.101
zed-0.101
br-0.098
obb-0.093
 reached-0.089
Token,
Token ID11
Feature activation+3.61e-02

Pos logit contributions
 surroundings+0.051
 bond+0.047
esty+0.046
 Believe+0.046
 eyebrow+0.046
Neg logit contributions
 ow-0.047
br-0.047
zed-0.046
obb-0.045
bridge-0.042
Token Qu
Token ID2264
Feature activation-1.30e-02

Pos logit contributions
 surroundings+0.057
 bond+0.053
 Believe+0.053
esty+0.052
 eyebrow+0.051
Neg logit contributions
br-0.052
 ow-0.052
zed-0.051
obb-0.050
bridge-0.048
Tokenackers
Token ID28874
Feature activation+4.19e-03

Pos logit contributions
 ow+0.016
br+0.016
zed+0.015
bridge+0.014
 arrest+0.013
Neg logit contributions
 surroundings-0.026
esty-0.024
 bond-0.023
 eyebrow-0.023
 Believe-0.023
Token realized
Token ID6939
Feature activation+2.34e-03

Pos logit contributions
 surroundings+0.006
esty+0.006
 bond+0.006
 eyebrow+0.006
 Believe+0.006
Neg logit contributions
br-0.006
 ow-0.006
zed-0.006
obb-0.006
bridge-0.006
Token this
Token ID428
Feature activation+7.09e-03

Pos logit contributions
 surroundings+0.013
 eyebrow+0.013
 bond+0.013
esty+0.013
assion+0.013
Neg logit contributions
br-0.012
 ow-0.012
zed-0.012
obb-0.011
bridge-0.011
Token game
Token ID983
Feature activation+1.01e-03

Pos logit contributions
 surroundings+0.010
 bond+0.009
 rhythms+0.008
 Believe+0.008
 eyebrow+0.008
Neg logit contributions
 ow-0.012
zed-0.012
br-0.012
obb-0.012
 arrest-0.011
Token.
Token ID13
Feature activation+3.41e-02

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
esty+0.002
 Believe+0.002
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token
Token ID198
Feature activation+2.69e-02

Pos logit contributions
 surroundings+0.062
 bond+0.061
 eyebrow+0.059
 property+0.056
smanship+0.056
Neg logit contributions
br-0.045
zed-0.040
 ow-0.040
 reached-0.038
obb-0.037
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
 surroundings+0.048
esty+0.046
 bond+0.046
 eyebrow+0.044
assion+0.043
Neg logit contributions
br-0.035
zed-0.035
 ow-0.035
obb-0.031
aster-0.030
TokenBut
Token ID1537
Feature activation+5.80e-02

Pos logit contributions
 surroundings+0.042
 bond+0.039
 eyebrow+0.038
wood+0.037
 zone+0.036
Neg logit contributions
br-0.048
zed-0.045
 ow-0.042
obb-0.042
P-0.041
Token then
Token ID788
Feature activation+2.99e-02

Pos logit contributions
 eyebrow+0.106
 surroundings+0.106
rolley+0.101
 bond+0.100
liness+0.098
Neg logit contributions
br-0.076
 ow-0.074
 reached-0.069
zed-0.068
 mo-0.064
Token,
Token ID11
Feature activation+3.65e-02

Pos logit contributions
 surroundings+0.060
 eyebrow+0.059
 bond+0.058
assion+0.055
esty+0.055
Neg logit contributions
br-0.035
 ow-0.034
zed-0.029
obb-0.028
 mo-0.025
Token it
Token ID340
Feature activation-1.02e-02

Pos logit contributions
 surroundings+0.078
 eyebrow+0.077
 bond+0.074
esty+0.072
liness+0.072
Neg logit contributions
br-0.039
 ow-0.036
zed-0.030
obb-0.030
 blast-0.030
Token was
Token ID373
Feature activation-3.73e-03

Pos logit contributions
 ow+0.015
br+0.015
zed+0.014
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.017
 bond-0.016
 eyebrow-0.015
esty-0.015
 Believe-0.015
Token time
Token ID640
Feature activation+1.87e-02

Pos logit contributions
br+0.004
 ow+0.004
zed+0.004
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.008
 bond-0.007
 eyebrow-0.007
 Believe-0.007
assion-0.007
Token They
Token ID1119
Feature activation-2.73e-03

Pos logit contributions
 surroundings+0.024
 bond+0.022
 rhythms+0.022
 eyebrow+0.021
 zone+0.021
Neg logit contributions
 ow-0.016
br-0.015
zed-0.014
obb-0.013
 reached-0.013
Token decided
Token ID3066
Feature activation-4.20e-03

Pos logit contributions
 ow+0.004
br+0.003
zed+0.003
obb+0.003
 mo+0.003
Neg logit contributions
 surroundings-0.005
 bond-0.004
esty-0.004
 eyebrow-0.004
 Believe-0.004
Token to
Token ID284
Feature activation-1.07e-03

Pos logit contributions
zed+0.005
 ow+0.005
br+0.005
obb+0.005
 arrest+0.004
Neg logit contributions
 surroundings-0.008
 bond-0.007
 eyebrow-0.007
esty-0.007
 Believe-0.007
Token share
Token ID2648
Feature activation-5.87e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.001
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.002
 eyebrow-0.002
 bond-0.002
esty-0.002
assion-0.002
Token the
Token ID262
Feature activation-4.63e-03

Pos logit contributions
 ow+0.007
br+0.006
zed+0.006
aster+0.005
obb+0.005
Neg logit contributions
 surroundings-0.012
esty-0.011
 eyebrow-0.011
 bond-0.011
assion-0.011
Token beef
Token ID12023
Feature activation+5.79e-02

Pos logit contributions
 ow+0.006
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.009
 bond-0.008
esty-0.008
 eyebrow-0.008
 Believe-0.008
Token and
Token ID290
Feature activation-6.73e-04

Pos logit contributions
 surroundings+0.091
assion+0.089
 Fighting+0.086
 Believe+0.086
 eyebrow+0.086
Neg logit contributions
zed-0.078
 ow-0.077
br-0.076
obb-0.072
 cuc-0.071
Token be
Token ID307
Feature activation-7.16e-03

Pos logit contributions
 ow+0.001
zed+0.001
br+0.001
aster+0.001
 arrest+0.001
Neg logit contributions
 surroundings-0.001
 eyebrow-0.001
esty-0.001
assion-0.001
 Believe-0.001
Token friends
Token ID2460
Feature activation-1.86e-02

Pos logit contributions
 ow+0.011
br+0.011
zed+0.011
obb+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.011
 bond-0.010
 eyebrow-0.010
esty-0.010
 Believe-0.010
Token again
Token ID757
Feature activation-4.73e-03

Pos logit contributions
br+0.023
 ow+0.023
zed+0.023
obb+0.021
bridge+0.020
Neg logit contributions
 surroundings-0.034
 eyebrow-0.031
 bond-0.031
assion-0.031
esty-0.031
Token.
Token ID13
Feature activation+8.71e-03

Pos logit contributions
 ow+0.006
br+0.006
zed+0.006
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.009
 bond-0.008
 eyebrow-0.008
esty-0.008
 Believe-0.008
Token looks
Token ID3073
Feature activation+2.52e-02

Pos logit contributions
 surroundings+0.043
 bond+0.040
 eyebrow+0.038
esty+0.037
 Believe+0.036
Neg logit contributions
br-0.043
 ow-0.043
zed-0.041
obb-0.039
bridge-0.036
Token like
Token ID588
Feature activation+1.39e-02

Pos logit contributions
 surroundings+0.044
 bond+0.043
 Believe+0.040
 zone+0.040
esty+0.040
Neg logit contributions
 ow-0.035
br-0.034
obb-0.033
zed-0.029
 pr-0.029
Token a
Token ID257
Feature activation+1.74e-02

Pos logit contributions
 surroundings+0.023
 bond+0.022
 Believe+0.021
 eyebrow+0.021
assion+0.020
Neg logit contributions
 ow-0.019
br-0.019
zed-0.019
obb-0.019
bridge-0.017
Token message
Token ID3275
Feature activation+4.51e-03

Pos logit contributions
 surroundings+0.031
 eyebrow+0.029
esty+0.029
 bond+0.028
 Believe+0.028
Neg logit contributions
br-0.023
 ow-0.023
zed-0.021
obb-0.020
 mo-0.019
Token,
Token ID11
Feature activation+1.22e-02

Pos logit contributions
 surroundings+0.007
 bond+0.007
 eyebrow+0.007
esty+0.007
 Believe+0.007
Neg logit contributions
 ow-0.006
br-0.006
zed-0.006
obb-0.006
bridge-0.006
Token but
Token ID475
Feature activation+5.69e-02

Pos logit contributions
 surroundings+0.024
esty+0.022
 bond+0.022
assion+0.021
 Believe+0.021
Neg logit contributions
 ow-0.016
br-0.014
zed-0.013
obb-0.012
bridge-0.012
Token I
Token ID314
Feature activation+1.31e-02

Pos logit contributions
 surroundings+0.128
 eyebrow+0.121
 bond+0.120
esty+0.119
owner+0.115
Neg logit contributions
 ow-0.051
br-0.042
zed-0.038
 pr-0.036
obb-0.034
Token'm
Token ID1101
Feature activation+4.62e-03

Pos logit contributions
 surroundings+0.022
 bond+0.019
assion+0.019
 eyebrow+0.019
 rhythms+0.019
Neg logit contributions
 ow-0.019
br-0.019
zed-0.018
obb-0.018
 reached-0.017
Token not
Token ID407
Feature activation-7.04e-04

Pos logit contributions
 Believe+0.006
 surroundings+0.006
 eyebrow+0.006
 Fighting+0.005
 bond+0.005
Neg logit contributions
br-0.008
 ow-0.008
zed-0.008
bridge-0.007
obb-0.007
Token sure
Token ID1654
Feature activation-1.01e-02

Pos logit contributions
br+0.001
zed+0.001
 ow+0.001
obb+0.001
bridge+0.001
Neg logit contributions
 surroundings-0.001
 eyebrow-0.001
 Believe-0.001
esty-0.001
 bond-0.001
Token what
Token ID644
Feature activation-8.93e-03

Pos logit contributions
br+0.016
 ow+0.016
zed+0.016
obb+0.016
bridge+0.015
Neg logit contributions
 surroundings-0.015
 bond-0.013
 eyebrow-0.013
 Believe-0.013
esty-0.013
Token happy
Token ID3772
Feature activation-7.95e-03

Pos logit contributions
br+0.012
 ow+0.012
zed+0.012
obb+0.011
bridge+0.011
Neg logit contributions
 surroundings-0.009
 bond-0.009
 eyebrow-0.009
esty-0.008
 Believe-0.008
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
 ow+0.011
br+0.011
zed+0.010
obb+0.010
bridge+0.009
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.013
esty-0.013
 Believe-0.012
Token They
Token ID1119
Feature activation+3.83e-03

Pos logit contributions
 surroundings+0.008
 bond+0.008
 eyebrow+0.008
esty+0.008
 Believe+0.008
Neg logit contributions
 ow-0.009
br-0.009
zed-0.008
obb-0.008
bridge-0.007
Token shared
Token ID4888
Feature activation+8.91e-03

Pos logit contributions
 surroundings+0.006
 bond+0.006
 eyebrow+0.006
esty+0.006
assion+0.006
Neg logit contributions
br-0.005
 ow-0.005
zed-0.005
obb-0.005
bridge-0.005
Token the
Token ID262
Feature activation+1.31e-02

Pos logit contributions
 surroundings+0.019
 zone+0.017
 Believe+0.017
esty+0.017
 bond+0.017
Neg logit contributions
 ow-0.009
zed-0.009
br-0.008
aster-0.007
on-0.007
Token sausage
Token ID31889
Feature activation+5.67e-02

Pos logit contributions
 surroundings+0.028
assion+0.028
esty+0.028
 rhythms+0.027
 Fighting+0.027
Neg logit contributions
 ow-0.012
zed-0.010
br-0.010
obb-0.010
 cuc-0.009
Token and
Token ID290
Feature activation+1.01e-03

Pos logit contributions
 surroundings+0.083
assion+0.078
 Believe+0.077
 bond+0.076
esty+0.076
Neg logit contributions
zed-0.087
 ow-0.087
br-0.086
obb-0.082
on-0.078
Token had
Token ID550
Feature activation+1.26e-03

Pos logit contributions
 surroundings+0.002
 eyebrow+0.002
esty+0.002
 Believe+0.002
assion+0.002
Neg logit contributions
 ow-0.001
zed-0.001
br-0.001
obb-0.001
 mo-0.001
Token a
Token ID257
Feature activation-8.49e-03

Pos logit contributions
 surroundings+0.002
 bond+0.002
esty+0.002
assion+0.002
 eyebrow+0.002
Neg logit contributions
br-0.002
 ow-0.002
obb-0.002
zed-0.002
bridge-0.002
Token fun
Token ID1257
Feature activation-5.95e-03

Pos logit contributions
 ow+0.012
zed+0.012
br+0.012
obb+0.012
bridge+0.011
Neg logit contributions
 bond-0.014
 surroundings-0.013
esty-0.012
 eyebrow-0.012
 Believe-0.012
Token time
Token ID640
Feature activation-1.01e-02

Pos logit contributions
obb+0.011
 ow+0.011
br+0.010
bridge+0.010
zed+0.010
Neg logit contributions
 bond-0.009
 surroundings-0.008
 hobbies-0.007
 Believe-0.007
 rhythms-0.007
Token in
Token ID287
Feature activation+6.94e-03

Pos logit contributions
 surroundings+0.016
 bond+0.016
esty+0.015
 Believe+0.015
assion+0.015
Neg logit contributions
 ow-0.011
br-0.010
 reached-0.010
zed-0.010
 mo-0.009
Token the
Token ID262
Feature activation-1.93e-03

Pos logit contributions
 surroundings+0.014
assion+0.013
 bond+0.013
esty+0.013
idents+0.013
Neg logit contributions
 ow-0.008
br-0.008
zed-0.007
obb-0.006
 mo-0.006
Token bird
Token ID6512
Feature activation-4.66e-03

Pos logit contributions
 ow+0.003
br+0.002
 mo+0.002
obb+0.002
 cor+0.002
Neg logit contributions
 Believe-0.003
assion-0.003
 surroundings-0.003
idents-0.003
esty-0.003
Tokenhouse
Token ID4803
Feature activation+2.59e-03

Pos logit contributions
br+0.006
 ow+0.005
zed+0.005
 mo+0.005
eh+0.005
Neg logit contributions
 surroundings-0.009
 bond-0.009
esty-0.008
 Believe-0.008
 eyebrow-0.008
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
 surroundings+0.005
 bond+0.004
esty+0.004
assion+0.004
 eyebrow+0.004
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token But
Token ID887
Feature activation+5.67e-02

Pos logit contributions
 bond+0.040
 surroundings+0.040
 eyebrow+0.037
esty+0.036
smanship+0.036
Neg logit contributions
br-0.032
 ow-0.031
zed-0.030
obb-0.028
 reached-0.027
Token she
Token ID673
Feature activation-1.12e-03

Pos logit contributions
 bond+0.105
 surroundings+0.103
 eyebrow+0.101
esty+0.098
smanship+0.097
Neg logit contributions
br-0.073
 ow-0.072
zed-0.071
 reached-0.069
 mo-0.061
Token could
Token ID714
Feature activation+2.84e-03

Pos logit contributions
 ow+0.002
zed+0.001
br+0.001
obb+0.001
 reached+0.001
Neg logit contributions
 surroundings-0.002
 bond-0.002
assion-0.002
 eyebrow-0.002
esty-0.002
Token not
Token ID407
Feature activation+6.39e-03

Pos logit contributions
 surroundings+0.005
 bond+0.005
 eyebrow+0.005
esty+0.005
assion+0.005
Neg logit contributions
 ow-0.004
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token find
Token ID1064
Feature activation-7.43e-03

Pos logit contributions
 surroundings+0.007
 Believe+0.007
 bond+0.007
 eyebrow+0.007
esty+0.007
Neg logit contributions
br-0.012
 ow-0.012
zed-0.012
obb-0.012
bridge-0.011
Token Z
Token ID1168
Feature activation-1.38e-02

Pos logit contributions
 ow+0.010
br+0.010
zed+0.009
obb+0.009
bridge+0.008
Neg logit contributions
 surroundings-0.013
 bond-0.012
 eyebrow-0.012
esty-0.012
 Believe-0.012
Token
Token ID198
Feature activation+5.69e-03

Pos logit contributions
 surroundings+0.019
 bond+0.018
esty+0.017
 eyebrow+0.017
assion+0.017
Neg logit contributions
 ow-0.018
br-0.018
zed-0.017
obb-0.017
bridge-0.015
Token
Token ID198
Feature activation+3.99e-04

Pos logit contributions
 surroundings+0.008
 eyebrow+0.007
 Believe+0.007
 bond+0.007
esty+0.007
Neg logit contributions
 ow-0.010
br-0.010
zed-0.010
obb-0.010
bridge-0.009
TokenShe
Token ID3347
Feature activation+2.20e-04

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token cut
Token ID2005
Feature activation+1.32e-02

Pos logit contributions
 surroundings+0.000
 bond+0.000
 eyebrow+0.000
esty+0.000
assion+0.000
Neg logit contributions
 ow-0.000
br-0.000
obb-0.000
zed-0.000
bridge-0.000
Token the
Token ID262
Feature activation+2.27e-02

Pos logit contributions
 surroundings+0.025
 bond+0.025
assion+0.024
esty+0.024
 Believe+0.024
Neg logit contributions
 ow-0.016
br-0.016
zed-0.015
obb-0.014
aster-0.013
Token beef
Token ID12023
Feature activation+5.62e-02

Pos logit contributions
 Believe+0.049
 Fighting+0.048
esty+0.047
 rhythms+0.047
 surroundings+0.047
Neg logit contributions
 ow-0.022
br-0.020
zed-0.017
obb-0.017
 cuc-0.017
Token into
Token ID656
Feature activation+2.27e-03

Pos logit contributions
 surroundings+0.088
 bond+0.085
 Believe+0.085
esty+0.084
 Fighting+0.082
Neg logit contributions
 ow-0.079
zed-0.079
br-0.078
obb-0.075
 cuc-0.074
Token small
Token ID1402
Feature activation+8.05e-03

Pos logit contributions
 surroundings+0.004
 bond+0.004
 eyebrow+0.004
esty+0.004
 Believe+0.004
Neg logit contributions
br-0.003
 ow-0.003
zed-0.003
obb-0.003
bridge-0.003
Token pieces
Token ID5207
Feature activation-2.42e-03

Pos logit contributions
 surroundings+0.014
 Believe+0.013
esty+0.013
 bond+0.013
assion+0.013
Neg logit contributions
 ow-0.011
br-0.010
zed-0.009
 cuc-0.009
obb-0.009
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
 ow+0.003
br+0.003
zed+0.003
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.004
esty-0.004
 Believe-0.004
Token Little
Token ID7703
Feature activation+5.61e-03

Pos logit contributions
 surroundings+0.015
 eyebrow+0.014
 Believe+0.013
esty+0.013
 bond+0.013
Neg logit contributions
br-0.021
 ow-0.020
zed-0.020
obb-0.019
bridge-0.018
Token<|endoftext|>
Token ID50256
Feature activation-3.65e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
esty+0.001
 eyebrow+0.001
assion+0.001
Neg logit contributions
 ow-0.001
zed-0.001
br-0.001
obb-0.001
aster-0.001
TokenM
Token ID44
Feature activation+1.96e-02

Pos logit contributions
 ow+0.006
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.005
 Believe-0.005
 eyebrow-0.005
esty-0.005
Tokenum
Token ID388
Feature activation+7.43e-03

Pos logit contributions
 surroundings+0.024
 bond+0.023
 eyebrow+0.021
 Believe+0.020
assion+0.019
Neg logit contributions
br-0.037
 ow-0.036
zed-0.035
obb-0.035
bridge-0.033
Token cooked
Token ID15847
Feature activation+2.33e-02

Pos logit contributions
 surroundings+0.007
 bond+0.007
 eyebrow+0.007
 Believe+0.006
liness+0.006
Neg logit contributions
obb-0.015
br-0.015
 ow-0.015
zed-0.014
bridge-0.013
Token a
Token ID257
Feature activation+1.96e-02

Pos logit contributions
 surroundings+0.040
 bond+0.038
 eyebrow+0.037
esty+0.037
 Believe+0.037
Neg logit contributions
 ow-0.032
br-0.031
zed-0.030
obb-0.029
bridge-0.027
Token beef
Token ID12023
Feature activation+5.61e-02

Pos logit contributions
 surroundings+0.041
esty+0.039
 Believe+0.038
 eyebrow+0.038
 bond+0.038
Neg logit contributions
 ow-0.019
br-0.019
zed-0.017
obb-0.017
aster-0.016
Token.
Token ID13
Feature activation+1.88e-02

Pos logit contributions
 surroundings+0.099
esty+0.094
 eyebrow+0.093
assion+0.093
 Believe+0.092
Neg logit contributions
 ow-0.069
br-0.069
zed-0.068
 cuc-0.065
aster-0.063
Token It
Token ID632
Feature activation+1.12e-03

Pos logit contributions
 surroundings+0.029
 bond+0.027
 eyebrow+0.027
esty+0.026
 Believe+0.026
Neg logit contributions
 ow-0.029
br-0.028
zed-0.028
obb-0.027
bridge-0.025
Token was
Token ID373
Feature activation+1.98e-02

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.002
Token smooth
Token ID7209
Feature activation+3.96e-03

Pos logit contributions
 surroundings+0.037
 bond+0.035
esty+0.035
 Believe+0.034
 eyebrow+0.034
Neg logit contributions
 ow-0.025
br-0.024
zed-0.023
obb-0.022
bridge-0.020
Token and
Token ID290
Feature activation+1.42e-04

Pos logit contributions
 surroundings+0.006
 bond+0.005
 eyebrow+0.005
esty+0.005
 Believe+0.005
Neg logit contributions
 ow-0.007
br-0.007
zed-0.006
obb-0.006
bridge-0.006
Token.
Token ID13
Feature activation+2.07e-03

Pos logit contributions
 ow+0.015
br+0.015
zed+0.015
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.022
 bond-0.020
 eyebrow-0.020
 Believe-0.020
esty-0.020
Token
Token ID198
Feature activation+5.03e-03

Pos logit contributions
 surroundings+0.003
 bond+0.003
 eyebrow+0.003
esty+0.003
 Believe+0.003
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token
Token ID198
Feature activation-2.43e-03

Pos logit contributions
 surroundings+0.009
esty+0.009
idents+0.009
 eyebrow+0.009
 zone+0.009
Neg logit contributions
br-0.006
 ow-0.006
aster-0.006
zed-0.006
on-0.006
TokenM
Token ID44
Feature activation-7.09e-03

Pos logit contributions
br+0.004
zed+0.003
aster+0.003
P+0.003
 ow+0.003
Neg logit contributions
 surroundings-0.004
esty-0.004
idents-0.004
 eyebrow-0.004
wood-0.004
Tokenoral
Token ID6864
Feature activation+2.44e-02

Pos logit contributions
 ow+0.014
zed+0.013
br+0.013
 cuc+0.012
obb+0.012
Neg logit contributions
 surroundings-0.009
 bond-0.008
 eyebrow-0.007
 Believe-0.007
 Fighting-0.007
Token:
Token ID25
Feature activation+5.59e-02

Pos logit contributions
 surroundings+0.041
esty+0.039
idents+0.038
 eyebrow+0.038
 bond+0.038
Neg logit contributions
br-0.036
 ow-0.034
obb-0.032
zed-0.031
aster-0.029
Token Hon
Token ID8835
Feature activation+1.63e-02

Pos logit contributions
 surroundings+0.075
 bond+0.071
 eyebrow+0.070
esty+0.066
smanship+0.063
Neg logit contributions
br-0.092
 ow-0.091
zed-0.090
on-0.089
itt-0.086
Tokenesty
Token ID9673
Feature activation+3.31e-02

Pos logit contributions
smanship+0.013
 bond+0.012
 eyebrow+0.012
 surroundings+0.011
 tactic+0.011
Neg logit contributions
P-0.033
br-0.033
obb-0.033
zed-0.032
aster-0.030
Token,
Token ID11
Feature activation+1.75e-02

Pos logit contributions
 surroundings+0.060
 eyebrow+0.058
 bond+0.056
esty+0.055
assion+0.055
Neg logit contributions
br-0.043
 ow-0.039
zed-0.035
obb-0.035
itt-0.031
Token generosity
Token ID31569
Feature activation+5.23e-02

Pos logit contributions
 surroundings+0.030
 eyebrow+0.028
assion+0.027
esty+0.027
 bond+0.027
Neg logit contributions
 ow-0.024
br-0.024
zed-0.022
obb-0.022
aster-0.021
Token and
Token ID290
Feature activation+3.32e-02

Pos logit contributions
 surroundings+0.121
 eyebrow+0.121
assion+0.117
esty+0.115
idents+0.113
Neg logit contributions
br-0.041
 ow-0.031
on-0.025
 time-0.022
 wo-0.021
Token cut
Token ID2005
Feature activation+2.56e-02

Pos logit contributions
 ow+0.016
br+0.016
zed+0.015
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.020
 bond-0.019
 eyebrow-0.018
esty-0.018
 Believe-0.018
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 surroundings+0.045
 bond+0.044
 Believe+0.043
assion+0.042
esty+0.041
Neg logit contributions
br-0.034
 ow-0.033
obb-0.032
zed-0.031
bridge-0.029
Token They
Token ID1119
Feature activation-7.77e-03

Pos logit contributions
 surroundings+0.016
 bond+0.015
 eyebrow+0.015
 Believe+0.015
esty+0.015
Neg logit contributions
 ow-0.021
br-0.020
zed-0.020
obb-0.019
bridge-0.018
Token shared
Token ID4888
Feature activation+8.70e-03

Pos logit contributions
 ow+0.011
br+0.011
zed+0.010
obb+0.010
bridge+0.009
Neg logit contributions
 surroundings-0.013
 bond-0.012
 eyebrow-0.012
esty-0.012
 Believe-0.012
Token the
Token ID262
Feature activation+8.96e-03

Pos logit contributions
 surroundings+0.018
 Believe+0.017
esty+0.017
 bond+0.017
assion+0.017
Neg logit contributions
 ow-0.009
br-0.009
zed-0.008
 cor-0.007
aster-0.007
Token sausage
Token ID31889
Feature activation+5.59e-02

Pos logit contributions
 surroundings+0.017
esty+0.016
assion+0.016
 Believe+0.016
 eyebrow+0.015
Neg logit contributions
 ow-0.011
br-0.011
obb-0.010
zed-0.010
bridge-0.009
Token with
Token ID351
Feature activation+5.82e-03

Pos logit contributions
 surroundings+0.087
 Believe+0.084
assion+0.084
 Fighting+0.082
esty+0.082
Neg logit contributions
 ow-0.078
br-0.078
zed-0.077
obb-0.074
on-0.071
Token their
Token ID511
Feature activation+1.36e-02

Pos logit contributions
 surroundings+0.009
 eyebrow+0.009
assion+0.009
 bond+0.009
 Believe+0.009
Neg logit contributions
 ow-0.009
zed-0.008
br-0.008
obb-0.008
aster-0.007
Token friends
Token ID2460
Feature activation+6.46e-03

Pos logit contributions
assion+0.024
 Believe+0.023
 eyebrow+0.023
esty+0.023
 Fighting+0.022
Neg logit contributions
 ow-0.018
 mo-0.016
 arrest-0.015
zed-0.015
 cor-0.015
Token and
Token ID290
Feature activation+3.58e-03

Pos logit contributions
 surroundings+0.012
 eyebrow+0.011
esty+0.011
 bond+0.011
 Believe+0.011
Neg logit contributions
zed-0.008
br-0.008
 ow-0.008
obb-0.007
aster-0.007
Token everyone
Token ID2506
Feature activation-1.18e-02

Pos logit contributions
 surroundings+0.007
assion+0.007
 eyebrow+0.007
esty+0.007
 Believe+0.007
Neg logit contributions
 ow-0.004
zed-0.004
br-0.004
 mo-0.004
aster-0.003
Token.
Token ID13
Feature activation+2.55e-02

Pos logit contributions
 surroundings+0.004
 bond+0.004
esty+0.003
 Believe+0.003
 eyebrow+0.003
Neg logit contributions
zed-0.004
br-0.004
 ow-0.004
obb-0.004
bridge-0.003
Token We
Token ID775
Feature activation+2.17e-02

Pos logit contributions
 surroundings+0.044
 bond+0.041
 eyebrow+0.040
assion+0.038
 rhythms+0.037
Neg logit contributions
br-0.036
 ow-0.036
zed-0.032
obb-0.032
bridge-0.030
Token can
Token ID460
Feature activation+5.94e-03

Pos logit contributions
 surroundings+0.036
 eyebrow+0.033
 bond+0.032
assion+0.032
esty+0.031
Neg logit contributions
 ow-0.032
br-0.032
obb-0.030
zed-0.030
bridge-0.027
Token look
Token ID804
Feature activation+6.94e-03

Pos logit contributions
 surroundings+0.009
 bond+0.008
 Believe+0.008
esty+0.008
 eyebrow+0.008
Neg logit contributions
br-0.009
 ow-0.009
zed-0.009
obb-0.009
bridge-0.008
Token,
Token ID11
Feature activation+2.39e-02

Pos logit contributions
 surroundings+0.012
 bond+0.012
 Believe+0.012
 eyebrow+0.012
esty+0.011
Neg logit contributions
 ow-0.009
br-0.009
obb-0.008
zed-0.008
 mo-0.007
Token but
Token ID475
Feature activation+5.58e-02

Pos logit contributions
 surroundings+0.043
 bond+0.041
assion+0.039
esty+0.039
 eyebrow+0.038
Neg logit contributions
 ow-0.035
br-0.030
 mo-0.029
bridge-0.028
zed-0.028
Token we
Token ID356
Feature activation+1.85e-02

Pos logit contributions
 surroundings+0.121
 eyebrow+0.117
 bond+0.114
esty+0.112
owner+0.111
Neg logit contributions
 ow-0.056
br-0.049
zed-0.042
 mo-0.042
obb-0.041
Token should
Token ID815
Feature activation+2.83e-04

Pos logit contributions
 surroundings+0.030
 bond+0.028
 eyebrow+0.028
esty+0.027
assion+0.027
Neg logit contributions
 ow-0.027
br-0.027
zed-0.025
obb-0.025
aster-0.023
Token not
Token ID407
Feature activation+1.62e-02

Pos logit contributions
 surroundings+0.000
 bond+0.000
esty+0.000
 eyebrow+0.000
 Believe+0.000
Neg logit contributions
br-0.000
 ow-0.000
zed-0.000
obb-0.000
bridge-0.000
Token touch
Token ID3638
Feature activation+8.02e-03

Pos logit contributions
 surroundings+0.024
 bond+0.022
 Believe+0.022
assion+0.022
 eyebrow+0.022
Neg logit contributions
zed-0.026
br-0.026
 ow-0.025
obb-0.025
bridge-0.023
Token it
Token ID340
Feature activation-2.69e-03

Pos logit contributions
 surroundings+0.014
 bond+0.013
esty+0.012
 eyebrow+0.012
 Believe+0.012
Neg logit contributions
br-0.011
zed-0.011
 ow-0.011
obb-0.010
bridge-0.010
Token with
Token ID351
Feature activation-6.08e-03

Pos logit contributions
 surroundings+0.024
 bond+0.023
assion+0.023
esty+0.023
 Believe+0.023
Neg logit contributions
zed-0.017
br-0.016
 ow-0.016
aster-0.015
on-0.015
Token him
Token ID683
Feature activation+1.52e-02

Pos logit contributions
 ow+0.008
br+0.008
zed+0.008
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.011
 bond-0.010
 eyebrow-0.010
esty-0.010
 Believe-0.010
Token.
Token ID13
Feature activation+2.34e-02

Pos logit contributions
 surroundings+0.035
 eyebrow+0.034
 rhythms+0.034
 Believe+0.034
 bond+0.034
Neg logit contributions
 ow-0.011
zed-0.010
br-0.009
oll-0.008
on-0.008
Token
Token ID198
Feature activation+1.70e-02

Pos logit contributions
 surroundings+0.038
 bond+0.036
 eyebrow+0.035
esty+0.035
assion+0.034
Neg logit contributions
 ow-0.034
br-0.034
zed-0.033
obb-0.031
aster-0.028
Token
Token ID198
Feature activation+1.64e-02

Pos logit contributions
 surroundings+0.027
 bond+0.025
esty+0.024
 eyebrow+0.024
assion+0.024
Neg logit contributions
 ow-0.026
br-0.026
zed-0.025
obb-0.024
bridge-0.022
TokenBut
Token ID1537
Feature activation+5.57e-02

Pos logit contributions
 surroundings+0.024
 bond+0.022
 eyebrow+0.021
esty+0.021
assion+0.021
Neg logit contributions
br-0.027
 ow-0.027
zed-0.027
obb-0.026
bridge-0.024
Token when
Token ID618
Feature activation+2.75e-02

Pos logit contributions
 surroundings+0.092
 eyebrow+0.088
assion+0.087
 bond+0.086
 rhythms+0.085
Neg logit contributions
 ow-0.084
zed-0.084
br-0.078
 reached-0.072
aster-0.071
Token Fl
Token ID1610
Feature activation+2.67e-02

Pos logit contributions
 surroundings+0.047
 bond+0.044
 eyebrow+0.042
esty+0.042
 Believe+0.042
Neg logit contributions
 ow-0.038
br-0.038
zed-0.036
obb-0.036
bridge-0.033
Tokenuffy
Token ID15352
Feature activation-8.83e-03

Pos logit contributions
 surroundings+0.040
 bond+0.038
 eyebrow+0.037
esty+0.036
 Believe+0.036
Neg logit contributions
 ow-0.042
br-0.042
zed-0.041
obb-0.040
bridge-0.036
Token got
Token ID1392
Feature activation-1.16e-02

Pos logit contributions
br+0.013
 ow+0.013
zed+0.012
obb+0.012
bridge+0.011
Neg logit contributions
 surroundings-0.014
 bond-0.013
esty-0.013
 eyebrow-0.013
 Believe-0.013
Token home
Token ID1363
Feature activation+2.28e-02

Pos logit contributions
 ow+0.017
obb+0.016
zed+0.016
br+0.016
 mo+0.016
Neg logit contributions
 bond-0.018
 surroundings-0.018
 rhythms-0.017
assion-0.017
 eyebrow-0.017
Token was
Token ID373
Feature activation+3.86e-03

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
esty+0.002
 Believe+0.002
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token a
Token ID257
Feature activation-1.45e-02

Pos logit contributions
 surroundings+0.005
 Believe+0.005
 eyebrow+0.005
 bond+0.005
 Fighting+0.005
Neg logit contributions
br-0.007
 ow-0.006
zed-0.006
obb-0.006
bridge-0.006
Token little
Token ID1310
Feature activation+5.10e-03

Pos logit contributions
zed+0.024
br+0.023
bridge+0.022
 ow+0.021
obb+0.021
Neg logit contributions
 surroundings-0.021
 bond-0.020
esty-0.020
 Believe-0.018
 rhythms-0.017
Token girl
Token ID2576
Feature activation+2.74e-03

Pos logit contributions
 surroundings+0.006
 bond+0.005
 eyebrow+0.005
esty+0.005
assion+0.005
Neg logit contributions
 ow-0.010
br-0.010
obb-0.009
zed-0.009
bridge-0.009
Token with
Token ID351
Feature activation-2.07e-02

Pos logit contributions
 surroundings+0.005
 bond+0.005
 eyebrow+0.005
esty+0.005
 Believe+0.005
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
aster-0.003
Token blonde
Token ID21541
Feature activation-6.85e-02

Pos logit contributions
br+0.035
obb+0.033
zed+0.033
bridge+0.032
atmeal+0.030
Neg logit contributions
 bond-0.026
 surroundings-0.025
 Believe-0.024
 rhythms-0.024
 Fighting-0.024
Token hair
Token ID4190
Feature activation-2.14e-02

Pos logit contributions
zed+0.142
br+0.142
obb+0.137
bridge+0.135
 ow+0.132
Neg logit contributions
 surroundings-0.066
 bond-0.053
esty-0.050
 eyebrow-0.047
 opinions-0.043
Token.
Token ID13
Feature activation+3.64e-03

Pos logit contributions
br+0.033
obb+0.033
zed+0.032
 ow+0.032
aster+0.029
Neg logit contributions
 surroundings-0.032
 bond-0.030
assion-0.027
 eyebrow-0.027
esty-0.027
Token She
Token ID1375
Feature activation+2.23e-03

Pos logit contributions
 surroundings+0.006
 bond+0.005
 eyebrow+0.005
esty+0.005
 Believe+0.005
Neg logit contributions
 ow-0.006
br-0.005
zed-0.005
obb-0.005
bridge-0.005
Token had
Token ID550
Feature activation-6.36e-03

Pos logit contributions
 surroundings+0.003
 bond+0.002
 eyebrow+0.002
 Believe+0.002
esty+0.002
Neg logit contributions
br-0.004
 ow-0.004
obb-0.004
zed-0.004
bridge-0.004
Token a
Token ID257
Feature activation-1.21e-04

Pos logit contributions
br+0.009
obb+0.009
 ow+0.009
zed+0.009
aster+0.008
Neg logit contributions
 surroundings-0.010
 bond-0.010
 eyebrow-0.009
esty-0.009
assion-0.009
Token glowing
Token ID21377
Feature activation-1.08e-02

Pos logit contributions
 surroundings+0.019
 bond+0.018
 eyebrow+0.018
esty+0.017
 Believe+0.017
Neg logit contributions
 ow-0.018
br-0.018
zed-0.017
obb-0.017
bridge-0.015
Token wand
Token ID11569
Feature activation-7.19e-03

Pos logit contributions
 ow+0.015
br+0.015
zed+0.015
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.018
 bond-0.017
 eyebrow-0.016
esty-0.016
 Believe-0.016
Token and
Token ID290
Feature activation+2.02e-03

Pos logit contributions
br+0.010
 ow+0.010
zed+0.010
obb+0.009
bridge+0.009
Neg logit contributions
 surroundings-0.012
 bond-0.011
esty-0.011
 eyebrow-0.011
 Believe-0.011
Token having
Token ID1719
Feature activation-9.82e-03

Pos logit contributions
esty+0.004
 surroundings+0.004
 eyebrow+0.004
 bond+0.004
idents+0.004
Neg logit contributions
 ow-0.002
zed-0.002
 mo-0.002
br-0.002
 reached-0.002
Token the
Token ID262
Feature activation+9.70e-03

Pos logit contributions
 ow+0.015
br+0.015
zed+0.015
obb+0.015
aster+0.013
Neg logit contributions
 surroundings-0.015
 bond-0.014
 Believe-0.013
 eyebrow-0.013
esty-0.013
Token sill
Token ID49276
Feature activation-6.64e-02

Pos logit contributions
 surroundings+0.015
 eyebrow+0.014
esty+0.014
assion+0.014
 bond+0.013
Neg logit contributions
 ow-0.015
br-0.015
obb-0.014
zed-0.014
bridge-0.013
Tokeniest
Token ID6386
Feature activation-1.87e-02

Pos logit contributions
obb+0.095
 arrest+0.094
 ow+0.093
 cuc+0.091
br+0.089
Neg logit contributions
 bond-0.096
 surroundings-0.095
 zone-0.091
 eyebrow-0.086
 opinions-0.085
Token time
Token ID640
Feature activation-1.97e-02

Pos logit contributions
 ow+0.027
br+0.026
zed+0.025
obb+0.025
bridge+0.023
Neg logit contributions
 surroundings-0.031
esty-0.029
 eyebrow-0.029
assion-0.029
 bond-0.029
Token of
Token ID286
Feature activation-1.14e-02

Pos logit contributions
obb+0.031
 ow+0.030
zed+0.028
br+0.027
aster+0.027
Neg logit contributions
 surroundings-0.030
 bond-0.027
 Believe-0.026
 rhythms-0.026
assion-0.025
Token his
Token ID465
Feature activation-1.46e-03

Pos logit contributions
br+0.018
obb+0.018
zed+0.017
 ow+0.016
bridge+0.016
Neg logit contributions
 surroundings-0.017
 bond-0.017
 rhythms-0.016
 Believe-0.015
 harmony-0.015
Token life
Token ID1204
Feature activation-2.01e-02

Pos logit contributions
br+0.002
 ow+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.002
 bond-0.002
 eyebrow-0.002
esty-0.002
 Believe-0.002
Token only
Token ID691
Feature activation+2.32e-02

Pos logit contributions
 surroundings+0.033
 bond+0.030
 Believe+0.030
esty+0.029
 eyebrow+0.028
Neg logit contributions
br-0.043
zed-0.041
 ow-0.041
obb-0.040
bridge-0.038
Token three
Token ID1115
Feature activation-1.68e-02

Pos logit contributions
 surroundings+0.042
 bond+0.040
 eyebrow+0.040
assion+0.039
esty+0.038
Neg logit contributions
 ow-0.029
br-0.029
obb-0.026
zed-0.026
oll-0.023
Token,
Token ID11
Feature activation+1.66e-02

Pos logit contributions
br+0.032
zed+0.031
 ow+0.031
obb+0.031
bridge+0.029
Neg logit contributions
 surroundings-0.021
 bond-0.018
 eyebrow-0.017
esty-0.017
 rhythms-0.016
Token with
Token ID351
Feature activation-1.01e-02

Pos logit contributions
 surroundings+0.022
 bond+0.020
 eyebrow+0.020
esty+0.020
assion+0.019
Neg logit contributions
 ow-0.030
br-0.029
zed-0.029
obb-0.028
bridge-0.026
Token curly
Token ID45731
Feature activation-5.06e-02

Pos logit contributions
br+0.015
zed+0.014
obb+0.014
bridge+0.013
 ow+0.013
Neg logit contributions
 surroundings-0.015
 bond-0.015
 Believe-0.015
 rhythms-0.014
 eyebrow-0.014
Token blonde
Token ID21541
Feature activation-6.55e-02

Pos logit contributions
zed+0.089
br+0.086
obb+0.086
 ow+0.085
aster+0.080
Neg logit contributions
 surroundings-0.067
 bond-0.057
esty-0.057
 eyebrow-0.056
 rhythms-0.054
Token hair
Token ID4190
Feature activation-2.57e-02

Pos logit contributions
zed+0.138
obb+0.132
br+0.131
 ow+0.128
bridge+0.127
Neg logit contributions
 surroundings-0.066
esty-0.051
 bond-0.048
 eyebrow-0.044
 opinions-0.043
Token and
Token ID290
Feature activation-2.51e-02

Pos logit contributions
zed+0.046
obb+0.046
 ow+0.045
br+0.045
bridge+0.043
Neg logit contributions
 surroundings-0.031
 bond-0.027
assion-0.026
esty-0.026
 eyebrow-0.026
Token she
Token ID673
Feature activation+4.38e-04

Pos logit contributions
 ow+0.032
br+0.031
zed+0.030
obb+0.029
bridge+0.026
Neg logit contributions
 surroundings-0.046
 bond-0.043
 eyebrow-0.043
esty-0.042
 Believe-0.042
Token loved
Token ID6151
Feature activation+1.15e-03

Pos logit contributions
 surroundings+0.001
 bond+0.000
esty+0.000
 eyebrow+0.000
 Believe+0.000
Neg logit contributions
br-0.001
 ow-0.001
zed-0.001
obb-0.001
bridge-0.001
Token to
Token ID284
Feature activation-1.05e-02

Pos logit contributions
 surroundings+0.002
 bond+0.002
assion+0.001
 Believe+0.001
 rhythms+0.001
Neg logit contributions
br-0.002
 ow-0.002
obb-0.002
zed-0.002
bridge-0.002
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
 ow+0.009
br+0.009
zed+0.009
obb+0.008
bridge+0.008
Neg logit contributions
 surroundings-0.009
 bond-0.009
 eyebrow-0.008
esty-0.008
assion-0.008
Token ran
Token ID4966
Feature activation-1.21e-02

Pos logit contributions
 ow+0.018
br+0.017
obb+0.017
zed+0.017
bridge+0.016
Neg logit contributions
 surroundings-0.018
 bond-0.017
esty-0.016
 Believe-0.016
 eyebrow-0.016
Token home
Token ID1363
Feature activation+7.83e-04

Pos logit contributions
 ow+0.023
br+0.022
obb+0.021
zed+0.021
bridge+0.020
Neg logit contributions
 surroundings-0.015
 bond-0.014
 eyebrow-0.014
esty-0.014
 Believe-0.013
Token with
Token ID351
Feature activation-2.36e-02

Pos logit contributions
 surroundings+0.001
 bond+0.001
esty+0.001
 eyebrow+0.001
 Believe+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token the
Token ID262
Feature activation-3.57e-03

Pos logit contributions
br+0.032
 ow+0.032
zed+0.031
obb+0.030
bridge+0.028
Neg logit contributions
 surroundings-0.041
 bond-0.039
 eyebrow-0.037
esty-0.037
 Believe-0.037
Token sill
Token ID49276
Feature activation-6.51e-02

Pos logit contributions
 ow+0.004
br+0.004
obb+0.004
zed+0.003
 mo+0.003
Neg logit contributions
 surroundings-0.007
esty-0.007
assion-0.007
 eyebrow-0.007
 Believe-0.006
Tokeniest
Token ID6386
Feature activation-1.56e-02

Pos logit contributions
 ow+0.100
obb+0.100
 arrest+0.097
br+0.094
P+0.093
Neg logit contributions
 bond-0.088
 surroundings-0.087
 eyebrow-0.082
 zone-0.082
liness-0.075
Token of
Token ID286
Feature activation-1.23e-02

Pos logit contributions
 ow+0.019
br+0.019
zed+0.017
obb+0.016
 mo+0.016
Neg logit contributions
 surroundings-0.029
esty-0.028
assion-0.028
 Believe-0.027
 eyebrow-0.027
Token smiles
Token ID21845
Feature activation-2.02e-02

Pos logit contributions
obb+0.019
br+0.019
zed+0.019
 ow+0.018
bridge+0.017
Neg logit contributions
 surroundings-0.018
 bond-0.018
 Believe-0.017
 rhythms-0.016
 Fighting-0.015
Token.
Token ID13
Feature activation+5.57e-03

Pos logit contributions
 ow+0.031
obb+0.030
zed+0.029
br+0.029
aster+0.027
Neg logit contributions
 surroundings-0.030
 bond-0.029
 zone-0.027
esty-0.027
assion-0.027
Token<|endoftext|>
Token ID50256
Feature activation-1.03e-02

Pos logit contributions
 surroundings+0.008
 bond+0.008
 eyebrow+0.008
esty+0.008
 Believe+0.007
Neg logit contributions
 ow-0.009
br-0.009
zed-0.008
obb-0.008
bridge-0.008
Token,
Token ID11
Feature activation-6.74e-03

Pos logit contributions
 surroundings+0.007
 bond+0.007
esty+0.007
assion+0.007
 eyebrow+0.007
Neg logit contributions
 ow-0.005
zed-0.005
br-0.005
obb-0.004
aster-0.004
Token a
Token ID257
Feature activation-9.12e-03

Pos logit contributions
br+0.008
 ow+0.008
zed+0.008
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.013
 bond-0.012
 Believe-0.012
 eyebrow-0.011
esty-0.011
Token small
Token ID1402
Feature activation+5.96e-03

Pos logit contributions
 ow+0.009
br+0.009
zed+0.008
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.019
 bond-0.018
 eyebrow-0.018
esty-0.018
 Believe-0.018
Token girl
Token ID2576
Feature activation-1.16e-02

Pos logit contributions
 surroundings+0.010
 bond+0.009
 eyebrow+0.009
esty+0.009
assion+0.009
Neg logit contributions
 ow-0.009
br-0.008
zed-0.008
obb-0.008
aster-0.007
Token with
Token ID351
Feature activation-3.01e-02

Pos logit contributions
obb+0.014
 ow+0.013
br+0.013
zed+0.013
bridge+0.011
Neg logit contributions
 surroundings-0.022
 bond-0.021
 eyebrow-0.020
 Believe-0.020
 Fighting-0.019
Token blonde
Token ID21541
Feature activation-6.37e-02

Pos logit contributions
br+0.042
zed+0.042
obb+0.041
 ow+0.039
bridge+0.037
Neg logit contributions
 surroundings-0.048
 bond-0.047
 eyebrow-0.045
 Believe-0.044
 rhythms-0.043
Token hair
Token ID4190
Feature activation-3.93e-02

Pos logit contributions
obb+0.131
zed+0.129
br+0.127
endo+0.125
bridge+0.125
Neg logit contributions
 surroundings-0.060
esty-0.045
 bond-0.042
 eyebrow-0.042
 opinions-0.037
Token came
Token ID1625
Feature activation+1.03e-02

Pos logit contributions
obb+0.070
br+0.067
endo+0.067
zed+0.066
aster+0.066
Neg logit contributions
 surroundings-0.045
 bond-0.040
 eyebrow-0.037
 rhythms-0.036
liness-0.035
Token over
Token ID625
Feature activation-1.87e-02

Pos logit contributions
 surroundings+0.014
 bond+0.013
esty+0.013
 eyebrow+0.012
 Believe+0.012
Neg logit contributions
 ow-0.018
br-0.018
zed-0.017
obb-0.016
bridge-0.015
Token to
Token ID284
Feature activation-2.54e-03

Pos logit contributions
br+0.029
 ow+0.028
zed+0.028
obb+0.027
bridge+0.025
Neg logit contributions
 surroundings-0.030
 bond-0.028
 eyebrow-0.027
 Believe-0.026
esty-0.026
Token her
Token ID607
Feature activation+9.87e-03

Pos logit contributions
br+0.004
obb+0.004
zed+0.004
 ow+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.004
 bond-0.003
 Believe-0.003
 eyebrow-0.003
assion-0.003
Token near
Token ID1474
Feature activation+8.00e-03

Pos logit contributions
 surroundings+0.009
 bond+0.008
 Believe+0.008
 eyebrow+0.008
assion+0.008
Neg logit contributions
br-0.009
 ow-0.009
zed-0.009
obb-0.009
bridge-0.008
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
 surroundings+0.015
 bond+0.014
esty+0.014
 eyebrow+0.014
 Believe+0.014
Neg logit contributions
 ow-0.010
br-0.009
zed-0.009
obb-0.009
aster-0.008
Token clouds
Token ID15114
Feature activation-2.03e-02

Pos logit contributions
 eyebrow+0.029
 Believe+0.029
esty+0.029
 surroundings+0.029
 bond+0.028
Neg logit contributions
 ow-0.021
br-0.018
obb-0.017
 mo-0.017
 o-0.016
Token.
Token ID13
Feature activation-8.30e-03

Pos logit contributions
 ow+0.036
zed+0.035
obb+0.035
br+0.035
oll+0.032
Neg logit contributions
 surroundings-0.026
 bond-0.024
 rhythms-0.022
 Believe-0.022
assion-0.022
Token Everywhere
Token ID48201
Feature activation-2.83e-02

Pos logit contributions
 ow+0.013
br+0.012
zed+0.012
obb+0.012
bridge+0.011
Neg logit contributions
 surroundings-0.013
 bond-0.012
 Believe-0.012
 eyebrow-0.012
esty-0.012
Token it
Token ID340
Feature activation-6.30e-02

Pos logit contributions
zed+0.042
obb+0.042
br+0.042
 ow+0.041
bridge+0.039
Neg logit contributions
 surroundings-0.043
 bond-0.041
 Believe-0.038
esty-0.038
assion-0.037
Token flew
Token ID13112
Feature activation-3.50e-03

Pos logit contributions
 ow+0.099
zed+0.099
obb+0.098
br+0.098
 arrest+0.094
Neg logit contributions
 surroundings-0.088
 bond-0.079
 rhythms-0.074
 Believe-0.074
esty-0.072
Token,
Token ID11
Feature activation-9.28e-03

Pos logit contributions
br+0.005
 ow+0.005
zed+0.004
obb+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.006
 bond-0.006
 eyebrow-0.006
esty-0.006
assion-0.006
Token it
Token ID340
Feature activation-3.29e-02

Pos logit contributions
br+0.014
zed+0.014
 ow+0.014
obb+0.013
oll+0.012
Neg logit contributions
 surroundings-0.014
 bond-0.013
 Believe-0.013
 rhythms-0.013
 eyebrow-0.012
Token left
Token ID1364
Feature activation-7.87e-04

Pos logit contributions
 ow+0.051
br+0.049
zed+0.049
obb+0.049
aster+0.046
Neg logit contributions
 surroundings-0.049
 bond-0.045
 Believe-0.044
assion-0.044
esty-0.043
Token a
Token ID257
Feature activation-3.04e-03

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
obb+0.001
bridge+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
esty-0.001
 Believe-0.001
Token wind
Token ID2344
Feature activation-1.14e-02

Pos logit contributions
 ow+0.006
br+0.006
zed+0.006
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.008
 bond-0.008
 eyebrow-0.007
esty-0.007
 Believe-0.007
Token and
Token ID290
Feature activation-2.11e-03

Pos logit contributions
 ow+0.018
br+0.018
zed+0.018
obb+0.018
bridge+0.016
Neg logit contributions
 surroundings-0.016
 bond-0.015
assion-0.015
 eyebrow-0.015
esty-0.015
Token take
Token ID1011
Feature activation-7.93e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
 mo+0.002
Neg logit contributions
 surroundings-0.004
 eyebrow-0.004
esty-0.004
 bond-0.004
 Believe-0.004
Token it
Token ID340
Feature activation-6.16e-03

Pos logit contributions
 ow+0.012
obb+0.012
zed+0.011
br+0.011
bridge+0.011
Neg logit contributions
 surroundings-0.012
 bond-0.011
 Believe-0.011
esty-0.011
 rhythms-0.011
Token wherever
Token ID14530
Feature activation-3.89e-02

Pos logit contributions
 ow+0.013
zed+0.012
obb+0.012
br+0.012
aster+0.011
Neg logit contributions
 surroundings-0.007
 bond-0.006
assion-0.006
esty-0.006
 eyebrow-0.006
Token it
Token ID340
Feature activation-6.27e-02

Pos logit contributions
oll+0.070
obb+0.070
br+0.067
 ow+0.065
itt+0.063
Neg logit contributions
 surroundings-0.046
 ourselves-0.043
 bond-0.040
assion-0.039
 themselves-0.039
Token wanted
Token ID2227
Feature activation-2.04e-02

Pos logit contributions
itt+0.112
zed+0.108
obb+0.104
oll+0.104
br+0.103
Neg logit contributions
 zone-0.068
 surroundings-0.068
wood-0.063
 Believe-0.062
 means-0.061
Token to
Token ID284
Feature activation-9.83e-03

Pos logit contributions
 ow+0.032
obb+0.031
br+0.031
zed+0.030
bridge+0.029
Neg logit contributions
 surroundings-0.031
 Believe-0.028
 bond-0.028
 eyebrow-0.027
 zone-0.027
Token go
Token ID467
Feature activation-1.03e-02

Pos logit contributions
itt+0.016
 ow+0.016
br+0.016
obb+0.016
eh+0.015
Neg logit contributions
 surroundings-0.013
 bond-0.013
 ourselves-0.013
 communicate-0.013
 Believe-0.012
Token.
Token ID13
Feature activation-2.80e-03

Pos logit contributions
 ow+0.015
zed+0.015
br+0.015
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.017
 bond-0.015
esty-0.015
assion-0.015
 Believe-0.015
Token One
Token ID1881
Feature activation+9.89e-03

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
obb+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.004
esty-0.004
 Believe-0.004
Token loved
Token ID6151
Feature activation+3.03e-03

Pos logit contributions
obb+0.002
br+0.002
 ow+0.002
zed+0.002
aster+0.002
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
 Believe-0.001
assion-0.001
Token to
Token ID284
Feature activation-7.73e-03

Pos logit contributions
 surroundings+0.004
 bond+0.003
assion+0.003
 rhythms+0.003
 Believe+0.003
Neg logit contributions
br-0.006
obb-0.006
zed-0.006
 ow-0.005
bridge-0.005
Token sing
Token ID1702
Feature activation+4.18e-03

Pos logit contributions
obb+0.013
br+0.013
oll+0.013
itt+0.013
zed+0.012
Neg logit contributions
 bond-0.010
 communicate-0.009
 cope-0.009
 rhythms-0.009
 surroundings-0.009
Token.
Token ID13
Feature activation-8.20e-03

Pos logit contributions
 surroundings+0.007
 bond+0.007
 eyebrow+0.007
esty+0.007
 Believe+0.007
Neg logit contributions
br-0.006
 ow-0.006
zed-0.005
obb-0.005
bridge-0.005
Token Everywhere
Token ID48201
Feature activation-2.73e-02

Pos logit contributions
 ow+0.012
br+0.012
zed+0.011
obb+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.013
 bond-0.013
 eyebrow-0.012
esty-0.012
 Believe-0.012
Token it
Token ID340
Feature activation-6.24e-02

Pos logit contributions
zed+0.039
obb+0.038
br+0.038
 ow+0.037
bridge+0.035
Neg logit contributions
 surroundings-0.044
 bond-0.042
 Believe-0.039
assion-0.038
esty-0.038
Token went
Token ID1816
Feature activation-1.50e-03

Pos logit contributions
obb+0.098
zed+0.097
 ow+0.097
br+0.096
 arrest+0.094
Neg logit contributions
 surroundings-0.084
 bond-0.077
 rhythms-0.073
 Believe-0.071
esty-0.071
Token,
Token ID11
Feature activation-5.58e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.002
 eyebrow-0.002
esty-0.002
 Believe-0.002
Token it
Token ID340
Feature activation-2.62e-02

Pos logit contributions
br+0.008
zed+0.008
 ow+0.008
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.009
 bond-0.009
 Believe-0.008
 eyebrow-0.008
esty-0.008
Token would
Token ID561
Feature activation-3.93e-03

Pos logit contributions
 ow+0.043
br+0.042
obb+0.042
zed+0.042
bridge+0.039
Neg logit contributions
 surroundings-0.036
 bond-0.034
esty-0.032
 Believe-0.032
assion-0.032
Token sing
Token ID1702
Feature activation+6.08e-03

Pos logit contributions
br+0.006
 ow+0.006
zed+0.006
obb+0.006
itt+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.006
 Believe-0.006
 eyebrow-0.006
assion-0.006
Token her
Token ID607
Feature activation-2.46e-03

Pos logit contributions
 surroundings+0.022
 bond+0.021
 eyebrow+0.021
esty+0.021
assion+0.020
Neg logit contributions
 ow-0.013
zed-0.012
br-0.011
obb-0.010
aster-0.010
Token mom
Token ID1995
Feature activation+1.02e-02

Pos logit contributions
 ow+0.004
br+0.004
zed+0.003
obb+0.003
 mo+0.003
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.004
esty-0.004
assion-0.004
Token if
Token ID611
Feature activation-1.75e-03

Pos logit contributions
 surroundings+0.016
 bond+0.016
 eyebrow+0.015
 rhythms+0.015
esty+0.014
Neg logit contributions
br-0.015
 ow-0.015
 pr-0.014
on-0.013
 cuc-0.013
Token she
Token ID673
Feature activation-4.30e-02

Pos logit contributions
br+0.002
 ow+0.002
obb+0.002
zed+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.003
esty-0.003
 Believe-0.003
assion-0.003
Token could
Token ID714
Feature activation-2.11e-02

Pos logit contributions
obb+0.079
br+0.079
 ow+0.079
zed+0.078
bridge+0.074
Neg logit contributions
 surroundings-0.049
esty-0.046
 Believe-0.046
 bond-0.045
assion-0.044
Token have
Token ID423
Feature activation-6.18e-02

Pos logit contributions
 ow+0.034
zed+0.033
br+0.032
obb+0.032
bridge+0.030
Neg logit contributions
 surroundings-0.031
 Believe-0.028
 bond-0.028
assion-0.027
idents-0.026
Token a
Token ID257
Feature activation-4.15e-02

Pos logit contributions
obb+0.131
zed+0.124
ihu+0.123
oll+0.121
yt+0.114
Neg logit contributions
 opinions-0.045
 ourselves-0.043
 appreciate-0.042
 surroundings-0.042
 themselves-0.041
Token slice
Token ID16416
Feature activation+4.57e-03

Pos logit contributions
zed+0.065
 ow+0.058
obb+0.057
bridge+0.057
oll+0.055
Neg logit contributions
 bond-0.064
 surroundings-0.061
 promise-0.060
idents-0.058
 eyebrow-0.057
Token of
Token ID286
Feature activation-2.51e-02

Pos logit contributions
 surroundings+0.008
 bond+0.008
esty+0.007
 eyebrow+0.007
assion+0.007
Neg logit contributions
 ow-0.006
br-0.006
zed-0.006
obb-0.006
bridge-0.005
Token pie
Token ID2508
Feature activation+2.94e-04

Pos logit contributions
br+0.029
zed+0.028
obb+0.026
 ow+0.026
bridge+0.024
Neg logit contributions
 bond-0.047
 surroundings-0.047
 eyebrow-0.045
idents-0.044
 Fighting-0.043
Token.
Token ID13
Feature activation+1.20e-03

Pos logit contributions
 surroundings+0.000
 bond+0.000
esty+0.000
 eyebrow+0.000
assion+0.000
Neg logit contributions
 ow-0.000
zed-0.000
br-0.000
obb-0.000
bridge-0.000
Token its
Token ID663
Feature activation+8.87e-03

Pos logit contributions
 surroundings+0.018
 bond+0.017
 eyebrow+0.017
esty+0.017
assion+0.016
Neg logit contributions
 ow-0.013
br-0.013
zed-0.013
obb-0.012
aster-0.011
Token wings
Token ID12098
Feature activation-4.89e-03

Pos logit contributions
 Fighting+0.014
 eyebrow+0.014
 Sharing+0.014
 Believe+0.014
esty+0.014
Neg logit contributions
 ow-0.012
br-0.011
zed-0.011
 pr-0.010
 mo-0.010
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
br+0.007
 ow+0.007
zed+0.007
obb+0.006
bridge+0.006
Neg logit contributions
 surroundings-0.008
esty-0.007
 eyebrow-0.007
assion-0.007
 Believe-0.007
Token flew
Token ID13112
Feature activation-9.99e-03

Pos logit contributions
zed+0.021
 ow+0.021
br+0.020
obb+0.018
 mo+0.017
Neg logit contributions
 surroundings-0.030
 eyebrow-0.028
esty-0.028
assion-0.027
 bond-0.027
Token wherever
Token ID14530
Feature activation-4.40e-02

Pos logit contributions
br+0.017
 ow+0.016
zed+0.016
obb+0.016
bridge+0.014
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.013
assion-0.013
esty-0.013
Token it
Token ID340
Feature activation-6.18e-02

Pos logit contributions
obb+0.069
oll+0.067
br+0.066
 ow+0.065
bridge+0.060
Neg logit contributions
 surroundings-0.064
 bond-0.058
 ourselves-0.055
assion-0.055
 rhythms-0.054
Token wanted
Token ID2227
Feature activation-2.81e-02

Pos logit contributions
obb+0.093
zed+0.093
br+0.092
itt+0.092
 ow+0.090
Neg logit contributions
 surroundings-0.087
 bond-0.079
 zone-0.076
 Believe-0.076
esty-0.073
Token to
Token ID284
Feature activation-1.26e-02

Pos logit contributions
 ow+0.043
obb+0.042
br+0.042
zed+0.041
bridge+0.039
Neg logit contributions
 surroundings-0.043
 bond-0.040
 Believe-0.039
 eyebrow-0.038
esty-0.037
Token go
Token ID467
Feature activation-1.26e-02

Pos logit contributions
obb+0.017
br+0.017
 ow+0.017
zed+0.017
itt+0.016
Neg logit contributions
 surroundings-0.021
 bond-0.021
 communicate-0.019
 Believe-0.019
 rhythms-0.019
Token,
Token ID11
Feature activation-5.95e-03

Pos logit contributions
 ow+0.018
br+0.017
zed+0.017
obb+0.017
bridge+0.015
Neg logit contributions
 surroundings-0.022
 bond-0.020
esty-0.019
assion-0.019
 eyebrow-0.019
Token but
Token ID475
Feature activation+2.21e-02

Pos logit contributions
 ow+0.010
br+0.010
zed+0.010
obb+0.009
bridge+0.009
Neg logit contributions
 surroundings-0.008
 bond-0.008
 eyebrow-0.008
esty-0.008
assion-0.007
Token years
Token ID812
Feature activation-1.23e-02

Pos logit contributions
br+0.037
zed+0.035
obb+0.035
 ow+0.035
bridge+0.034
Neg logit contributions
 surroundings-0.022
 bond-0.019
 eyebrow-0.018
esty-0.018
 rhythms-0.017
Token old
Token ID1468
Feature activation+1.36e-02

Pos logit contributions
zed+0.031
br+0.030
bridge+0.029
 ow+0.029
obb+0.028
Neg logit contributions
 surroundings-0.008
 eyebrow-0.006
 bond-0.005
owner-0.005
assion-0.004
Token and
Token ID290
Feature activation-4.71e-03

Pos logit contributions
assion+0.028
 Believe+0.028
 eyebrow+0.028
 surroundings+0.027
 bond+0.026
Neg logit contributions
 ow-0.016
br-0.012
 pr-0.011
 peach-0.010
 o-0.010
Token had
Token ID550
Feature activation-5.40e-03

Pos logit contributions
 ow+0.008
zed+0.008
br+0.008
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.007
 bond-0.006
 eyebrow-0.006
esty-0.006
assion-0.006
Token long
Token ID890
Feature activation-3.06e-02

Pos logit contributions
br+0.008
obb+0.008
zed+0.008
 ow+0.008
aster+0.007
Neg logit contributions
 surroundings-0.008
 bond-0.008
assion-0.007
esty-0.007
 rhythms-0.007
Token blonde
Token ID21541
Feature activation-6.17e-02

Pos logit contributions
 ow+0.045
br+0.042
zed+0.041
obb+0.040
bridge+0.036
Neg logit contributions
 surroundings-0.050
 Believe-0.049
esty-0.048
 bond-0.048
 eyebrow-0.047
Token hair
Token ID4190
Feature activation-1.38e-02

Pos logit contributions
zed+0.124
br+0.121
obb+0.116
 ow+0.116
bridge+0.114
Neg logit contributions
 surroundings-0.071
esty-0.059
 bond-0.056
 eyebrow-0.052
 opinions-0.050
Token.
Token ID13
Feature activation-2.25e-02

Pos logit contributions
 ow+0.018
br+0.017
zed+0.017
obb+0.017
bridge+0.015
Neg logit contributions
 surroundings-0.025
 bond-0.023
esty-0.023
 eyebrow-0.022
assion-0.022
Token She
Token ID1375
Feature activation+1.19e-03

Pos logit contributions
br+0.036
 ow+0.035
zed+0.034
obb+0.034
bridge+0.031
Neg logit contributions
 surroundings-0.034
 bond-0.031
 eyebrow-0.031
 Believe-0.031
assion-0.030
Token loved
Token ID6151
Feature activation+1.42e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
esty+0.001
 eyebrow+0.001
 Believe+0.001
Neg logit contributions
br-0.002
 ow-0.002
obb-0.002
zed-0.002
bridge-0.002
Token to
Token ID284
Feature activation-6.00e-03

Pos logit contributions
 surroundings+0.002
 bond+0.002
assion+0.001
 rhythms+0.001
 hobbies+0.001
Neg logit contributions
obb-0.003
br-0.003
zed-0.003
 ow-0.003
bridge-0.003
Token very
Token ID845
Feature activation+1.69e-03

Pos logit contributions
 surroundings+0.035
 bond+0.032
 Believe+0.032
esty+0.031
 eyebrow+0.030
Neg logit contributions
br-0.045
zed-0.044
 ow-0.044
obb-0.043
bridge-0.041
Token adorable
Token ID29012
Feature activation+3.91e-03

Pos logit contributions
 surroundings+0.002
esty+0.002
 Believe+0.002
 bond+0.002
 Winning+0.002
Neg logit contributions
br-0.003
bridge-0.003
zed-0.003
 ow-0.003
 arrest-0.003
Token,
Token ID11
Feature activation+1.99e-02

Pos logit contributions
 surroundings+0.006
 bond+0.006
 eyebrow+0.006
esty+0.006
 Believe+0.006
Neg logit contributions
 ow-0.006
br-0.006
zed-0.006
obb-0.005
bridge-0.005
Token with
Token ID351
Feature activation-6.95e-03

Pos logit contributions
 surroundings+0.022
 bond+0.022
 Believe+0.020
 eyebrow+0.019
 Fighting+0.019
Neg logit contributions
obb-0.038
br-0.037
 ow-0.037
zed-0.036
bridge-0.034
Token long
Token ID890
Feature activation-3.39e-02

Pos logit contributions
obb+0.011
br+0.011
zed+0.011
bridge+0.010
eh+0.010
Neg logit contributions
 surroundings-0.010
 bond-0.010
 rhythms-0.009
 Believe-0.009
 Fighting-0.009
Token blonde
Token ID21541
Feature activation-6.17e-02

Pos logit contributions
br+0.056
zed+0.055
obb+0.055
 ow+0.054
aster+0.051
Neg logit contributions
 surroundings-0.049
 bond-0.043
 eyebrow-0.042
esty-0.041
 rhythms-0.040
Token hair
Token ID4190
Feature activation-2.07e-02

Pos logit contributions
zed+0.128
obb+0.125
br+0.121
 ow+0.118
bridge+0.118
Neg logit contributions
 surroundings-0.064
esty-0.050
 bond-0.048
 eyebrow-0.043
 hobbies-0.041
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
zed+0.038
obb+0.038
 ow+0.037
br+0.037
bridge+0.035
Neg logit contributions
 surroundings-0.025
 bond-0.022
assion-0.020
esty-0.020
 eyebrow-0.020
Token piercing
Token ID30662
Feature activation-1.95e-02

Pos logit contributions
 ow+0.021
br+0.020
zed+0.020
obb+0.019
bridge+0.017
Neg logit contributions
 surroundings-0.031
 bond-0.029
 eyebrow-0.028
esty-0.028
 Believe-0.028
Token blue
Token ID4171
Feature activation-3.19e-02

Pos logit contributions
 ow+0.029
br+0.028
zed+0.025
obb+0.024
bridge+0.023
Neg logit contributions
 surroundings-0.032
 Believe-0.031
esty-0.031
 bond-0.031
 eyebrow-0.030
Token eyes
Token ID2951
Feature activation-2.77e-02

Pos logit contributions
zed+0.050
br+0.049
 ow+0.049
obb+0.048
aster+0.044
Neg logit contributions
 surroundings-0.049
 bond-0.045
 eyebrow-0.043
esty-0.042
assion-0.042
Token then
Token ID788
Feature activation+2.97e-03

Pos logit contributions
 surroundings+0.045
 eyebrow+0.044
esty+0.043
 bond+0.041
 Believe+0.040
Neg logit contributions
 ow-0.045
zed-0.043
br-0.042
aster-0.040
 reached-0.039
Token,
Token ID11
Feature activation+3.43e-03

Pos logit contributions
 surroundings+0.005
 bond+0.005
esty+0.004
 eyebrow+0.004
 Believe+0.004
Neg logit contributions
 ow-0.004
br-0.004
zed-0.004
obb-0.004
bridge-0.004
Token Tim
Token ID5045
Feature activation-1.82e-03

Pos logit contributions
 surroundings+0.007
 eyebrow+0.007
 bond+0.007
esty+0.006
 Believe+0.006
Neg logit contributions
 ow-0.004
br-0.004
zed-0.004
obb-0.003
aster-0.003
Tokenmy
Token ID1820
Feature activation-1.97e-02

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
obb+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
esty-0.001
 Believe-0.001
Token slipped
Token ID18859
Feature activation-3.92e-03

Pos logit contributions
 ow+0.030
br+0.030
zed+0.029
obb+0.029
bridge+0.026
Neg logit contributions
 surroundings-0.030
 bond-0.028
esty-0.027
 eyebrow-0.027
assion-0.027
Token and
Token ID290
Feature activation-6.14e-02

Pos logit contributions
 ow+0.007
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.005
 eyebrow-0.004
 bond-0.004
 Believe-0.004
 Fighting-0.004
Token fell
Token ID3214
Feature activation-2.04e-02

Pos logit contributions
br+0.083
bridge+0.081
ihu+0.077
zed+0.076
ocol+0.076
Neg logit contributions
 tighter-0.082
 eyebrow-0.081
idents-0.080
 surroundings-0.079
 Fighting-0.079
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
zed+0.038
 ow+0.037
br+0.036
obb+0.035
aster+0.035
Neg logit contributions
 surroundings-0.024
 eyebrow-0.022
 Fighting-0.021
 bond-0.021
assion-0.021
Token He
Token ID679
Feature activation-2.63e-02

Pos logit contributions
br+0.016
 ow+0.016
zed+0.016
obb+0.016
bridge+0.015
Neg logit contributions
 surroundings-0.015
 bond-0.014
 eyebrow-0.014
 Fighting-0.014
assion-0.014
Token hit
Token ID2277
Feature activation+7.60e-04

Pos logit contributions
br+0.033
 ow+0.032
obb+0.031
zed+0.031
bridge+0.029
Neg logit contributions
 surroundings-0.047
 bond-0.044
 eyebrow-0.043
esty-0.042
assion-0.042
Token his
Token ID465
Feature activation+1.34e-02

Pos logit contributions
 surroundings+0.002
 bond+0.002
esty+0.002
assion+0.002
 Believe+0.002
Neg logit contributions
 ow-0.001
br-0.001
obb-0.001
zed-0.001
aster-0.001
Token put
Token ID1234
Feature activation-2.64e-02

Pos logit contributions
 ow+0.016
br+0.016
zed+0.015
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.019
 bond-0.018
esty-0.017
 eyebrow-0.017
 Believe-0.017
Token it
Token ID340
Feature activation-1.85e-02

Pos logit contributions
 ow+0.037
br+0.037
zed+0.035
obb+0.035
bridge+0.031
Neg logit contributions
 surroundings-0.044
 bond-0.041
 eyebrow-0.040
esty-0.040
 Believe-0.039
Token on
Token ID319
Feature activation-1.08e-02

Pos logit contributions
 ow+0.030
br+0.029
zed+0.029
obb+0.028
aster+0.026
Neg logit contributions
 surroundings-0.027
 bond-0.025
 eyebrow-0.025
esty-0.025
assion-0.024
Token the
Token ID262
Feature activation-8.30e-03

Pos logit contributions
 ow+0.015
br+0.014
zed+0.014
obb+0.014
bridge+0.012
Neg logit contributions
 surroundings-0.019
 bond-0.017
 eyebrow-0.017
esty-0.017
 Believe-0.017
Token window
Token ID4324
Feature activation-2.02e-02

Pos logit contributions
 ow+0.012
br+0.012
zed+0.011
obb+0.011
 mo+0.010
Neg logit contributions
 surroundings-0.013
 bond-0.013
 Believe-0.013
esty-0.012
assion-0.012
Token sill
Token ID49276
Feature activation-6.05e-02

Pos logit contributions
br+0.024
 ow+0.024
zed+0.023
obb+0.021
bridge+0.021
Neg logit contributions
 surroundings-0.038
 bond-0.036
esty-0.036
 Believe-0.035
 eyebrow-0.035
Token with
Token ID351
Feature activation-2.53e-02

Pos logit contributions
 ow+0.098
obb+0.094
 arrest+0.094
br+0.094
 blast+0.091
Neg logit contributions
 surroundings-0.076
 eyebrow-0.074
 zone-0.074
liness-0.070
 bond-0.070
Token a
Token ID257
Feature activation-3.54e-02

Pos logit contributions
br+0.039
obb+0.037
zed+0.036
 ow+0.035
atmeal+0.033
Neg logit contributions
 surroundings-0.038
 bond-0.036
 eyebrow-0.036
 Believe-0.035
 directions-0.033
Token tight
Token ID5381
Feature activation-1.26e-02

Pos logit contributions
 ow+0.044
zed+0.044
br+0.042
obb+0.042
bridge+0.037
Neg logit contributions
 surroundings-0.063
 bond-0.061
 eyebrow-0.060
 Believe-0.058
esty-0.057
Token lid
Token ID19789
Feature activation-3.02e-02

Pos logit contributions
 ow+0.019
obb+0.018
zed+0.018
br+0.018
oll+0.017
Neg logit contributions
 surroundings-0.019
 bond-0.019
 eyebrow-0.018
esty-0.017
 Believe-0.016
Token.
Token ID13
Feature activation+1.76e-03

Pos logit contributions
 ow+0.047
obb+0.045
zed+0.045
br+0.045
aster+0.041
Neg logit contributions
 surroundings-0.043
 eyebrow-0.042
 bond-0.040
assion-0.040
owner-0.038
Token could
Token ID714
Feature activation-8.36e-03

Pos logit contributions
 surroundings+0.010
 eyebrow+0.010
 bond+0.009
 rhythms+0.009
 Fighting+0.009
Neg logit contributions
zed-0.007
 ow-0.007
br-0.006
 reached-0.006
obb-0.006
Token do
Token ID466
Feature activation-1.33e-02

Pos logit contributions
 ow+0.013
br+0.013
zed+0.012
obb+0.012
bridge+0.011
Neg logit contributions
 surroundings-0.013
 bond-0.012
 Believe-0.012
esty-0.011
assion-0.011
Token anything
Token ID1997
Feature activation-7.43e-03

Pos logit contributions
 ow+0.018
br+0.017
obb+0.017
zed+0.016
bridge+0.015
Neg logit contributions
 surroundings-0.023
 bond-0.022
 Believe-0.021
 rhythms-0.021
assion-0.021
Token,
Token ID11
Feature activation+9.69e-06

Pos logit contributions
 ow+0.011
zed+0.010
obb+0.010
br+0.010
bridge+0.010
Neg logit contributions
 surroundings-0.012
 Believe-0.011
 bond-0.011
assion-0.011
 rhythms-0.011
Token as
Token ID355
Feature activation-1.16e-02

Feature not active on prev token;
no predictions were affected.
Token long
Token ID890
Feature activation-6.04e-02

Pos logit contributions
 ow+0.015
br+0.015
obb+0.014
zed+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.021
 bond-0.019
 Believe-0.018
 rhythms-0.018
assion-0.018
Token as
Token ID355
Feature activation-1.88e-02

Pos logit contributions
 ow+0.144
itt+0.139
obb+0.139
P+0.138
eh+0.137
Neg logit contributions
 themselves-0.029
 surroundings-0.028
 then-0.024
 attention-0.023
 since-0.023
Token he
Token ID339
Feature activation-2.74e-02

Pos logit contributions
 ow+0.022
zed+0.021
br+0.021
obb+0.021
bridge+0.019
Neg logit contributions
 surroundings-0.036
 bond-0.033
 Believe-0.033
 rhythms-0.032
 ourselves-0.031
Token stayed
Token ID9658
Feature activation-1.74e-02

Pos logit contributions
 ow+0.043
br+0.042
zed+0.041
obb+0.040
bridge+0.038
Neg logit contributions
 surroundings-0.041
 bond-0.038
 Believe-0.037
esty-0.037
 eyebrow-0.037
Token fit
Token ID4197
Feature activation-5.67e-03

Pos logit contributions
br+0.023
 ow+0.023
zed+0.023
obb+0.022
bridge+0.020
Neg logit contributions
 surroundings-0.029
 bond-0.029
 eyebrow-0.028
assion-0.027
 Believe-0.027
Token and
Token ID290
Feature activation-1.81e-02

Pos logit contributions
 ow+0.008
br+0.008
zed+0.007
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.010
 bond-0.009
 eyebrow-0.009
esty-0.009
assion-0.009
Token window
Token ID4324
Feature activation+2.06e-03

Pos logit contributions
 surroundings+0.024
 bond+0.023
 eyebrow+0.022
esty+0.022
 Believe+0.021
Neg logit contributions
 ow-0.031
br-0.031
zed-0.030
obb-0.030
bridge-0.028
Token and
Token ID290
Feature activation-3.36e-03

Pos logit contributions
 surroundings+0.003
 bond+0.003
esty+0.003
 eyebrow+0.003
 Believe+0.003
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token said
Token ID531
Feature activation-1.38e-02

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
 reached+0.004
 mo+0.004
Neg logit contributions
 surroundings-0.006
 bond-0.006
esty-0.006
 eyebrow-0.006
 Believe-0.006
Token,
Token ID11
Feature activation+1.87e-02

Pos logit contributions
obb+0.024
 ow+0.023
zed+0.023
br+0.023
eh+0.023
Neg logit contributions
 surroundings-0.016
assion-0.015
 Believe-0.015
idents-0.015
 eyebrow-0.015
Token "
Token ID366
Feature activation-1.74e-02

Pos logit contributions
 surroundings+0.028
 bond+0.026
 eyebrow+0.025
 Believe+0.025
esty+0.025
Neg logit contributions
 ow-0.030
br-0.029
zed-0.028
obb-0.028
bridge-0.026
TokenJ
Token ID41
Feature activation-6.03e-02

Pos logit contributions
 ow+0.025
br+0.025
zed+0.024
obb+0.023
bridge+0.021
Neg logit contributions
 surroundings-0.029
 bond-0.027
 eyebrow-0.026
esty-0.026
 Believe-0.026
Tokenenna
Token ID13713
Feature activation-2.26e-02

Pos logit contributions
 ow+0.130
zed+0.123
br+0.114
obb+0.114
 slit+0.110
Neg logit contributions
 surroundings-0.061
 zone-0.057
esty-0.056
 eyebrow-0.053
assion-0.053
Token,
Token ID11
Feature activation+2.30e-02

Pos logit contributions
 ow+0.035
br+0.034
zed+0.033
obb+0.033
bridge+0.031
Neg logit contributions
 surroundings-0.035
 bond-0.032
esty-0.031
 Believe-0.031
assion-0.031
Token there
Token ID612
Feature activation+1.59e-02

Pos logit contributions
 surroundings+0.041
 bond+0.038
 eyebrow+0.037
esty+0.037
 Believe+0.037
Neg logit contributions
 ow-0.030
br-0.030
zed-0.029
obb-0.028
bridge-0.026
Token's
Token ID338
Feature activation-1.10e-03

Pos logit contributions
 surroundings+0.023
 bond+0.021
 eyebrow+0.021
esty+0.021
 Believe+0.020
Neg logit contributions
 ow-0.026
br-0.026
zed-0.025
obb-0.024
bridge-0.022
Token a
Token ID257
Feature activation-9.06e-03

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.002
 bond-0.002
esty-0.002
 eyebrow-0.002
assion-0.002
Token looking
Token ID2045
Feature activation-9.95e-03

Pos logit contributions
obb+0.020
br+0.019
oll+0.019
 ow+0.018
bridge+0.018
Neg logit contributions
 surroundings-0.016
 bond-0.014
 ourselves-0.014
 themselves-0.014
 rhythms-0.014
Token around
Token ID1088
Feature activation-6.71e-03

Pos logit contributions
 ow+0.020
br+0.019
zed+0.019
obb+0.018
aster+0.018
Neg logit contributions
 surroundings-0.012
 bond-0.010
 eyebrow-0.010
esty-0.010
assion-0.010
Token it
Token ID340
Feature activation-1.32e-03

Pos logit contributions
br+0.010
 ow+0.009
zed+0.009
obb+0.009
bridge+0.008
Neg logit contributions
 surroundings-0.011
 bond-0.010
 eyebrow-0.010
 Believe-0.010
assion-0.010
Token.
Token ID13
Feature activation-1.68e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.002
 bond-0.002
 eyebrow-0.002
esty-0.002
 Believe-0.002
Token Everywhere
Token ID48201
Feature activation-2.30e-02

Pos logit contributions
 ow+0.002
br+0.002
obb+0.002
zed+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.003
 Believe-0.003
 eyebrow-0.003
esty-0.003
Token it
Token ID340
Feature activation-6.00e-02

Pos logit contributions
obb+0.031
zed+0.031
 ow+0.031
br+0.031
bridge+0.028
Neg logit contributions
 surroundings-0.039
 bond-0.036
 Believe-0.035
esty-0.034
assion-0.034
Token looked
Token ID3114
Feature activation-2.71e-02

Pos logit contributions
 ow+0.091
br+0.087
obb+0.086
zed+0.084
 arrest+0.082
Neg logit contributions
 surroundings-0.093
 bond-0.082
 Believe-0.078
esty-0.077
 rhythms-0.075
Token,
Token ID11
Feature activation-4.34e-03

Pos logit contributions
br+0.041
 ow+0.041
zed+0.040
obb+0.040
bridge+0.038
Neg logit contributions
 surroundings-0.042
 bond-0.036
esty-0.035
 eyebrow-0.035
 ourselves-0.035
Token there
Token ID612
Feature activation-1.03e-03

Pos logit contributions
br+0.006
 ow+0.006
zed+0.006
obb+0.006
aster+0.005
Neg logit contributions
 surroundings-0.007
 bond-0.007
 Believe-0.007
 eyebrow-0.007
esty-0.007
Token was
Token ID373
Feature activation+5.34e-03

Pos logit contributions
 ow+0.001
zed+0.001
br+0.001
 reached+0.001
on+0.001
Neg logit contributions
 surroundings-0.002
esty-0.002
 eyebrow-0.002
assion-0.002
 bond-0.002
Token beauty
Token ID8737
Feature activation-8.88e-03

Pos logit contributions
 surroundings+0.011
esty+0.011
 bond+0.011
 eyebrow+0.011
idents+0.010
Neg logit contributions
 ow-0.006
br-0.005
zed-0.005
obb-0.005
bridge-0.004
Token coin
Token ID10752
Feature activation+7.88e-03

Pos logit contributions
 ow+0.016
br+0.016
zed+0.016
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.022
 bond-0.021
 eyebrow-0.020
esty-0.020
 Believe-0.020
Token.
Token ID13
Feature activation+4.12e-04

Pos logit contributions
 surroundings+0.015
 bond+0.014
 eyebrow+0.014
esty+0.014
 Believe+0.013
Neg logit contributions
 ow-0.010
br-0.009
zed-0.009
obb-0.009
bridge-0.008
Token But
Token ID887
Feature activation+2.93e-02

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
assion+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token she
Token ID673
Feature activation-1.22e-02

Pos logit contributions
 surroundings+0.066
 bond+0.064
esty+0.064
 eyebrow+0.063
assion+0.061
Neg logit contributions
 ow-0.028
br-0.026
zed-0.026
obb-0.024
aster-0.023
Token slipped
Token ID18859
Feature activation+7.15e-03

Pos logit contributions
 ow+0.017
br+0.016
zed+0.016
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.021
 bond-0.020
assion-0.020
 eyebrow-0.019
esty-0.019
Token and
Token ID290
Feature activation-5.98e-02

Pos logit contributions
 surroundings+0.008
 eyebrow+0.008
 bond+0.008
 Believe+0.007
 Fighting+0.007
Neg logit contributions
 ow-0.013
br-0.013
zed-0.013
obb-0.013
bridge-0.012
Token fell
Token ID3214
Feature activation-1.26e-02

Pos logit contributions
bridge+0.083
br+0.082
ihu+0.081
zed+0.079
yt+0.079
Neg logit contributions
 tighter-0.081
 eyebrow-0.071
 Fighting-0.068
Don-0.067
 since-0.066
Token into
Token ID656
Feature activation-2.03e-02

Pos logit contributions
zed+0.023
 ow+0.022
aster+0.022
br+0.021
obb+0.021
Neg logit contributions
 surroundings-0.015
 eyebrow-0.014
 Fighting-0.014
wood-0.013
 tighter-0.013
Token the
Token ID262
Feature activation-8.78e-03

Pos logit contributions
br+0.032
zed+0.031
 ow+0.030
obb+0.030
bridge+0.029
Neg logit contributions
 surroundings-0.031
 eyebrow-0.029
 bond-0.028
 Believe-0.028
 rhythms-0.027
Token water
Token ID1660
Feature activation-2.10e-02

Pos logit contributions
zed+0.013
br+0.013
 ow+0.013
obb+0.012
oll+0.012
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.012
 rhythms-0.011
 Fighting-0.011
Token.
Token ID13
Feature activation-6.95e-03

Pos logit contributions
zed+0.038
br+0.037
 ow+0.036
obb+0.035
oll+0.034
Neg logit contributions
 eyebrow-0.024
 surroundings-0.023
liness-0.022
 Fighting-0.022
 zone-0.021
Token sand
Token ID6450
Feature activation-3.95e-02

Pos logit contributions
br+0.022
zed+0.022
 ow+0.022
obb+0.020
oll+0.019
Neg logit contributions
 surroundings-0.030
 bond-0.028
 eyebrow-0.028
 rhythms-0.027
esty-0.027
Token tower
Token ID10580
Feature activation-2.85e-02

Pos logit contributions
br+0.058
 ow+0.056
zed+0.055
obb+0.053
oll+0.051
Neg logit contributions
 surroundings-0.062
 eyebrow-0.055
 bond-0.055
 rhythms-0.054
esty-0.054
Token fell
Token ID3214
Feature activation-1.09e-03

Pos logit contributions
 ow+0.035
br+0.035
zed+0.034
obb+0.033
oll+0.030
Neg logit contributions
 surroundings-0.048
 eyebrow-0.046
 bond-0.045
 rhythms-0.044
 Believe-0.043
Token and
Token ID290
Feature activation-3.21e-02

Pos logit contributions
zed+0.002
 ow+0.002
br+0.002
aster+0.002
obb+0.002
Neg logit contributions
 surroundings-0.001
 eyebrow-0.001
 bond-0.001
assion-0.001
 Fighting-0.001
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
zed+0.047
br+0.045
atmeal+0.044
oll+0.044
bridge+0.043
Neg logit contributions
 Fighting-0.041
 tighter-0.041
 eyebrow-0.041
idents-0.040
assion-0.039
Token sand
Token ID6450
Feature activation-5.96e-02

Pos logit contributions
zed+0.023
br+0.022
 ow+0.021
oll+0.020
obb+0.020
Neg logit contributions
 surroundings-0.025
 bond-0.023
 eyebrow-0.022
 rhythms-0.022
esty-0.021
Token scattered
Token ID16830
Feature activation-1.16e-02

Pos logit contributions
br+0.087
oll+0.084
P+0.083
zed+0.083
 ow+0.081
Neg logit contributions
 surroundings-0.082
 zone-0.074
 eyebrow-0.073
owner-0.071
 bond-0.071
Token everywhere
Token ID8347
Feature activation-2.15e-02

Pos logit contributions
zed+0.020
br+0.019
 ow+0.019
aster+0.018
atmeal+0.018
Neg logit contributions
 surroundings-0.015
 eyebrow-0.014
 bond-0.014
 Fighting-0.014
 themselves-0.013
Token.
Token ID13
Feature activation-6.91e-03

Pos logit contributions
br+0.036
 ow+0.036
obb+0.035
zed+0.035
atmeal+0.033
Neg logit contributions
 surroundings-0.027
 eyebrow-0.026
 bond-0.024
 rhythms-0.024
 ourselves-0.024
Token
Token ID198
Feature activation-2.71e-05

Pos logit contributions
 ow+0.011
br+0.011
zed+0.011
obb+0.010
bridge+0.010
Neg logit contributions
 surroundings-0.010
 Believe-0.009
 eyebrow-0.009
 Fighting-0.009
 bond-0.009
Token
Token ID198
Feature activation-1.15e-02

Pos logit contributions
 ow+0.000
br+0.000
zed+0.000
obb+0.000
aster+0.000
Neg logit contributions
 surroundings-0.000
 bond-0.000
esty-0.000
 eyebrow-0.000
assion-0.000
Token and
Token ID290
Feature activation-4.93e-02

Pos logit contributions
 ow+0.007
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.004
 eyebrow-0.004
 bond-0.004
 Believe-0.004
esty-0.004
Token spilled
Token ID31896
Feature activation-2.02e-02

Pos logit contributions
br+0.072
bridge+0.068
add+0.063
obb+0.062
itt+0.060
Neg logit contributions
 eyebrow-0.065
idents-0.064
 surroundings-0.062
 tighter-0.062
 Fighting-0.060
Token his
Token ID465
Feature activation-2.63e-03

Pos logit contributions
br+0.029
zed+0.028
 ow+0.027
obb+0.026
bridge+0.025
Neg logit contributions
 surroundings-0.032
 eyebrow-0.031
 bond-0.031
 Fighting-0.029
 Believe-0.029
Token bucket
Token ID19236
Feature activation-2.56e-02

Pos logit contributions
br+0.004
 ow+0.004
zed+0.004
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.004
esty-0.004
 Believe-0.004
Token of
Token ID286
Feature activation-1.04e-02

Pos logit contributions
br+0.042
zed+0.042
 ow+0.041
obb+0.038
aster+0.038
Neg logit contributions
 surroundings-0.033
 eyebrow-0.033
 bond-0.029
liness-0.029
esty-0.028
Token sand
Token ID6450
Feature activation-5.93e-02

Pos logit contributions
 ow+0.013
br+0.012
zed+0.012
obb+0.012
bridge+0.010
Neg logit contributions
 surroundings-0.020
 bond-0.018
esty-0.018
assion-0.018
 Believe-0.018
Token.
Token ID13
Feature activation-2.79e-02

Pos logit contributions
zed+0.112
br+0.109
aster+0.106
 ow+0.102
itt+0.102
Neg logit contributions
 surroundings-0.065
idents-0.056
wood-0.056
liness-0.055
 eyebrow-0.054
Token Jane
Token ID12091
Feature activation-1.03e-02

Pos logit contributions
br+0.053
obb+0.048
 ow+0.048
zed+0.046
bridge+0.046
Neg logit contributions
 surroundings-0.035
 eyebrow-0.033
 Believe-0.031
 Fighting-0.029
owner-0.029
Token was
Token ID373
Feature activation-1.79e-03

Pos logit contributions
 ow+0.014
br+0.014
zed+0.014
obb+0.013
bridge+0.012
Neg logit contributions
 surroundings-0.018
 bond-0.017
esty-0.016
 Believe-0.016
assion-0.016
Token so
Token ID523
Feature activation-1.56e-02

Pos logit contributions
br+0.003
 ow+0.003
zed+0.003
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.003
 eyebrow-0.002
 bond-0.002
 Believe-0.002
esty-0.002
Token angry
Token ID7954
Feature activation-2.16e-03

Pos logit contributions
br+0.028
zed+0.026
 ow+0.025
bridge+0.025
obb+0.024
Neg logit contributions
 surroundings-0.021
 eyebrow-0.020
 bond-0.019
 Believe-0.018
 Fighting-0.018
Token play
Token ID711
Feature activation+5.46e-04

Pos logit contributions
 ow+0.004
br+0.004
zed+0.003
obb+0.003
aster+0.003
Neg logit contributions
 surroundings-0.004
 eyebrow-0.004
 bond-0.004
esty-0.004
assion-0.004
Token lawyer
Token ID6853
Feature activation+6.65e-03

Pos logit contributions
 surroundings+0.001
 eyebrow+0.001
 bond+0.001
assion+0.001
esty+0.001
Neg logit contributions
br-0.001
 ow-0.001
zed-0.001
obb-0.001
bridge-0.001
Token together
Token ID1978
Feature activation+1.02e-02

Pos logit contributions
 surroundings+0.010
 bond+0.010
 eyebrow+0.010
esty+0.009
 Believe+0.009
Neg logit contributions
br-0.010
 ow-0.010
zed-0.010
obb-0.009
bridge-0.009
Token sometimes
Token ID3360
Feature activation+6.56e-03

Pos logit contributions
 surroundings+0.017
 eyebrow+0.015
 bond+0.015
esty+0.015
assion+0.015
Neg logit contributions
br-0.015
 ow-0.015
zed-0.014
obb-0.014
aster-0.013
Token,
Token ID11
Feature activation+1.25e-03

Pos logit contributions
 surroundings+0.012
 eyebrow+0.011
 bond+0.011
esty+0.011
 Believe+0.011
Neg logit contributions
 ow-0.008
br-0.008
zed-0.008
obb-0.007
aster-0.007
Token but
Token ID475
Feature activation+3.06e-02

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
assion+0.002
esty+0.002
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.002
Token only
Token ID691
Feature activation+2.16e-02

Pos logit contributions
 surroundings+0.069
 eyebrow+0.064
esty+0.064
assion+0.062
 zone+0.062
Neg logit contributions
 ow-0.026
br-0.025
zed-0.023
 pr-0.019
obb-0.019
Token after
Token ID706
Feature activation-5.25e-03

Pos logit contributions
 surroundings+0.034
 eyebrow+0.031
 bond+0.031
esty+0.030
assion+0.030
Neg logit contributions
 ow-0.033
br-0.033
zed-0.031
obb-0.030
aster-0.028
Token Lily
Token ID20037
Feature activation-1.63e-02

Pos logit contributions
br+0.008
 ow+0.007
obb+0.007
zed+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.008
 bond-0.008
 Believe-0.007
 eyebrow-0.007
 rhythms-0.007
Token did
Token ID750
Feature activation-1.82e-02

Pos logit contributions
zed+0.022
 ow+0.022
br+0.022
obb+0.020
aster+0.019
Neg logit contributions
 surroundings-0.028
 eyebrow-0.026
 bond-0.026
assion-0.025
 Believe-0.025
Token her
Token ID607
Feature activation+4.82e-03

Pos logit contributions
 ow+0.025
br+0.025
zed+0.024
obb+0.023
bridge+0.021
Neg logit contributions
 surroundings-0.031
 bond-0.029
 eyebrow-0.028
esty-0.028
 Believe-0.028
Token that
Token ID326
Feature activation+1.95e-02

Pos logit contributions
 surroundings+0.015
 bond+0.015
esty+0.015
 eyebrow+0.015
 Believe+0.014
Neg logit contributions
br-0.013
zed-0.013
 ow-0.013
obb-0.013
bridge-0.012
Token's
Token ID338
Feature activation+1.89e-02

Pos logit contributions
 surroundings+0.032
esty+0.029
 eyebrow+0.029
 bond+0.029
 Believe+0.027
Neg logit contributions
 ow-0.030
br-0.029
zed-0.028
obb-0.025
bridge-0.024
Token really
Token ID1107
Feature activation+1.40e-02

Pos logit contributions
 surroundings+0.039
 eyebrow+0.036
 bond+0.036
esty+0.035
 zone+0.034
Neg logit contributions
 ow-0.023
br-0.020
zed-0.019
obb-0.019
 blast-0.016
Token cool
Token ID3608
Feature activation+1.41e-03

Pos logit contributions
 surroundings+0.021
esty+0.020
 bond+0.019
assion+0.019
 Believe+0.019
Neg logit contributions
 ow-0.021
zed-0.021
br-0.020
obb-0.020
bridge-0.019
Token!
Token ID0
Feature activation+4.84e-03

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
esty+0.002
 Believe+0.002
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.002
Token But
Token ID887
Feature activation+3.72e-02

Pos logit contributions
 surroundings+0.008
 bond+0.008
 eyebrow+0.007
esty+0.007
assion+0.007
Neg logit contributions
br-0.007
 ow-0.007
zed-0.006
obb-0.006
bridge-0.006
Token be
Token ID307
Feature activation+1.14e-02

Pos logit contributions
 surroundings+0.068
 eyebrow+0.064
 bond+0.062
esty+0.062
assion+0.061
Neg logit contributions
 ow-0.049
br-0.045
zed-0.044
obb-0.041
 mo-0.039
Token careful
Token ID8161
Feature activation+1.40e-02

Pos logit contributions
 surroundings+0.019
 bond+0.018
idents+0.018
assion+0.017
 zone+0.017
Neg logit contributions
 ow-0.016
br-0.016
zed-0.016
eh-0.016
obb-0.016
Token,
Token ID11
Feature activation+1.01e-02

Pos logit contributions
 surroundings+0.025
 bond+0.025
esty+0.024
 eyebrow+0.023
assion+0.023
Neg logit contributions
 ow-0.018
zed-0.017
br-0.017
obb-0.015
bridge-0.014
Token it
Token ID340
Feature activation+2.62e-03

Pos logit contributions
 surroundings+0.020
 bond+0.019
 eyebrow+0.018
esty+0.018
assion+0.018
Neg logit contributions
 ow-0.012
br-0.011
zed-0.011
obb-0.010
aster-0.009
Token's
Token ID338
Feature activation+1.70e-02

Pos logit contributions
 surroundings+0.003
esty+0.003
 Believe+0.003
 bond+0.003
assion+0.003
Neg logit contributions
 ow-0.005
br-0.005
zed-0.005
obb-0.005
bridge-0.005
Token more
Token ID517
Feature activation-6.31e-03

Pos logit contributions
 ow+0.013
br+0.013
zed+0.012
obb+0.012
bridge+0.011
Neg logit contributions
 surroundings-0.015
 bond-0.014
 eyebrow-0.013
esty-0.013
 Believe-0.013
Token to
Token ID284
Feature activation-3.59e-03

Pos logit contributions
 ow+0.009
br+0.009
zed+0.009
obb+0.009
bridge+0.008
Neg logit contributions
 surroundings-0.010
 bond-0.009
 eyebrow-0.009
esty-0.009
 Believe-0.009
Token write
Token ID3551
Feature activation-1.23e-03

Pos logit contributions
 ow+0.005
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.005
 eyebrow-0.005
esty-0.005
 Believe-0.005
Token."
Token ID526
Feature activation+2.94e-03

Pos logit contributions
br+0.002
 ow+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.002
 bond-0.002
esty-0.002
 eyebrow-0.002
 Believe-0.002
Token
Token ID198
Feature activation-3.43e-03

Pos logit contributions
 surroundings+0.005
 bond+0.005
esty+0.004
 eyebrow+0.004
assion+0.004
Neg logit contributions
 ow-0.004
br-0.004
zed-0.004
obb-0.004
bridge-0.004
TokenBut
Token ID1537
Feature activation+3.18e-02

Pos logit contributions
 ow+0.005
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.005
 bond-0.005
esty-0.005
 eyebrow-0.005
assion-0.005
Token Tommy
Token ID19919
Feature activation+1.14e-02

Pos logit contributions
 surroundings+0.056
 bond+0.053
 eyebrow+0.052
assion+0.051
esty+0.051
Neg logit contributions
 ow-0.042
zed-0.041
br-0.039
aster-0.038
obb-0.036
Token didn
Token ID1422
Feature activation-1.07e-02

Pos logit contributions
 surroundings+0.019
 bond+0.019
 rhythms+0.017
 eyebrow+0.017
 Believe+0.017
Neg logit contributions
 ow-0.016
zed-0.016
obb-0.015
br-0.015
 reached-0.014
Token't
Token ID470
Feature activation-4.17e-03

Pos logit contributions
 ow+0.014
 cuc+0.012
 cor+0.012
br+0.012
eh+0.012
Neg logit contributions
 Believe-0.018
 Fighting-0.017
 eyebrow-0.017
 surroundings-0.017
assion-0.017
Token listen
Token ID6004
Feature activation-8.14e-03

Pos logit contributions
 ow+0.009
br+0.009
zed+0.009
obb+0.009
bridge+0.008
Neg logit contributions
 surroundings-0.004
 bond-0.004
 Believe-0.003
 eyebrow-0.003
esty-0.003
Token.
Token ID13
Feature activation+4.36e-03

Pos logit contributions
 ow+0.009
zed+0.009
br+0.009
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.016
 bond-0.015
esty-0.015
 Believe-0.015
 eyebrow-0.014
Token She
Token ID1375
Feature activation-1.10e-04

Pos logit contributions
 surroundings+0.003
 bond+0.003
 eyebrow+0.003
esty+0.003
assion+0.003
Neg logit contributions
 ow-0.003
br-0.003
zed-0.003
obb-0.003
bridge-0.003
Token finished
Token ID5201
Feature activation-2.00e-02

Pos logit contributions
 ow+0.000
br+0.000
zed+0.000
obb+0.000
bridge+0.000
Neg logit contributions
 surroundings-0.000
 bond-0.000
 eyebrow-0.000
esty-0.000
 Believe-0.000
Token her
Token ID607
Feature activation+5.62e-04

Pos logit contributions
br+0.030
 ow+0.030
obb+0.029
bridge+0.027
zed+0.026
Neg logit contributions
 surroundings-0.032
 bond-0.029
 Believe-0.028
 eyebrow-0.028
assion-0.028
Token ice
Token ID4771
Feature activation+2.22e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
br-0.001
 ow-0.001
zed-0.001
obb-0.001
bridge-0.001
Token-
Token ID12
Feature activation-3.23e-03

Pos logit contributions
 surroundings+0.004
 bond+0.004
 eyebrow+0.004
 Believe+0.004
esty+0.004
Neg logit contributions
br-0.003
 ow-0.003
zed-0.003
obb-0.002
aster-0.002
Tokencream
Token ID36277
Feature activation+3.23e-02

Pos logit contributions
 ow+0.005
br+0.005
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.005
 bond-0.004
esty-0.004
 eyebrow-0.004
assion-0.004
Token and
Token ID290
Feature activation-5.36e-03

Pos logit contributions
 surroundings+0.055
esty+0.052
 eyebrow+0.051
 Believe+0.051
assion+0.051
Neg logit contributions
br-0.045
 ow-0.044
zed-0.042
obb-0.041
aster-0.038
Token said
Token ID531
Feature activation-8.68e-03

Pos logit contributions
 ow+0.007
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.009
 bond-0.009
 eyebrow-0.009
esty-0.009
 Believe-0.008
Token goodbye
Token ID24829
Feature activation+5.82e-03

Pos logit contributions
 ow+0.014
obb+0.013
br+0.013
zed+0.013
aster+0.012
Neg logit contributions
 surroundings-0.012
 bond-0.012
 Believe-0.012
 eyebrow-0.011
assion-0.011
Token to
Token ID284
Feature activation-2.87e-03

Pos logit contributions
 surroundings+0.011
 bond+0.010
 eyebrow+0.010
 Believe+0.010
 rhythms+0.010
Neg logit contributions
zed-0.007
br-0.007
 ow-0.007
obb-0.006
 reached-0.006
Token the
Token ID262
Feature activation+4.70e-04

Pos logit contributions
br+0.004
 ow+0.004
obb+0.004
zed+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.005
 bond-0.005
 Believe-0.004
 eyebrow-0.004
esty-0.004
Token one
Token ID530
Feature activation+8.00e-03

Pos logit contributions
 ow+0.018
br+0.018
zed+0.017
obb+0.017
bridge+0.015
Neg logit contributions
 surroundings-0.022
 bond-0.020
 eyebrow-0.020
esty-0.020
 Believe-0.020
Token to
Token ID284
Feature activation+1.55e-03

Pos logit contributions
 surroundings+0.016
 bond+0.015
 eyebrow+0.015
assion+0.015
esty+0.015
Neg logit contributions
 ow-0.009
br-0.009
zed-0.008
obb-0.008
bridge-0.007
Token ride
Token ID6594
Feature activation-1.59e-03

Pos logit contributions
 surroundings+0.003
 bond+0.003
 eyebrow+0.002
esty+0.002
 Believe+0.002
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.002
Token on
Token ID319
Feature activation-1.36e-02

Pos logit contributions
br+0.002
zed+0.002
 ow+0.002
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.003
 bond-0.003
 eyebrow-0.003
 Believe-0.003
assion-0.003
Token.
Token ID13
Feature activation+6.49e-03

Pos logit contributions
 ow+0.017
br+0.016
zed+0.016
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.025
 bond-0.024
 eyebrow-0.024
esty-0.024
 Believe-0.023
Token But
Token ID887
Feature activation+3.10e-02

Pos logit contributions
 surroundings+0.014
 bond+0.013
 Believe+0.013
 eyebrow+0.013
 rhythms+0.012
Neg logit contributions
 ow-0.006
br-0.006
obb-0.006
zed-0.006
 reached-0.005
Token she
Token ID673
Feature activation-9.01e-03

Pos logit contributions
 surroundings+0.078
assion+0.073
 bond+0.072
 Believe+0.072
 eyebrow+0.071
Neg logit contributions
 ow-0.021
zed-0.018
br-0.015
 reached-0.014
obb-0.013
Token promised
Token ID8072
Feature activation-7.71e-03

Pos logit contributions
 ow+0.012
zed+0.012
 reached+0.011
br+0.011
obb+0.011
Neg logit contributions
 surroundings-0.016
assion-0.015
 bond-0.014
 rhythms-0.014
 routes-0.014
Token they
Token ID484
Feature activation-1.07e-02

Pos logit contributions
 ow+0.012
br+0.012
zed+0.011
obb+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.012
 bond-0.011
 eyebrow-0.011
esty-0.011
 Believe-0.011
Token could
Token ID714
Feature activation-9.71e-03

Pos logit contributions
 ow+0.015
zed+0.015
br+0.014
obb+0.014
 reached+0.013
Neg logit contributions
 surroundings-0.018
 eyebrow-0.017
 bond-0.017
 rhythms-0.017
 Believe-0.016
Token come
Token ID1282
Feature activation-4.49e-03

Pos logit contributions
 ow+0.014
br+0.014
zed+0.014
obb+0.013
bridge+0.012
Neg logit contributions
 surroundings-0.016
 bond-0.015
esty-0.014
 eyebrow-0.014
 Believe-0.014
Token,
Token ID11
Feature activation+5.39e-03

Pos logit contributions
 ow+0.041
obb+0.040
br+0.039
bridge+0.039
eh+0.038
Neg logit contributions
 surroundings-0.019
idents-0.019
 Believe-0.017
 Fighting-0.017
 themselves-0.017
Token they
Token ID484
Feature activation-9.69e-03

Pos logit contributions
 surroundings+0.011
 bond+0.010
 eyebrow+0.010
esty+0.010
assion+0.010
Neg logit contributions
 ow-0.006
br-0.006
zed-0.006
obb-0.005
aster-0.005
Token sat
Token ID3332
Feature activation+1.37e-02

Pos logit contributions
br+0.015
 ow+0.015
zed+0.014
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.014
 bond-0.014
 eyebrow-0.014
esty-0.013
 Believe-0.013
Token down
Token ID866
Feature activation+3.98e-03

Pos logit contributions
 bond+0.024
 Believe+0.024
 eyebrow+0.023
assion+0.023
 rhythms+0.022
Neg logit contributions
 ow-0.017
zed-0.017
obb-0.017
 mo-0.016
bridge-0.015
Token to
Token ID284
Feature activation+1.12e-02

Pos logit contributions
 surroundings+0.005
 bond+0.005
 eyebrow+0.005
 Believe+0.005
esty+0.005
Neg logit contributions
 ow-0.007
br-0.007
zed-0.007
obb-0.007
bridge-0.006
Token eat
Token ID4483
Feature activation+6.19e-03

Pos logit contributions
 surroundings+0.018
 bond+0.017
 eyebrow+0.017
esty+0.017
 Believe+0.016
Neg logit contributions
 ow-0.016
br-0.016
zed-0.016
obb-0.015
bridge-0.014
Token the
Token ID262
Feature activation+4.12e-03

Pos logit contributions
 surroundings+0.012
esty+0.012
assion+0.012
 bond+0.012
 Believe+0.012
Neg logit contributions
 ow-0.007
br-0.006
zed-0.006
obb-0.006
aster-0.006
Token pancakes
Token ID47008
Feature activation+1.30e-02

Pos logit contributions
 surroundings+0.008
esty+0.008
 Believe+0.007
assion+0.007
 bond+0.007
Neg logit contributions
 ow-0.005
br-0.005
obb-0.005
zed-0.004
 mo-0.004
Token.
Token ID13
Feature activation+1.37e-02

Pos logit contributions
 surroundings+0.021
 bond+0.020
 eyebrow+0.019
esty+0.019
 Believe+0.019
Neg logit contributions
 ow-0.019
br-0.019
zed-0.018
obb-0.018
bridge-0.016
Token They
Token ID1119
Feature activation-1.22e-02

Pos logit contributions
 surroundings+0.020
 bond+0.019
 eyebrow+0.019
esty+0.018
 Believe+0.018
Neg logit contributions
 ow-0.022
br-0.021
zed-0.021
obb-0.020
bridge-0.019
Token were
Token ID547
Feature activation+1.54e-02

Pos logit contributions
 ow+0.018
br+0.017
zed+0.017
obb+0.016
bridge+0.015
Neg logit contributions
 surroundings-0.020
 bond-0.019
 eyebrow-0.018
esty-0.018
 Believe-0.018
Token a
Token ID257
Feature activation+8.72e-03

Pos logit contributions
 surroundings+0.017
 bond+0.016
esty+0.016
 eyebrow+0.016
assion+0.016
Neg logit contributions
 ow-0.008
br-0.007
obb-0.006
zed-0.006
 cor-0.005
Token big
Token ID1263
Feature activation+1.59e-02

Pos logit contributions
 surroundings+0.018
 bond+0.017
 eyebrow+0.017
esty+0.017
 Believe+0.017
Neg logit contributions
 ow-0.009
br-0.008
zed-0.008
obb-0.008
bridge-0.007
Token dog
Token ID3290
Feature activation+1.41e-02

Pos logit contributions
 surroundings+0.030
esty+0.028
 eyebrow+0.028
 bond+0.027
 Believe+0.027
Neg logit contributions
 ow-0.021
br-0.019
obb-0.018
zed-0.017
 mo-0.016
Token.
Token ID13
Feature activation+5.48e-03

Pos logit contributions
 surroundings+0.020
 Fighting+0.019
 bond+0.019
 Believe+0.019
assion+0.019
Neg logit contributions
obb-0.023
 ow-0.022
br-0.022
zed-0.021
bridge-0.020
Token The
Token ID383
Feature activation+4.30e-03

Pos logit contributions
 surroundings+0.007
 bond+0.007
 eyebrow+0.007
esty+0.007
 Believe+0.007
Neg logit contributions
br-0.009
 ow-0.009
obb-0.009
zed-0.009
bridge-0.009
Token dog
Token ID3290
Feature activation+1.15e-02

Pos logit contributions
 surroundings+0.009
assion+0.009
 eyebrow+0.008
esty+0.008
wood+0.008
Neg logit contributions
 ow-0.005
br-0.004
obb-0.004
 wo-0.003
 sne-0.003
Token is
Token ID318
Feature activation+1.84e-02

Pos logit contributions
 surroundings+0.016
 bond+0.015
 eyebrow+0.014
esty+0.014
 Believe+0.014
Neg logit contributions
 ow-0.019
br-0.019
zed-0.019
obb-0.019
bridge-0.017
Token barking
Token ID48961
Feature activation+1.05e-02

Pos logit contributions
 surroundings+0.035
 bond+0.033
esty+0.032
 eyebrow+0.032
assion+0.032
Neg logit contributions
 ow-0.023
br-0.021
zed-0.020
obb-0.019
 mo-0.017
Token loud
Token ID7812
Feature activation-3.87e-03

Pos logit contributions
 surroundings+0.015
 bond+0.014
 eyebrow+0.014
esty+0.014
 Believe+0.014
Neg logit contributions
 ow-0.017
br-0.017
zed-0.016
obb-0.016
bridge-0.015
Token.
Token ID13
Feature activation-6.93e-03

Pos logit contributions
 ow+0.006
br+0.006
zed+0.005
obb+0.005
bridge+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.006
 eyebrow-0.006
esty-0.006
 Believe-0.006
Token Anna
Token ID11735
Feature activation+4.46e-03

Pos logit contributions
br+0.011
obb+0.011
 ow+0.011
zed+0.010
bridge+0.010
Neg logit contributions
 surroundings-0.010
 eyebrow-0.010
 Believe-0.009
esty-0.009
 Fighting-0.009
Token the
Token ID262
Feature activation+1.36e-02

Pos logit contributions
 surroundings+0.016
 bond+0.015
esty+0.015
 eyebrow+0.015
 Believe+0.014
Neg logit contributions
 ow-0.010
br-0.010
zed-0.009
obb-0.009
bridge-0.008
Token smile
Token ID8212
Feature activation-7.45e-03

Pos logit contributions
 surroundings+0.023
esty+0.022
 Believe+0.022
 eyebrow+0.022
assion+0.022
Neg logit contributions
 ow-0.019
br-0.018
obb-0.017
zed-0.016
bridge-0.015
Tokeny
Token ID88
Feature activation-5.25e-04

Pos logit contributions
obb+0.012
 ow+0.011
zed+0.011
br+0.011
eh+0.010
Neg logit contributions
 surroundings-0.011
 bond-0.010
assion-0.010
esty-0.010
 Fighting-0.010
Token face
Token ID1986
Feature activation-6.08e-03

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
obb+0.001
bridge+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
esty-0.001
 Believe-0.001
Token and
Token ID290
Feature activation-5.18e-04

Pos logit contributions
 ow+0.009
obb+0.009
zed+0.009
br+0.009
 arrest+0.008
Neg logit contributions
 surroundings-0.009
assion-0.009
 eyebrow-0.008
 bond-0.008
esty-0.008
Token the
Token ID262
Feature activation+8.23e-03

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
 mo+0.001
obb+0.001
Neg logit contributions
 surroundings-0.001
esty-0.001
 bond-0.001
assion-0.001
 eyebrow-0.001
Token heart
Token ID2612
Feature activation-8.80e-03

Pos logit contributions
 surroundings+0.014
esty+0.014
 Believe+0.013
assion+0.013
 bond+0.013
Neg logit contributions
 ow-0.011
br-0.010
obb-0.010
zed-0.010
bridge-0.009
Token.
Token ID13
Feature activation-1.60e-03

Pos logit contributions
 ow+0.013
obb+0.013
zed+0.013
br+0.013
aster+0.011
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.013
assion-0.012
 Believe-0.012
Token She
Token ID1375
Feature activation+6.29e-04

Pos logit contributions
 ow+0.003
br+0.003
zed+0.003
obb+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.002
 Believe-0.002
 bond-0.002
 eyebrow-0.002
esty-0.002
Token reads
Token ID9743
Feature activation+1.78e-02

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
 Believe+0.001
esty+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
 surroundings+0.040
esty+0.039
 bond+0.038
 eyebrow+0.036
idents+0.036
Neg logit contributions
br-0.017
 ow-0.017
zed-0.014
on-0.013
aster-0.012
Token excited
Token ID6568
Feature activation-4.31e-03

Pos logit contributions
 surroundings+0.006
 bond+0.005
 Fighting+0.005
 Believe+0.005
 eyebrow+0.005
Neg logit contributions
br-0.009
 ow-0.008
zed-0.008
obb-0.008
bridge-0.008
Token to
Token ID284
Feature activation+6.52e-03

Pos logit contributions
br+0.007
 ow+0.007
zed+0.006
obb+0.006
bridge+0.006
Neg logit contributions
 surroundings-0.007
 bond-0.006
 eyebrow-0.006
assion-0.006
idents-0.006
Token go
Token ID467
Feature activation+5.46e-03

Pos logit contributions
 Believe+0.005
 bond+0.005
 surroundings+0.005
 rhythms+0.005
 communicate+0.005
Neg logit contributions
obb-0.015
br-0.014
 ow-0.014
oll-0.013
eh-0.013
Token to
Token ID284
Feature activation+2.55e-02

Pos logit contributions
 surroundings+0.007
 bond+0.006
 Believe+0.006
esty+0.006
 eyebrow+0.006
Neg logit contributions
 ow-0.010
obb-0.010
br-0.010
zed-0.010
bridge-0.009
Token the
Token ID262
Feature activation+3.34e-02

Pos logit contributions
 surroundings+0.044
 bond+0.042
 eyebrow+0.041
esty+0.041
 Believe+0.040
Neg logit contributions
 ow-0.034
br-0.034
zed-0.033
obb-0.032
bridge-0.029
Token lake
Token ID13546
Feature activation+1.04e-02

Pos logit contributions
 surroundings+0.063
 eyebrow+0.062
 bond+0.060
esty+0.059
 Believe+0.058
Neg logit contributions
 ow-0.041
br-0.038
obb-0.033
 mo-0.033
zed-0.033
Token with
Token ID351
Feature activation-1.69e-02

Pos logit contributions
 surroundings+0.020
 bond+0.019
 eyebrow+0.019
esty+0.019
 Believe+0.019
Neg logit contributions
 ow-0.012
br-0.011
zed-0.011
obb-0.011
aster-0.010
Token their
Token ID511
Feature activation+1.67e-02

Pos logit contributions
br+0.029
zed+0.027
 ow+0.027
obb+0.027
bridge+0.025
Neg logit contributions
 surroundings-0.024
 bond-0.022
esty-0.022
 eyebrow-0.021
 rhythms-0.021
Token dad
Token ID9955
Feature activation-8.88e-03

Pos logit contributions
 eyebrow+0.034
assion+0.033
esty+0.033
 Believe+0.032
 surroundings+0.032
Neg logit contributions
 ow-0.019
 mo-0.015
 o-0.014
 blast-0.014
br-0.013
Token.
Token ID13
Feature activation+9.47e-04

Pos logit contributions
 ow+0.010
br+0.010
zed+0.010
obb+0.009
aster+0.008
Neg logit contributions
 surroundings-0.017
 bond-0.016
 eyebrow-0.016
 Believe-0.016
esty-0.016
Token They
Token ID1119
Feature activation-1.66e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.001
Token
Token ID198
Feature activation+1.38e-03

Pos logit contributions
 surroundings+0.005
 bond+0.005
 eyebrow+0.005
esty+0.004
 Believe+0.004
Neg logit contributions
 ow-0.006
br-0.006
zed-0.005
obb-0.005
bridge-0.005
Token"
Token ID1
Feature activation-2.63e-03

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
 Believe+0.002
assion+0.002
Neg logit contributions
br-0.002
 ow-0.002
zed-0.002
obb-0.002
aster-0.002
TokenNot
Token ID3673
Feature activation+2.81e-02

Pos logit contributions
br+0.005
 ow+0.005
obb+0.005
zed+0.005
P+0.005
Neg logit contributions
 surroundings-0.003
assion-0.003
 bond-0.003
 eyebrow-0.003
esty-0.003
Token yet
Token ID1865
Feature activation+1.22e-02

Pos logit contributions
 surroundings+0.042
 bond+0.039
 eyebrow+0.038
esty+0.038
 Believe+0.037
Neg logit contributions
 ow-0.045
br-0.045
zed-0.044
obb-0.043
bridge-0.039
Token,
Token ID11
Feature activation-1.91e-03

Pos logit contributions
 surroundings+0.021
 bond+0.019
 eyebrow+0.019
esty+0.019
 Believe+0.019
Neg logit contributions
 ow-0.017
br-0.017
zed-0.016
obb-0.016
bridge-0.014
Token sweet
Token ID6029
Feature activation+4.73e-03

Pos logit contributions
br+0.003
zed+0.003
 ow+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.003
 eyebrow-0.003
esty-0.003
 Believe-0.003
Tokenie
Token ID494
Feature activation-2.19e-02

Pos logit contributions
 surroundings+0.006
 bond+0.006
 eyebrow+0.006
esty+0.005
 Believe+0.005
Neg logit contributions
br-0.008
zed-0.008
 ow-0.008
obb-0.008
bridge-0.008
Token.
Token ID13
Feature activation-9.64e-04

Pos logit contributions
br+0.033
 ow+0.033
zed+0.032
obb+0.032
bridge+0.029
Neg logit contributions
 surroundings-0.034
 bond-0.031
esty-0.030
 eyebrow-0.030
 Believe-0.029
Token We
Token ID775
Feature activation+8.56e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.001
bridge+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
esty-0.001
 Believe-0.001
Token have
Token ID423
Feature activation-1.30e-02

Pos logit contributions
 surroundings+0.016
 eyebrow+0.015
assion+0.015
 bond+0.015
 rhythms+0.015
Neg logit contributions
 ow-0.011
br-0.010
obb-0.010
zed-0.010
aster-0.009
Token to
Token ID284
Feature activation+5.71e-03

Pos logit contributions
 ow+0.020
br+0.020
zed+0.019
obb+0.019
bridge+0.017
Neg logit contributions
 surroundings-0.020
 bond-0.019
 eyebrow-0.018
esty-0.018
 Believe-0.018
Token waved
Token ID26834
Feature activation-1.74e-02

Pos logit contributions
 surroundings+0.002
 bond+0.002
 eyebrow+0.002
esty+0.002
 Believe+0.002
Neg logit contributions
 ow-0.002
br-0.002
zed-0.002
obb-0.002
bridge-0.002
Token goodbye
Token ID24829
Feature activation-3.69e-04

Pos logit contributions
 ow+0.021
br+0.021
zed+0.020
obb+0.019
bridge+0.017
Neg logit contributions
 surroundings-0.033
 bond-0.031
 eyebrow-0.030
esty-0.030
 Believe-0.030
Token to
Token ID284
Feature activation-1.57e-02

Pos logit contributions
 ow+0.000
br+0.000
zed+0.000
obb+0.000
 mo+0.000
Neg logit contributions
 surroundings-0.001
 bond-0.001
 Believe-0.001
 eyebrow-0.001
esty-0.001
Token all
Token ID477
Feature activation-8.12e-03

Pos logit contributions
br+0.024
 ow+0.023
obb+0.022
zed+0.021
bridge+0.021
Neg logit contributions
 surroundings-0.025
 bond-0.024
 Believe-0.023
 eyebrow-0.023
esty-0.023
Token his
Token ID465
Feature activation+6.37e-03

Pos logit contributions
 ow+0.011
br+0.011
obb+0.011
zed+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.013
 Believe-0.012
 rhythms-0.012
Token friends
Token ID2460
Feature activation-8.97e-03

Pos logit contributions
 eyebrow+0.010
 Believe+0.010
 Fighting+0.010
assion+0.010
esty+0.010
Neg logit contributions
 ow-0.010
br-0.009
zed-0.009
obb-0.008
 cor-0.008
Token and
Token ID290
Feature activation-8.24e-03

Pos logit contributions
 ow+0.014
br+0.014
zed+0.014
obb+0.013
bridge+0.013
Neg logit contributions
 surroundings-0.013
 bond-0.012
 eyebrow-0.012
esty-0.012
 Believe-0.012
Token skipped
Token ID26684
Feature activation-7.15e-03

Pos logit contributions
zed+0.009
 ow+0.008
br+0.008
 reached+0.007
 mo+0.007
Neg logit contributions
 surroundings-0.017
 eyebrow-0.016
assion-0.016
esty-0.016
 Believe-0.016
Token down
Token ID866
Feature activation-8.57e-03

Pos logit contributions
br+0.012
 ow+0.012
zed+0.012
obb+0.011
bridge+0.011
Neg logit contributions
 surroundings-0.010
 bond-0.009
 eyebrow-0.009
esty-0.009
 Believe-0.009
Token the
Token ID262
Feature activation+5.67e-03

Pos logit contributions
 ow+0.012
br+0.012
zed+0.011
obb+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.015
 bond-0.014
 eyebrow-0.013
esty-0.013
 Believe-0.013
Token street
Token ID4675
Feature activation-1.01e-02

Pos logit contributions
 surroundings+0.006
 bond+0.006
 eyebrow+0.006
esty+0.006
 Believe+0.006
Neg logit contributions
 ow-0.011
br-0.011
zed-0.011
obb-0.011
bridge-0.010
Token worry
Token ID5490
Feature activation-1.48e-02

Pos logit contributions
 surroundings+0.013
 bond+0.012
 eyebrow+0.011
esty+0.011
 Believe+0.011
Neg logit contributions
br-0.024
 ow-0.024
zed-0.023
obb-0.023
bridge-0.021
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
zed+0.028
br+0.027
bridge+0.026
obb+0.026
aster+0.025
Neg logit contributions
 surroundings-0.018
idents-0.017
 eyebrow-0.017
assion-0.016
 bond-0.015
Token Tim
Token ID5045
Feature activation-1.12e-02

Pos logit contributions
br+0.016
zed+0.016
 ow+0.016
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.021
 bond-0.019
 eyebrow-0.019
 Believe-0.019
esty-0.019
Token!
Token ID0
Feature activation+4.12e-04

Pos logit contributions
 ow+0.015
br+0.015
zed+0.014
obb+0.014
bridge+0.012
Neg logit contributions
 surroundings-0.020
 bond-0.019
 eyebrow-0.018
esty-0.018
 Believe-0.018
Token If
Token ID1002
Feature activation+7.77e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
assion+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token you
Token ID345
Feature activation-4.09e-03

Pos logit contributions
 surroundings+0.014
 bond+0.013
 Believe+0.013
assion+0.013
esty+0.013
Neg logit contributions
br-0.010
 ow-0.009
obb-0.009
zed-0.009
bridge-0.009
Token think
Token ID892
Feature activation-3.65e-03

Pos logit contributions
 ow+0.006
br+0.006
zed+0.006
obb+0.006
bridge+0.005
Neg logit contributions
 surroundings-0.006
 bond-0.006
esty-0.006
 eyebrow-0.006
 Believe-0.006
Token it
Token ID340
Feature activation-4.25e-03

Pos logit contributions
 ow+0.005
br+0.005
zed+0.005
obb+0.005
bridge+0.004
Neg logit contributions
 surroundings-0.006
 bond-0.006
 eyebrow-0.006
esty-0.006
 Believe-0.006
Token's
Token ID338
Feature activation+1.63e-02

Pos logit contributions
 ow+0.008
br+0.008
zed+0.007
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.006
 bond-0.005
 eyebrow-0.005
esty-0.005
 Believe-0.005
Token too
Token ID1165
Feature activation+1.47e-02

Pos logit contributions
 surroundings+0.028
 bond+0.027
 eyebrow+0.027
esty+0.026
 Believe+0.026
Neg logit contributions
 ow-0.023
br-0.022
zed-0.021
obb-0.020
aster-0.018
Token spicy
Token ID26880
Feature activation+1.73e-02

Pos logit contributions
 surroundings+0.027
 bond+0.025
esty+0.025
 Believe+0.025
 eyebrow+0.025
Neg logit contributions
 ow-0.019
br-0.018
obb-0.017
zed-0.017
aster-0.015
Token receive
Token ID3328
Feature activation-1.13e-02

Pos logit contributions
 bond+0.003
 surroundings+0.003
 Believe+0.003
 eyebrow+0.003
esty+0.003
Neg logit contributions
br-0.004
 ow-0.004
obb-0.004
zed-0.004
oll-0.003
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
 ow+0.012
br+0.012
zed+0.011
obb+0.011
aster+0.010
Neg logit contributions
 surroundings-0.022
assion-0.021
 bond-0.021
 eyebrow-0.021
esty-0.021
Token lovely
Token ID14081
Feature activation+1.12e-03

Pos logit contributions
 surroundings+0.021
assion+0.021
esty+0.020
eter+0.020
 Fighting+0.020
Neg logit contributions
 ow-0.011
br-0.011
 o-0.009
 che-0.009
 banana-0.009
Token fish
Token ID5916
Feature activation+8.61e-03

Pos logit contributions
 surroundings+0.002
assion+0.002
esty+0.002
 eyebrow+0.002
 Fighting+0.002
Neg logit contributions
br-0.001
 ow-0.001
zed-0.001
 cor-0.001
 cuc-0.001
Token as
Token ID355
Feature activation-9.42e-03

Pos logit contributions
 surroundings+0.015
 eyebrow+0.014
 bond+0.014
esty+0.013
assion+0.013
Neg logit contributions
 ow-0.012
br-0.012
zed-0.011
obb-0.010
bridge-0.010
Token a
Token ID257
Feature activation-1.44e-02

Pos logit contributions
 ow+0.014
obb+0.014
br+0.013
zed+0.013
bridge+0.012
Neg logit contributions
 surroundings-0.015
 bond-0.013
 Believe-0.013
 rhythms-0.013
assion-0.013
Token gift
Token ID6979
Feature activation-2.06e-03

Pos logit contributions
br+0.022
 ow+0.022
zed+0.021
obb+0.020
bridge+0.019
Neg logit contributions
 surroundings-0.023
 bond-0.021
 eyebrow-0.021
esty-0.021
 Believe-0.020
Token.
Token ID13
Feature activation+4.46e-03

Pos logit contributions
 ow+0.003
br+0.003
zed+0.003
obb+0.003
bridge+0.002
Neg logit contributions
 surroundings-0.003
 bond-0.003
 eyebrow-0.003
esty-0.003
 Believe-0.003
Token From
Token ID3574
Feature activation+2.32e-02

Pos logit contributions
 surroundings+0.006
 bond+0.006
 Believe+0.006
 eyebrow+0.006
esty+0.006
Neg logit contributions
 ow-0.008
br-0.008
obb-0.007
zed-0.007
bridge-0.007
Token that
Token ID326
Feature activation+1.85e-02

Pos logit contributions
 eyebrow+0.047
esty+0.047
 surroundings+0.047
 bond+0.047
idents+0.046
Neg logit contributions
 ow-0.024
zed-0.021
 o-0.020
br-0.019
obb-0.018
Token day
Token ID1110
Feature activation-9.17e-03

Pos logit contributions
 surroundings+0.031
esty+0.028
 eyebrow+0.028
assion+0.028
 bond+0.027
Neg logit contributions
br-0.027
zed-0.027
 ow-0.027
obb-0.024
aster-0.023
Token a
Token ID257
Feature activation-1.35e-02

Pos logit contributions
 surroundings+0.004
 bond+0.004
 Believe+0.003
assion+0.003
esty+0.003
Neg logit contributions
br-0.002
 ow-0.002
zed-0.002
obb-0.002
bridge-0.002
Token long
Token ID890
Feature activation-2.95e-02

Pos logit contributions
br+0.016
 ow+0.015
zed+0.013
obb+0.013
 mo+0.012
Neg logit contributions
 surroundings-0.027
esty-0.026
 Believe-0.026
 bond-0.025
 eyebrow-0.025
Token pipe
Token ID12656
Feature activation-9.96e-03

Pos logit contributions
 ow+0.048
obb+0.046
zed+0.046
br+0.045
oll+0.043
Neg logit contributions
 surroundings-0.041
 bond-0.039
 eyebrow-0.038
esty-0.036
 rhythms-0.036
Token and
Token ID290
Feature activation+2.38e-04

Pos logit contributions
zed+0.016
 ow+0.016
obb+0.016
br+0.015
aster+0.014
Neg logit contributions
 surroundings-0.013
 bond-0.012
assion-0.012
 eyebrow-0.012
 Believe-0.012
Token a
Token ID257
Feature activation-1.57e-02

Pos logit contributions
 surroundings+0.000
 bond+0.000
esty+0.000
 eyebrow+0.000
 Believe+0.000
Neg logit contributions
br-0.000
 ow-0.000
zed-0.000
obb-0.000
bridge-0.000
Token seat
Token ID5852
Feature activation-1.78e-02

Pos logit contributions
br+0.019
 ow+0.018
 mo+0.015
zed+0.015
obb+0.015
Neg logit contributions
 surroundings-0.031
 Believe-0.030
esty-0.030
 bond-0.029
assion-0.029
Token for
Token ID329
Feature activation-5.06e-03

Pos logit contributions
 ow+0.026
br+0.025
zed+0.025
obb+0.024
aster+0.021
Neg logit contributions
 surroundings-0.028
 bond-0.027
 eyebrow-0.026
esty-0.026
assion-0.025
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
br+0.008
 ow+0.007
zed+0.007
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.008
 bond-0.007
 rhythms-0.007
 eyebrow-0.007
 Believe-0.007
Token driver
Token ID4639
Feature activation-1.54e-02

Pos logit contributions
 ow+0.018
br+0.017
obb+0.016
zed+0.016
bridge+0.015
Neg logit contributions
 surroundings-0.021
 Believe-0.020
esty-0.020
 bond-0.020
 eyebrow-0.019
Token.
Token ID13
Feature activation-2.11e-03

Pos logit contributions
 ow+0.020
br+0.019
zed+0.019
obb+0.018
bridge+0.017
Neg logit contributions
 surroundings-0.028
 bond-0.026
 eyebrow-0.026
esty-0.026
 Believe-0.025
Token Their
Token ID5334
Feature activation-1.09e-04

Pos logit contributions
br+0.003
 ow+0.003
obb+0.003
zed+0.003
bridge+0.003
Neg logit contributions
 surroundings-0.004
 bond-0.003
 eyebrow-0.003
esty-0.003
assion-0.003
Token's
Token ID338
Feature activation+1.92e-02

Pos logit contributions
 surroundings+0.024
 bond+0.024
 Fighting+0.023
esty+0.023
 eyebrow+0.022
Neg logit contributions
zed-0.019
 ow-0.018
br-0.018
 reached-0.018
 mo-0.017
Token mom
Token ID1995
Feature activation+1.73e-02

Pos logit contributions
 surroundings+0.031
esty+0.029
 eyebrow+0.029
 bond+0.029
assion+0.029
Neg logit contributions
 ow-0.028
zed-0.026
br-0.026
obb-0.025
 mo-0.024
Tokenmy
Token ID1820
Feature activation+1.51e-02

Pos logit contributions
 surroundings+0.024
 bond+0.022
esty+0.021
 Believe+0.020
 eyebrow+0.020
Neg logit contributions
 ow-0.030
 reached-0.029
br-0.028
on-0.028
 came-0.028
Token and
Token ID290
Feature activation-5.25e-03

Pos logit contributions
 surroundings+0.026
 bond+0.024
esty+0.023
 eyebrow+0.023
assion+0.023
Neg logit contributions
 ow-0.021
br-0.021
zed-0.021
 reached-0.019
obb-0.018
Token daddy
Token ID35822
Feature activation+1.10e-02

Pos logit contributions
 ow+0.008
br+0.008
zed+0.008
obb+0.007
bridge+0.007
Neg logit contributions
 surroundings-0.008
 bond-0.008
 eyebrow-0.008
esty-0.008
 Believe-0.008
Token said
Token ID531
Feature activation-8.86e-03

Pos logit contributions
 surroundings+0.019
 bond+0.018
esty+0.018
 eyebrow+0.018
assion+0.017
Neg logit contributions
 ow-0.014
br-0.014
zed-0.014
obb-0.013
 mo-0.012
Token they
Token ID484
Feature activation+2.40e-03

Pos logit contributions
obb+0.014
 ow+0.013
br+0.013
zed+0.013
eh+0.012
Neg logit contributions
 surroundings-0.013
 bond-0.012
 Believe-0.012
 eyebrow-0.012
assion-0.012
Token wanted
Token ID2227
Feature activation-2.90e-03

Pos logit contributions
 surroundings+0.005
 eyebrow+0.004
 bond+0.004
esty+0.004
 rhythms+0.004
Neg logit contributions
 ow-0.003
zed-0.003
br-0.003
 reached-0.003
obb-0.002
Token to
Token ID284
Feature activation-6.22e-03

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
obb+0.004
aster+0.004
Neg logit contributions
 surroundings-0.005
 bond-0.004
 eyebrow-0.004
esty-0.004
assion-0.004
Token buy
Token ID2822
Feature activation+8.39e-03

Pos logit contributions
 ow+0.009
br+0.009
zed+0.009
obb+0.009
bridge+0.008
Neg logit contributions
 surroundings-0.010
 bond-0.010
 Believe-0.009
 eyebrow-0.009
esty-0.009
Token the
Token ID262
Feature activation+6.30e-03

Pos logit contributions
 surroundings+0.015
 bond+0.014
esty+0.014
 eyebrow+0.014
assion+0.013
Neg logit contributions
 ow-0.011
br-0.011
zed-0.010
obb-0.010
bridge-0.009
TokenOh
Token ID5812
Feature activation+1.78e-03

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
 Believe-0.001
assion-0.001
Token,
Token ID11
Feature activation-3.98e-03

Pos logit contributions
 bond+0.002
idents+0.002
 surroundings+0.002
esty+0.002
 Fighting+0.002
Neg logit contributions
obb-0.003
zed-0.003
br-0.003
bridge-0.003
eh-0.002
Token Tom
Token ID4186
Feature activation-1.25e-02

Pos logit contributions
zed+0.007
br+0.007
obb+0.006
 ow+0.006
eh+0.006
Neg logit contributions
 Believe-0.005
 Fighting-0.005
idents-0.005
esty-0.005
 bond-0.005
Token,
Token ID11
Feature activation+4.99e-03

Pos logit contributions
br+0.022
zed+0.021
obb+0.021
 ow+0.021
bridge+0.020
Neg logit contributions
 surroundings-0.016
esty-0.015
 bond-0.014
liness-0.014
 Fighting-0.014
Token what
Token ID644
Feature activation-1.91e-02

Pos logit contributions
 Believe+0.006
 bond+0.006
 Fighting+0.006
idents+0.006
esty+0.006
Neg logit contributions
obb-0.008
zed-0.008
br-0.008
bridge-0.007
eh-0.007
Token did
Token ID750
Feature activation-3.98e-02

Pos logit contributions
zed+0.039
obb+0.038
br+0.036
 ow+0.035
ihu+0.035
Neg logit contributions
 Believe-0.017
 Fighting-0.017
 opinions-0.016
 rhythms-0.016
 hobbies-0.015
Token you
Token ID345
Feature activation+3.91e-03

Pos logit contributions
obb+0.067
br+0.063
bridge+0.062
 ow+0.061
add+0.059
Neg logit contributions
 ourselves-0.054
 surroundings-0.053
idents-0.051
 bond-0.049
 rhythms-0.048
Token do
Token ID466
Feature activation-7.27e-03

Pos logit contributions
 surroundings+0.005
 bond+0.005
 eyebrow+0.005
esty+0.005
 Believe+0.005
Neg logit contributions
 ow-0.007
br-0.007
zed-0.007
obb-0.006
bridge-0.006
Token?
Token ID30
Feature activation+1.26e-02

Pos logit contributions
br+0.008
 ow+0.008
zed+0.008
obb+0.008
bridge+0.007
Neg logit contributions
 surroundings-0.014
 bond-0.014
esty-0.013
 eyebrow-0.013
assion-0.013
Token You
Token ID921
Feature activation-3.43e-03

Pos logit contributions
 surroundings+0.018
 bond+0.016
esty+0.016
 eyebrow+0.016
 Believe+0.016
Neg logit contributions
 ow-0.021
br-0.021
zed-0.020
obb-0.020
bridge-0.018
Token were
Token ID547
Feature activation+1.01e-02

Pos logit contributions
zed+0.005
br+0.005
 ow+0.005
obb+0.005
aster+0.005
Neg logit contributions
 surroundings-0.005
 bond-0.005
esty-0.005
 eyebrow-0.005
 Believe-0.005
Token said
Token ID531
Feature activation-1.11e-02

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.002
 bond-0.002
 eyebrow-0.002
esty-0.002
 Believe-0.002
Token she
Token ID673
Feature activation+4.62e-03

Pos logit contributions
br+0.017
obb+0.016
 ow+0.016
zed+0.016
bridge+0.016
Neg logit contributions
 surroundings-0.016
 bond-0.015
 eyebrow-0.015
idents-0.015
 Believe-0.015
Token could
Token ID714
Feature activation-3.61e-03

Pos logit contributions
 surroundings+0.008
 bond+0.007
 eyebrow+0.007
 Believe+0.007
 rhythms+0.007
Neg logit contributions
 ow-0.007
br-0.007
zed-0.007
obb-0.006
 reached-0.006
Token no
Token ID645
Feature activation-1.04e-02

Pos logit contributions
 ow+0.005
br+0.005
zed+0.004
obb+0.004
aster+0.004
Neg logit contributions
 surroundings-0.006
 bond-0.006
 eyebrow-0.006
esty-0.006
assion-0.006
Token longer
Token ID2392
Feature activation-1.02e-02

Pos logit contributions
br+0.016
 ow+0.015
zed+0.015
obb+0.015
bridge+0.014
Neg logit contributions
 surroundings-0.017
 bond-0.016
 eyebrow-0.015
esty-0.015
 Believe-0.015
Token get
Token ID651
Feature activation-3.79e-02

Pos logit contributions
br+0.015
 ow+0.015
zed+0.014
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.016
 bond-0.015
 eyebrow-0.015
 Believe-0.014
esty-0.014
Token past
Token ID1613
Feature activation-2.68e-02

Pos logit contributions
br+0.065
zed+0.062
 ow+0.062
bridge+0.060
obb+0.059
Neg logit contributions
 surroundings-0.048
owner-0.044
 ourselves-0.044
esty-0.043
 attention-0.043
Tokenries
Token ID1678
Feature activation-2.61e-03

Pos logit contributions
br+0.040
zed+0.039
 ow+0.037
obb+0.036
 blast+0.035
Neg logit contributions
 surroundings-0.043
esty-0.038
 ourselves-0.037
 eyebrow-0.037
 bond-0.037
Token.
Token ID13
Feature activation-7.07e-04

Pos logit contributions
 ow+0.004
zed+0.004
br+0.004
obb+0.004
bridge+0.004
Neg logit contributions
 surroundings-0.004
 bond-0.004
 eyebrow-0.003
esty-0.003
assion-0.003
Token The
Token ID383
Feature activation-1.12e-02

Pos logit contributions
 ow+0.001
br+0.001
zed+0.001
obb+0.001
aster+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
 eyebrow-0.001
esty-0.001
assion-0.001
Token girl
Token ID2576
Feature activation-1.49e-04

Pos logit contributions
 ow+0.021
br+0.020
obb+0.020
zed+0.019
bridge+0.018
Neg logit contributions
 surroundings-0.014
assion-0.013
 bond-0.013
 eyebrow-0.013
 Believe-0.012
Token with
Token ID351
Feature activation-5.80e-03

Pos logit contributions
 surroundings+0.021
assion+0.020
esty+0.020
 bond+0.020
 Believe+0.019
Neg logit contributions
 ow-0.013
br-0.012
zed-0.011
 mo-0.011
bridge-0.011
Token trees
Token ID7150
Feature activation-1.63e-02

Pos logit contributions
 ow+0.007
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.010
 bond-0.010
 eyebrow-0.010
esty-0.009
 Believe-0.009
Token and
Token ID290
Feature activation-7.37e-03

Pos logit contributions
 ow+0.030
zed+0.029
br+0.029
obb+0.029
bridge+0.027
Neg logit contributions
 surroundings-0.020
 bond-0.018
 eyebrow-0.018
 Believe-0.017
esty-0.017
Token flowers
Token ID12734
Feature activation-2.99e-02

Pos logit contributions
 ow+0.011
br+0.010
zed+0.009
obb+0.009
bridge+0.009
Neg logit contributions
 surroundings-0.013
 bond-0.012
esty-0.012
 Believe-0.012
assion-0.012
Token and
Token ID290
Feature activation-1.09e-02

Pos logit contributions
zed+0.052
 ow+0.052
obb+0.051
br+0.051
aster+0.047
Neg logit contributions
 surroundings-0.038
 bond-0.035
 eyebrow-0.033
 Believe-0.033
 Fighting-0.032
Token benches
Token ID43183
Feature activation-4.36e-02

Pos logit contributions
 ow+0.016
br+0.015
zed+0.014
obb+0.014
bridge+0.013
Neg logit contributions
 surroundings-0.018
 bond-0.017
esty-0.017
 Believe-0.017
 eyebrow-0.017
Token.
Token ID13
Feature activation-8.31e-03

Pos logit contributions
zed+0.078
obb+0.076
 ow+0.075
br+0.073
aster+0.073
Neg logit contributions
 surroundings-0.055
 eyebrow-0.045
 Fighting-0.044
 bond-0.044
assion-0.044
Token She
Token ID1375
Feature activation-5.28e-03

Pos logit contributions
 ow+0.012
br+0.012
zed+0.012
obb+0.011
bridge+0.010
Neg logit contributions
 surroundings-0.014
 bond-0.013
 eyebrow-0.012
esty-0.012
assion-0.012
Token thought
Token ID1807
Feature activation+5.83e-04

Pos logit contributions
 ow+0.008
br+0.007
zed+0.007
obb+0.007
bridge+0.006
Neg logit contributions
 surroundings-0.009
 bond-0.008
 eyebrow-0.008
esty-0.008
assion-0.008
Token she
Token ID673
Feature activation+9.18e-04

Pos logit contributions
 surroundings+0.001
 rhythms+0.001
 themselves+0.001
 Believe+0.001
 eyebrow+0.001
Neg logit contributions
P-0.001
obb-0.001
eh-0.001
br-0.001
bridge-0.001
Token could
Token ID714
Feature activation-1.04e-03

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token sand
Token ID6450
Feature activation-1.99e-02

Pos logit contributions
 surroundings+0.004
 bond+0.004
 eyebrow+0.004
esty+0.004
 rhythms+0.004
Neg logit contributions
br-0.003
 ow-0.003
zed-0.003
obb-0.003
aster-0.002
Token was
Token ID373
Feature activation+1.81e-02

Pos logit contributions
 ow+0.035
br+0.034
zed+0.033
obb+0.033
bridge+0.031
Neg logit contributions
 surroundings-0.027
 bond-0.025
 eyebrow-0.024
esty-0.024
 Believe-0.024
Token rough
Token ID5210
Feature activation+5.11e-03

Pos logit contributions
 surroundings+0.032
 bond+0.030
esty+0.030
 eyebrow+0.030
 Believe+0.029
Neg logit contributions
 ow-0.024
br-0.024
zed-0.023
obb-0.022
bridge-0.020
Token and
Token ID290
Feature activation-2.67e-03

Pos logit contributions
 surroundings+0.007
 bond+0.007
esty+0.007
 eyebrow+0.007
 Believe+0.006
Neg logit contributions
 ow-0.009
br-0.009
zed-0.008
obb-0.008
bridge-0.007
Token the
Token ID262
Feature activation+4.69e-03

Pos logit contributions
 ow+0.003
br+0.003
zed+0.003
obb+0.003
 mo+0.003
Neg logit contributions
 surroundings-0.005
esty-0.005
 bond-0.005
 eyebrow-0.005
 Believe-0.005
Token waves
Token ID9813
Feature activation-3.59e-02

Pos logit contributions
 surroundings+0.009
 bond+0.008
 eyebrow+0.008
esty+0.008
 Believe+0.008
Neg logit contributions
 ow-0.006
br-0.006
zed-0.006
obb-0.005
bridge-0.005
Token were
Token ID547
Feature activation+5.70e-03

Pos logit contributions
 ow+0.056
br+0.055
zed+0.053
obb+0.052
bridge+0.048
Neg logit contributions
 surroundings-0.055
 bond-0.051
 eyebrow-0.050
esty-0.049
 Believe-0.049
Token big
Token ID1263
Feature activation-1.75e-02

Pos logit contributions
 surroundings+0.010
 bond+0.010
esty+0.010
 eyebrow+0.010
 Believe+0.009
Neg logit contributions
 ow-0.008
br-0.007
zed-0.007
obb-0.007
bridge-0.006
Token.
Token ID13
Feature activation-3.35e-03

Pos logit contributions
 ow+0.031
br+0.031
zed+0.030
obb+0.029
aster+0.027
Neg logit contributions
 surroundings-0.023
 bond-0.021
 eyebrow-0.020
esty-0.020
 Believe-0.020
Token
Token ID198
Feature activation+4.74e-03

Pos logit contributions
 ow+0.004
br+0.004
zed+0.004
obb+0.004
bridge+0.003
Neg logit contributions
 surroundings-0.006
 bond-0.006
 eyebrow-0.006
esty-0.006
 Believe-0.006
Token
Token ID198
Feature activation-4.65e-03

Pos logit contributions
 surroundings+0.008
 bond+0.007
esty+0.007
 eyebrow+0.007
assion+0.007
Neg logit contributions
br-0.007
 ow-0.007
zed-0.006
obb-0.006
bridge-0.006
Token in
Token ID287
Feature activation-1.54e-02

Pos logit contributions
 surroundings+0.003
 bond+0.003
esty+0.003
 eyebrow+0.003
assion+0.003
Neg logit contributions
 ow-0.004
br-0.004
zed-0.004
obb-0.003
bridge-0.003
Token the
Token ID262
Feature activation-1.97e-02

Pos logit contributions
br+0.022
 ow+0.022
zed+0.021
obb+0.021
bridge+0.019
Neg logit contributions
 surroundings-0.025
 bond-0.024
 eyebrow-0.023
 Believe-0.023
esty-0.023
Token rain
Token ID6290
Feature activation-1.39e-02

Pos logit contributions
br+0.029
 ow+0.029
zed+0.028
obb+0.027
bridge+0.025
Neg logit contributions
 surroundings-0.033
 bond-0.030
esty-0.029
 eyebrow-0.028
assion-0.028
Token until
Token ID1566
Feature activation-8.23e-03

Pos logit contributions
 ow+0.020
br+0.020
zed+0.019
obb+0.018
bridge+0.017
Neg logit contributions
 surroundings-0.023
 bond-0.022
 eyebrow-0.022
esty-0.021
 Believe-0.021
Token his
Token ID465
Feature activation-6.49e-04

Pos logit contributions
br+0.015
 ow+0.014
oll+0.013
obb+0.013
zed+0.013
Neg logit contributions
 surroundings-0.010
 bond-0.010
 ourselves-0.009
 themselves-0.009
 harmony-0.009
Token clothes
Token ID8242
Feature activation-3.80e-02

Pos logit contributions
br+0.001
 ow+0.001
zed+0.001
obb+0.001
bridge+0.001
Neg logit contributions
 surroundings-0.001
 bond-0.001
esty-0.001
 eyebrow-0.001
 Believe-0.001
Token were
Token ID547
Feature activation-1.19e-02

Pos logit contributions
 ow+0.058
br+0.058
zed+0.055
obb+0.054
aster+0.050
Neg logit contributions
 surroundings-0.058
 bond-0.055
 eyebrow-0.053
esty-0.052
 Believe-0.052
Token soaked
Token ID33657
Feature activation+5.27e-04

Pos logit contributions
br+0.019
 ow+0.018
zed+0.018
obb+0.017
itt+0.017
Neg logit contributions
 surroundings-0.017
 bond-0.016
 eyebrow-0.015
assion-0.015
 directions-0.014
Token through
Token ID832
Feature activation-2.42e-02

Pos logit contributions
 surroundings+0.001
 bond+0.001
 eyebrow+0.001
esty+0.001
 Believe+0.001
Neg logit contributions
 ow-0.001
br-0.001
zed-0.001
obb-0.001
bridge-0.001
Token.
Token ID13
Feature activation-1.13e-03

Pos logit contributions
br+0.039
obb+0.037
zed+0.037
 ow+0.036
oll+0.033
Neg logit contributions
 surroundings-0.037
 bond-0.034
 rhythms-0.032
 eyebrow-0.032
 Believe-0.031
Token Then
Token ID3244
Feature activation-5.53e-03

Pos logit contributions
 ow+0.002
br+0.002
zed+0.002
obb+0.002
bridge+0.002
Neg logit contributions
 surroundings-0.002
 bond-0.002
 eyebrow-0.002
 Believe-0.002
esty-0.002