TOP ACTIVATIONS
MAX = 3.362

were always so happy on Wed nes days because of their
them and never threw a tant rum again . <|endoftext|> Once
called Daisy . Daisy loved Wed nes days because on Wed
my . Tim my loved Wed nes days because that was
my . Tim my loved Wed nes days because that was
his feet and threw a tant rum . "
named Lily . She loved Wed nes days because that 's
didn 't do it on purpose . Maybe he was sick
Wed nes days because on Wed nes days she did something
a new found sense of purpose and pride .
did not do it on purpose . She wiped her tears
. As soon as the battery hit the ground it lit
to cry and threw a tant rum . She didn 't
car . " Mine !" Anna says .
Jimmy was always excited for Wed nes days because it was
hand . " Mine !" Tom says . He
yell . " Mine !" Ben says .
L ily didn 't like shampoo because it made her eyes
Why do you w ag your tail ?" Spot laughed and
kept crying and throwing a tant rum . Finally

MIN ACTIVATIONS
MIN = -4.391

loo and pretended to be Esk im os . After a
They made v room - v room noises as they moved
He made v room - v room noises and drove it
made a v room - v room sound and laughed .
loud noise . He sc run ched his eyes tightly and
and made v room - v room sounds . They laughed
He makes v room - v room sounds . Kim finds
They made v room - v room noises and pretended to
. It had some car v ings and letters on it
be cow boys and cow girls . They put on hats
They make v room - v room noises and pretend to
the park her " use ful - park ". <|endoftext|> Once
man was called a " v endor ". Tim my wanted
f enn el and an ise and car away and c
They make v room - v room noises and pretend to
and make v room - v room noises . One day
He made v room - v room noises and drove it
They called it a " v ac ation ". They packed
it go v room - v room . The truck loved
and made v room - v room noises .

INTERVAL 1.424 - 3.362
CONTAINS 0.395%

back to Mom my and Daddy and asked them if they
Look at the fire work .
joy because of the brilliant mirror . <|endoftext|> Once upon a
smiled and said , " Hello , kids . This bike
being kind and sharing the diamond with them . From then

INTERVAL -0.514 - 1.424
CONTAINS 86.115%

was cozy once again . <|endoftext|> Once upon a time there
coat . It is rough and sc aly . He says
cleaning a wound can help make it better , but sometimes
scared . Sam saw Tim and ran to get help .
So , she opened her hands and the butterfly flew away

INTERVAL -2.453 - -0.514
CONTAINS 13.485%

no ! What did you do ? You should not play
than being strong . <|endoftext|> Tom and Anna were twins ,
lovely yell ows , so she opened her window . But
fun to do things all by yourself , it is always
share , instead of always being nos y and wanting to

INTERVAL -4.391 - -2.453
CONTAINS 0.005%

castle that was one hundred inches high . She said her
. Grand ma shows them how to pick the ripe ones
bird fly from the chim ney ." L ily
He imagined he was a brave warrior with a big spear
thing . She shouted " v room v room " and
Token were
Token ID547
Feature activation+9.51e-02

Pos logit contributions
aman+0.018
pp+0.016
al+0.014
OO+0.014
 cash+0.013
Neg logit contributions
 brothers-0.011
 friends-0.011
 importantly-0.010
 villains-0.009
 families-0.009
Token always
Token ID1464
Feature activation+2.38e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
 cash+0.004
oph+0.004
Neg logit contributions
 villains-0.004
 brothers-0.004
 importantly-0.004
neys-0.003
ooters-0.003
Token so
Token ID523
Feature activation-2.67e-01

Pos logit contributions
aman+0.015
pp+0.014
al+0.013
OO+0.012
 cash+0.012
Neg logit contributions
 brothers-0.009
 importantly-0.008
 villains-0.008
 friends-0.008
neys-0.008
Token happy
Token ID3772
Feature activation+3.20e-01

Pos logit contributions
 brothers+0.009
 villains+0.008
 importantly+0.008
 friends+0.007
ooters+0.007
Neg logit contributions
aman-0.018
pp-0.017
al-0.015
 cash-0.014
OO-0.014
Token on
Token ID319
Feature activation+1.23e+00

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
OO+0.012
 cash+0.011
Neg logit contributions
 brothers-0.016
 importantly-0.015
 villains-0.015
 friends-0.015
ooters-0.014
Token Wed
Token ID3300
Feature activation+3.35e+00

Pos logit contributions
aman+0.067
pp+0.054
al+0.051
 cash+0.046
OO+0.046
Neg logit contributions
 brothers-0.062
 importantly-0.059
 friends-0.059
 villains-0.058
neys-0.055
Tokennes
Token ID2516
Feature activation-3.24e-02

Pos logit contributions
aman+0.234
pp+0.206
al+0.193
OO+0.184
 cash+0.183
Neg logit contributions
 brothers-0.124
 friends-0.118
 importantly-0.113
 villains-0.106
 families-0.098
Tokendays
Token ID12545
Feature activation+9.25e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.002
OO-0.002
 generation-0.001
Token because
Token ID780
Feature activation+6.78e-01

Pos logit contributions
aman+0.057
pp+0.051
al+0.046
OO+0.044
 cash+0.043
Neg logit contributions
 brothers-0.042
 friends-0.040
 importantly-0.038
 villains-0.035
 families-0.034
Token of
Token ID286
Feature activation-6.77e-02

Pos logit contributions
aman+0.037
pp+0.031
al+0.029
 generation+0.027
 one+0.027
Neg logit contributions
 brothers-0.030
 villains-0.029
neys-0.028
 friends-0.028
 importantly-0.027
Token their
Token ID511
Feature activation+6.29e-01

Pos logit contributions
 brothers+0.003
 importantly+0.003
 friends+0.003
 villains+0.003
neys+0.003
Neg logit contributions
aman-0.004
pp-0.003
al-0.003
 cash-0.003
 generation-0.003
Token them
Token ID606
Feature activation-7.77e-01

Pos logit contributions
 brothers+0.040
 friends+0.040
 importantly+0.036
 families+0.033
 villains+0.033
Neg logit contributions
aman-0.050
pp-0.044
al-0.039
OO-0.038
 cash-0.037
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
 brothers+0.034
 friends+0.033
 importantly+0.031
 villains+0.028
 families+0.027
Neg logit contributions
aman-0.049
pp-0.044
al-0.040
OO-0.038
 cash-0.038
Token never
Token ID1239
Feature activation-5.43e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token threw
Token ID9617
Feature activation+6.69e-01

Pos logit contributions
 brothers+0.025
 friends+0.024
 importantly+0.022
 villains+0.021
 families+0.020
Neg logit contributions
aman-0.034
pp-0.030
al-0.027
OO-0.026
 cash-0.026
Token a
Token ID257
Feature activation+9.08e-01

Pos logit contributions
aman+0.041
pp+0.036
OO+0.032
al+0.030
oph+0.030
Neg logit contributions
 friends-0.033
 brothers-0.031
 importantly-0.027
 families-0.027
 exciting-0.027
Token tant
Token ID24246
Feature activation+3.24e+00

Pos logit contributions
aman+0.055
pp+0.047
al+0.043
OO+0.041
 cash+0.040
Neg logit contributions
 friends-0.044
 brothers-0.042
 importantly-0.038
 villains-0.037
 exciting-0.036
Tokenrum
Token ID6582
Feature activation-4.49e-01

Pos logit contributions
aman+0.252
pp+0.221
al+0.208
 cash+0.205
OO+0.199
Neg logit contributions
 brothers-0.099
 friends-0.096
 importantly-0.085
 villains-0.077
 families-0.070
Token again
Token ID757
Feature activation-1.28e-01

Pos logit contributions
 brothers+0.018
 friends+0.018
 importantly+0.016
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.030
pp-0.027
al-0.024
OO-0.024
 cash-0.023
Token.
Token ID13
Feature activation-2.62e-02

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.005
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.008
pp-0.008
al-0.007
OO-0.007
 cash-0.007
Token<|endoftext|>
Token ID50256
Feature activation+2.19e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.002
OO-0.002
 cash-0.002
TokenOnce
Token ID7454
Feature activation+1.76e-01

Pos logit contributions
aman+0.011
pp+0.009
al+0.009
ara+0.008
OO+0.008
Neg logit contributions
 brothers-0.011
 importantly-0.011
 villains-0.011
 friends-0.011
 families-0.010
Token called
Token ID1444
Feature activation-4.23e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
OO-0.001
al-0.001
 cash-0.001
Token Daisy
Token ID40355
Feature activation-8.47e-01

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.011
 families+0.010
Neg logit contributions
aman-0.032
pp-0.029
al-0.026
OO-0.026
 cash-0.025
Token.
Token ID13
Feature activation+8.43e-02

Pos logit contributions
 brothers+0.032
 friends+0.032
 importantly+0.028
 villains+0.025
 families+0.025
Neg logit contributions
aman-0.060
pp-0.053
al-0.048
 cash-0.047
OO-0.047
Token Daisy
Token ID40355
Feature activation-1.41e-01

Pos logit contributions
aman+0.004
pp+0.003
al+0.003
oph+0.003
OO+0.002
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.005
 villains-0.005
neys-0.005
Token loved
Token ID6151
Feature activation+1.04e+00

Pos logit contributions
 brothers+0.006
 importantly+0.006
 friends+0.006
 villains+0.006
ooters+0.005
Neg logit contributions
aman-0.008
pp-0.007
al-0.007
OO-0.006
 cash-0.006
Token Wed
Token ID3300
Feature activation+3.12e+00

Pos logit contributions
aman+0.059
pp+0.050
 cash+0.047
al+0.046
OO+0.043
Neg logit contributions
 brothers-0.049
 importantly-0.048
 friends-0.045
 villains-0.044
neys-0.041
Tokennes
Token ID2516
Feature activation-4.68e-02

Pos logit contributions
aman+0.220
pp+0.190
al+0.181
OO+0.174
 cash+0.170
Neg logit contributions
 brothers-0.113
 friends-0.107
 importantly-0.103
 villains-0.097
 exciting-0.090
Tokendays
Token ID12545
Feature activation+4.28e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.002
 families+0.002
Neg logit contributions
aman-0.003
pp-0.003
al-0.002
OO-0.002
 cash-0.002
Token because
Token ID780
Feature activation+2.01e-01

Pos logit contributions
aman+0.029
pp+0.026
al+0.023
OO+0.023
 cash+0.022
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.016
 exciting-0.014
 villains-0.014
Token on
Token ID319
Feature activation-3.00e-02

Pos logit contributions
aman+0.008
pp+0.006
 one+0.006
al+0.006
 cash+0.005
Neg logit contributions
 brothers-0.012
 villains-0.012
neys-0.012
girls-0.011
 friends-0.011
Token Wed
Token ID3300
Feature activation+2.78e+00

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.001
 families+0.001
 exciting+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.001
OO-0.001
 cash-0.001
Tokenmy
Token ID1820
Feature activation-3.92e-01

Pos logit contributions
 brothers+0.058
 friends+0.055
 importantly+0.050
 villains+0.046
 families+0.045
Neg logit contributions
aman-0.082
pp-0.072
al-0.066
 cash-0.063
OO-0.063
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
 brothers+0.016
 friends+0.015
 importantly+0.014
 villains+0.013
 families+0.012
Neg logit contributions
aman-0.027
pp-0.024
al-0.022
OO-0.021
 cash-0.021
Token Tim
Token ID5045
Feature activation-6.11e-01

Pos logit contributions
aman+0.010
pp+0.008
OO+0.008
ah+0.008
al+0.007
Neg logit contributions
 friends-0.010
 importantly-0.010
 villains-0.010
 families-0.010
 brothers-0.010
Tokenmy
Token ID1820
Feature activation+1.89e-01

Pos logit contributions
 importantly+0.041
 brothers+0.039
 friends+0.038
 villains+0.038
ooters+0.036
Neg logit contributions
aman-0.022
pp-0.019
al-0.017
OO-0.015
y-0.014
Token loved
Token ID6151
Feature activation+1.05e+00

Pos logit contributions
aman+0.010
pp+0.009
al+0.008
OO+0.008
lder+0.007
Neg logit contributions
 importantly-0.009
 brothers-0.009
 friends-0.008
 villains-0.008
 pals-0.008
Token Wed
Token ID3300
Feature activation+3.07e+00

Pos logit contributions
aman+0.051
 cash+0.042
pp+0.042
al+0.038
 heaven+0.036
Neg logit contributions
 importantly-0.055
 brothers-0.053
 villains-0.049
 friends-0.048
neys-0.047
Tokennes
Token ID2516
Feature activation-3.74e-02

Pos logit contributions
aman+0.189
pp+0.171
al+0.153
OO+0.146
 cash+0.145
Neg logit contributions
 brothers-0.138
 friends-0.133
 importantly-0.125
 villains-0.115
 families-0.112
Tokendays
Token ID12545
Feature activation+5.26e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.002
OO-0.002
 cash-0.002
Token because
Token ID780
Feature activation+2.02e-01

Pos logit contributions
aman+0.034
pp+0.030
al+0.027
OO+0.026
 cash+0.026
Neg logit contributions
 brothers-0.023
 friends-0.022
 importantly-0.021
 villains-0.019
 families-0.018
Token that
Token ID326
Feature activation-1.50e-01

Pos logit contributions
aman+0.010
pp+0.009
 one+0.008
 cash+0.008
al+0.008
Neg logit contributions
 brothers-0.009
neys-0.009
 friends-0.009
 villains-0.009
 importantly-0.009
Token was
Token ID373
Feature activation+2.85e-01

Pos logit contributions
 importantly+0.007
 brothers+0.007
neys+0.006
 friends+0.006
 pals+0.006
Neg logit contributions
aman-0.007
pp-0.007
 cash-0.006
 one-0.006
al-0.006
Tokenmy
Token ID1820
Feature activation-4.44e-01

Pos logit contributions
 brothers+0.079
 friends+0.076
 importantly+0.071
 villains+0.067
 families+0.066
Neg logit contributions
aman-0.070
pp-0.060
al-0.053
OO-0.050
 cash-0.049
Token.
Token ID13
Feature activation+1.98e-01

Pos logit contributions
 brothers+0.019
 friends+0.018
 importantly+0.017
 villains+0.016
 families+0.015
Neg logit contributions
aman-0.029
pp-0.026
al-0.024
OO-0.023
 cash-0.022
Token Tim
Token ID5045
Feature activation-6.82e-01

Pos logit contributions
aman+0.011
pp+0.009
OO+0.008
ah+0.008
 cash+0.008
Neg logit contributions
 friends-0.009
 importantly-0.009
 villains-0.009
 brothers-0.009
 families-0.008
Tokenmy
Token ID1820
Feature activation+1.68e-01

Pos logit contributions
 importantly+0.049
 villains+0.047
 brothers+0.047
 friends+0.046
 families+0.044
Neg logit contributions
aman-0.022
pp-0.018
al-0.015
OO-0.013
y-0.013
Token loved
Token ID6151
Feature activation+1.01e+00

Pos logit contributions
aman+0.008
pp+0.008
al+0.007
OO+0.007
y+0.007
Neg logit contributions
 importantly-0.008
 brothers-0.008
 friends-0.008
 villains-0.007
 pals-0.007
Token Wed
Token ID3300
Feature activation+3.04e+00

Pos logit contributions
aman+0.052
pp+0.042
 cash+0.042
al+0.038
OO+0.036
Neg logit contributions
 importantly-0.051
 brothers-0.049
 villains-0.046
 friends-0.045
neys-0.044
Tokennes
Token ID2516
Feature activation-1.02e-01

Pos logit contributions
aman+0.198
pp+0.176
al+0.162
OO+0.154
 cash+0.152
Neg logit contributions
 brothers-0.127
 friends-0.121
 importantly-0.115
 villains-0.107
 families-0.102
Tokendays
Token ID12545
Feature activation+5.56e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.006
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token because
Token ID780
Feature activation+1.57e-01

Pos logit contributions
aman+0.035
pp+0.031
al+0.029
OO+0.027
 cash+0.027
Neg logit contributions
 brothers-0.025
 friends-0.023
 importantly-0.022
 villains-0.020
 families-0.020
Token that
Token ID326
Feature activation-2.15e-01

Pos logit contributions
aman+0.008
 one+0.006
pp+0.006
 cash+0.006
al+0.006
Neg logit contributions
neys-0.007
 brothers-0.007
 villains-0.007
girls-0.007
 importantly-0.007
Token was
Token ID373
Feature activation+2.61e-01

Pos logit contributions
 importantly+0.010
 brothers+0.009
neys+0.009
 friends+0.009
 pals+0.009
Neg logit contributions
aman-0.011
pp-0.009
 cash-0.009
 one-0.009
 salon-0.008
Token his
Token ID465
Feature activation+3.03e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.002
 families+0.002
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
OO-0.005
 cash-0.005
Token feet
Token ID3625
Feature activation-5.97e-01

Pos logit contributions
aman+0.018
pp+0.015
al+0.014
OO+0.014
 cash+0.014
Neg logit contributions
 importantly-0.013
 brothers-0.013
 friends-0.012
 villains-0.012
neys-0.012
Token and
Token ID290
Feature activation+2.40e-01

Pos logit contributions
 brothers+0.020
 friends+0.020
 importantly+0.015
 having+0.015
 exciting+0.015
Neg logit contributions
aman-0.044
pp-0.040
al-0.037
oph-0.037
OO-0.036
Token threw
Token ID9617
Feature activation+4.75e-01

Pos logit contributions
aman+0.017
pp+0.016
al+0.014
OO+0.014
oph+0.014
Neg logit contributions
 brothers-0.009
 friends-0.009
 importantly-0.008
 villains-0.007
 families-0.007
Token a
Token ID257
Feature activation+4.35e-01

Pos logit contributions
aman+0.035
pp+0.033
OO+0.028
oph+0.028
al+0.027
Neg logit contributions
 friends-0.018
 brothers-0.018
 boys-0.014
 exciting-0.014
 kids-0.013
Token tant
Token ID24246
Feature activation+2.93e+00

Pos logit contributions
aman+0.029
pp+0.026
al+0.024
 generation+0.022
OO+0.022
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.015
 villains-0.014
 exciting-0.013
Tokenrum
Token ID6582
Feature activation-8.08e-01

Pos logit contributions
aman+0.222
pp+0.197
al+0.184
 cash+0.178
OO+0.176
Neg logit contributions
 brothers-0.094
 friends-0.088
 importantly-0.081
 villains-0.074
 families-0.067
Token.
Token ID13
Feature activation-4.23e-02

Pos logit contributions
 brothers+0.033
 friends+0.032
 importantly+0.029
 villains+0.027
 families+0.025
Neg logit contributions
aman-0.055
pp-0.049
al-0.044
 cash-0.042
OO-0.042
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.003
pp-0.003
al-0.003
OO-0.002
 cash-0.002
Token
Token ID198
Feature activation+5.83e-02

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token"
Token ID1
Feature activation+6.31e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.003
OO+0.003
 cash+0.002
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.003
 villains-0.003
 families-0.002
Token named
Token ID3706
Feature activation-4.00e-01

Pos logit contributions
 brothers+0.000
 friends+0.000
 importantly+0.000
 villains+0.000
 families+0.000
Neg logit contributions
aman-0.000
pp-0.000
OO-0.000
al-0.000
oph-0.000
Token Lily
Token ID20037
Feature activation-2.18e-01

Pos logit contributions
 friends+0.015
 brothers+0.015
 importantly+0.014
 exciting+0.012
 families+0.012
Neg logit contributions
aman-0.028
pp-0.025
al-0.023
OO-0.022
 cash-0.021
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
 brothers+0.008
 friends+0.008
 importantly+0.007
 villains+0.006
 exciting+0.006
Neg logit contributions
aman-0.016
pp-0.014
al-0.013
OO-0.012
 cash-0.012
Token She
Token ID1375
Feature activation+6.86e-02

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.007
 friends-0.006
 importantly-0.006
 villains-0.006
 families-0.006
Token loved
Token ID6151
Feature activation+8.23e-01

Pos logit contributions
aman+0.004
pp+0.004
al+0.003
OO+0.003
 cash+0.003
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.003
 families-0.003
neys-0.002
Token Wed
Token ID3300
Feature activation+2.87e+00

Pos logit contributions
aman+0.047
pp+0.040
 cash+0.037
al+0.037
OO+0.034
Neg logit contributions
 brothers-0.039
 importantly-0.038
 friends-0.035
 villains-0.034
neys-0.033
Tokennes
Token ID2516
Feature activation-2.78e-01

Pos logit contributions
aman+0.205
pp+0.175
al+0.170
OO+0.162
 cash+0.158
Neg logit contributions
 brothers-0.100
 friends-0.096
 importantly-0.093
 villains-0.088
 exciting-0.081
Tokendays
Token ID12545
Feature activation+3.23e-01

Pos logit contributions
 brothers+0.011
 friends+0.010
 importantly+0.010
 villains+0.009
 families+0.009
Neg logit contributions
aman-0.019
pp-0.017
al-0.016
OO-0.015
 cash-0.015
Token because
Token ID780
Feature activation+8.40e-02

Pos logit contributions
aman+0.021
pp+0.019
al+0.017
OO+0.017
 cash+0.016
Neg logit contributions
 brothers-0.013
 friends-0.013
 importantly-0.012
 exciting-0.011
 villains-0.010
Token that
Token ID326
Feature activation-3.82e-01

Pos logit contributions
aman+0.004
pp+0.003
al+0.003
 cash+0.003
 salon+0.002
Neg logit contributions
 brothers-0.005
 friends-0.004
 villains-0.004
 importantly-0.004
neys-0.004
Token's
Token ID338
Feature activation+5.23e-01

Pos logit contributions
 brothers+0.021
 importantly+0.020
 friends+0.020
 villains+0.019
neys+0.018
Neg logit contributions
aman-0.018
pp-0.016
 cash-0.014
al-0.014
 heaven-0.012
Token didn
Token ID1422
Feature activation-2.42e-01

Pos logit contributions
 brothers+0.057
 friends+0.055
 importantly+0.049
 villains+0.047
 families+0.045
Neg logit contributions
aman-0.086
pp-0.075
al-0.068
OO-0.066
 cash-0.066
Token't
Token ID470
Feature activation-8.35e-02

Pos logit contributions
 brothers+0.013
 friends+0.012
 importantly+0.012
 villains+0.011
 families+0.010
Neg logit contributions
aman-0.013
pp-0.012
al-0.010
OO-0.010
 cash-0.010
Token do
Token ID466
Feature activation-8.57e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
 friends+0.004
 villains+0.003
neys+0.003
Neg logit contributions
aman-0.005
pp-0.004
al-0.004
OO-0.004
 cash-0.004
Token it
Token ID340
Feature activation+1.72e+00

Pos logit contributions
 brothers+0.037
 friends+0.037
 importantly+0.032
 villains+0.032
 exciting+0.029
Neg logit contributions
aman-0.058
pp-0.051
al-0.046
OO-0.044
oph-0.043
Token on
Token ID319
Feature activation+6.62e-01

Pos logit contributions
aman+0.112
pp+0.098
al+0.090
 cash+0.085
OO+0.083
Neg logit contributions
 brothers-0.076
 friends-0.076
 importantly-0.064
 villains-0.063
 exciting-0.061
Token purpose
Token ID4007
Feature activation+2.82e+00

Pos logit contributions
pp+0.043
aman+0.043
al+0.036
OO+0.035
ited+0.033
Neg logit contributions
 friends-0.029
 brothers-0.028
 families-0.022
 exciting-0.022
 kids-0.022
Token.
Token ID13
Feature activation+2.01e-01

Pos logit contributions
aman+0.157
pp+0.138
al+0.127
OO+0.117
 cash+0.116
Neg logit contributions
 brothers-0.139
 friends-0.131
 importantly-0.129
 villains-0.121
 families-0.115
Token Maybe
Token ID6674
Feature activation-2.54e-01

Pos logit contributions
aman+0.012
pp+0.010
al+0.009
 cash+0.009
OO+0.009
Neg logit contributions
 friends-0.009
 brothers-0.009
 importantly-0.008
 exciting-0.008
 families-0.008
Token he
Token ID339
Feature activation-4.05e-01

Pos logit contributions
 brothers+0.010
 friends+0.010
 importantly+0.009
 villains+0.009
 families+0.008
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
 cash-0.013
OO-0.013
Token was
Token ID373
Feature activation-2.96e-01

Pos logit contributions
 brothers+0.017
 friends+0.016
 importantly+0.015
 villains+0.014
 families+0.014
Neg logit contributions
aman-0.027
pp-0.024
al-0.021
OO-0.021
 cash-0.021
Token sick
Token ID6639
Feature activation-2.56e-01

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.011
 villains+0.011
 exciting+0.010
Neg logit contributions
aman-0.020
pp-0.018
al-0.016
OO-0.015
 cash-0.015
Token Wed
Token ID3300
Feature activation+3.12e+00

Pos logit contributions
aman+0.059
pp+0.050
 cash+0.047
al+0.046
OO+0.043
Neg logit contributions
 brothers-0.049
 importantly-0.048
 friends-0.045
 villains-0.044
neys-0.041
Tokennes
Token ID2516
Feature activation-4.68e-02

Pos logit contributions
aman+0.220
pp+0.190
al+0.181
OO+0.174
 cash+0.170
Neg logit contributions
 brothers-0.113
 friends-0.107
 importantly-0.103
 villains-0.097
 exciting-0.090
Tokendays
Token ID12545
Feature activation+4.28e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.002
 families+0.002
Neg logit contributions
aman-0.003
pp-0.003
al-0.002
OO-0.002
 cash-0.002
Token because
Token ID780
Feature activation+2.01e-01

Pos logit contributions
aman+0.029
pp+0.026
al+0.023
OO+0.023
 cash+0.022
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.016
 exciting-0.014
 villains-0.014
Token on
Token ID319
Feature activation-3.00e-02

Pos logit contributions
aman+0.008
pp+0.006
 one+0.006
al+0.006
 cash+0.005
Neg logit contributions
 brothers-0.012
 villains-0.012
neys-0.012
girls-0.011
 friends-0.011
Token Wed
Token ID3300
Feature activation+2.78e+00

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.001
 families+0.001
 exciting+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.001
OO-0.001
 cash-0.001
Tokennes
Token ID2516
Feature activation-3.97e-01

Pos logit contributions
aman+0.207
pp+0.182
al+0.174
OO+0.167
 cash+0.166
Neg logit contributions
 brothers-0.086
 friends-0.082
 importantly-0.080
 villains-0.079
 exciting-0.069
Tokendays
Token ID12545
Feature activation+2.18e-01

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.013
 villains+0.012
 families+0.012
Neg logit contributions
aman-0.027
pp-0.024
al-0.023
 cash-0.022
OO-0.022
Token she
Token ID673
Feature activation-1.67e-02

Pos logit contributions
aman+0.014
pp+0.013
al+0.012
OO+0.011
 cash+0.011
Neg logit contributions
 brothers-0.009
 friends-0.009
 importantly-0.008
 villains-0.008
 families-0.007
Token did
Token ID750
Feature activation-7.31e-01

Pos logit contributions
 brothers+0.001
 importantly+0.001
 friends+0.001
 villains+0.001
ooters+0.001
Neg logit contributions
aman-0.001
pp-0.001
al-0.001
OO-0.001
 cash-0.001
Token something
Token ID1223
Feature activation+6.36e-01

Pos logit contributions
 brothers+0.029
 friends+0.028
 importantly+0.026
 villains+0.024
 families+0.023
Neg logit contributions
aman-0.050
pp-0.045
al-0.041
OO-0.039
 cash-0.038
Token a
Token ID257
Feature activation+6.66e-01

Pos logit contributions
aman+0.018
pp+0.016
al+0.015
OO+0.014
 cash+0.013
Neg logit contributions
 brothers-0.016
 friends-0.015
 importantly-0.015
 villains-0.014
 families-0.013
Token new
Token ID649
Feature activation-3.20e-01

Pos logit contributions
aman+0.044
pp+0.040
al+0.036
OO+0.035
 cash+0.034
Neg logit contributions
 brothers-0.027
 friends-0.026
 importantly-0.024
 villains-0.023
 families-0.022
Token found
Token ID1043
Feature activation-1.24e-01

Pos logit contributions
 friends+0.014
 brothers+0.013
 importantly+0.012
 exciting+0.011
 families+0.011
Neg logit contributions
aman-0.021
pp-0.019
al-0.017
 cash-0.016
OO-0.016
Token sense
Token ID2565
Feature activation-3.88e-02

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.008
pp-0.008
OO-0.007
al-0.007
 cash-0.006
Token of
Token ID286
Feature activation+2.54e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.003
pp-0.003
al-0.003
OO-0.003
 cash-0.003
Token purpose
Token ID4007
Feature activation+2.78e+00

Pos logit contributions
aman+0.017
pp+0.014
al+0.014
 cash+0.014
 generation+0.013
Neg logit contributions
 brothers-0.010
 friends-0.009
 importantly-0.008
 villains-0.008
neys-0.008
Token and
Token ID290
Feature activation+2.26e-01

Pos logit contributions
aman+0.128
pp+0.114
al+0.110
 cash+0.094
y+0.090
Neg logit contributions
 brothers-0.141
 villains-0.137
 friends-0.132
 importantly-0.132
ooters-0.129
Token pride
Token ID11293
Feature activation+1.06e+00

Pos logit contributions
aman+0.014
pp+0.012
al+0.011
 cash+0.011
OO+0.010
Neg logit contributions
 brothers-0.009
 importantly-0.009
 friends-0.009
 villains-0.008
neys-0.008
Token.
Token ID13
Feature activation+3.96e-02

Pos logit contributions
aman+0.070
pp+0.061
al+0.056
OO+0.055
 cash+0.054
Neg logit contributions
 brothers-0.045
 friends-0.044
 importantly-0.041
 villains-0.036
 families-0.036
Token
Token ID198
Feature activation-6.14e-02

Pos logit contributions
aman+0.003
pp+0.002
al+0.002
OO+0.002
 cash+0.002
Neg logit contributions
 brothers-0.002
 friends-0.002
 importantly-0.002
 villains-0.001
 families-0.001
Token
Token ID198
Feature activation+4.48e-02

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.002
 families+0.002
Neg logit contributions
aman-0.004
pp-0.003
al-0.003
OO-0.003
oph-0.003
Token did
Token ID750
Feature activation-6.43e-01

Pos logit contributions
 brothers+0.022
 importantly+0.021
 friends+0.021
 villains+0.019
ooters+0.019
Neg logit contributions
aman-0.027
pp-0.025
al-0.024
OO-0.021
 cash-0.021
Token not
Token ID407
Feature activation-1.82e-01

Pos logit contributions
 friends+0.024
 brothers+0.023
 importantly+0.020
 villains+0.019
 exciting+0.019
Neg logit contributions
aman-0.048
pp-0.043
al-0.039
OO-0.037
oph-0.037
Token do
Token ID466
Feature activation-9.08e-01

Pos logit contributions
 brothers+0.008
 friends+0.008
 importantly+0.008
 villains+0.007
 families+0.007
Neg logit contributions
aman-0.011
pp-0.010
al-0.009
OO-0.009
 cash-0.008
Token it
Token ID340
Feature activation+1.64e+00

Pos logit contributions
 brothers+0.046
 friends+0.045
 importantly+0.042
 villains+0.039
 exciting+0.038
Neg logit contributions
aman-0.054
pp-0.047
al-0.041
OO-0.040
 cash-0.038
Token on
Token ID319
Feature activation+5.29e-01

Pos logit contributions
aman+0.107
pp+0.094
al+0.086
OO+0.081
 cash+0.081
Neg logit contributions
 brothers-0.072
 friends-0.070
 importantly-0.063
 villains-0.059
 families-0.057
Token purpose
Token ID4007
Feature activation+2.73e+00

Pos logit contributions
aman+0.031
pp+0.029
al+0.025
OO+0.024
oph+0.022
Neg logit contributions
 brothers-0.027
 friends-0.027
 importantly-0.023
 villains-0.023
 families-0.022
Token.
Token ID13
Feature activation+1.67e-01

Pos logit contributions
aman+0.141
pp+0.125
al+0.118
 cash+0.109
OO+0.104
Neg logit contributions
 brothers-0.136
 friends-0.127
 importantly-0.125
 villains-0.120
 families-0.114
Token She
Token ID1375
Feature activation-7.75e-02

Pos logit contributions
aman+0.010
pp+0.009
al+0.008
OO+0.007
 cash+0.007
Neg logit contributions
 brothers-0.009
 friends-0.008
 importantly-0.008
 villains-0.007
 families-0.007
Token wiped
Token ID21122
Feature activation-5.99e-01

Pos logit contributions
 brothers+0.003
 friends+0.003
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.005
al-0.004
OO-0.004
 cash-0.004
Token her
Token ID607
Feature activation-1.13e-01

Pos logit contributions
 brothers+0.027
 friends+0.027
 importantly+0.021
 exciting+0.020
 boys+0.020
Neg logit contributions
aman-0.039
pp-0.037
OO-0.032
al-0.030
lder-0.029
Token tears
Token ID10953
Feature activation-5.71e-02

Pos logit contributions
 brothers+0.005
 importantly+0.005
 friends+0.004
 villains+0.004
neys+0.004
Neg logit contributions
aman-0.007
pp-0.006
al-0.006
 cash-0.006
OO-0.005
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
aman+0.061
pp+0.055
al+0.050
 cash+0.050
OO+0.048
Neg logit contributions
 brothers-0.032
 friends-0.032
 importantly-0.029
 villains-0.026
 exciting-0.025
Token As
Token ID1081
Feature activation+8.96e-01

Pos logit contributions
aman+0.014
pp+0.012
al+0.011
OO+0.011
 cash+0.010
Neg logit contributions
 brothers-0.010
 friends-0.010
 importantly-0.009
 villains-0.008
 families-0.008
Token soon
Token ID2582
Feature activation+5.30e-01

Pos logit contributions
aman+0.047
pp+0.035
al+0.034
 one+0.033
 cash+0.033
Neg logit contributions
 brothers-0.044
ooters-0.042
 importantly-0.042
neys-0.041
 villains-0.041
Token as
Token ID355
Feature activation+3.47e-01

Pos logit contributions
aman+0.025
pp+0.021
al+0.019
OO+0.017
 cash+0.017
Neg logit contributions
 brothers-0.032
 friends-0.030
 importantly-0.029
 villains-0.028
 families-0.027
Token the
Token ID262
Feature activation+8.58e-01

Pos logit contributions
aman+0.013
 one+0.011
al+0.010
pp+0.010
 cash+0.009
Neg logit contributions
ooters-0.020
neys-0.019
 importantly-0.018
 villains-0.018
 brothers-0.018
Token battery
Token ID6555
Feature activation+2.71e+00

Pos logit contributions
 cash+0.032
 one+0.030
aman+0.030
al+0.025
 generation+0.021
Neg logit contributions
neys-0.048
ooters-0.046
girls-0.044
 importantly-0.044
adows-0.042
Token hit
Token ID2277
Feature activation+1.29e+00

Pos logit contributions
aman+0.150
pp+0.130
al+0.119
OO+0.110
 cash+0.109
Neg logit contributions
 brothers-0.139
 friends-0.133
 importantly-0.130
 villains-0.121
 families-0.117
Token the
Token ID262
Feature activation-4.30e-01

Pos logit contributions
aman+0.090
pp+0.081
al+0.075
OO+0.071
 cash+0.071
Neg logit contributions
 brothers-0.048
 friends-0.046
 importantly-0.043
 villains-0.040
 families-0.037
Token ground
Token ID2323
Feature activation+1.24e-01

Pos logit contributions
 importantly+0.023
 brothers+0.022
 friends+0.021
ooters+0.021
neys+0.021
Neg logit contributions
aman-0.020
 cash-0.018
al-0.017
pp-0.016
OO-0.014
Token it
Token ID340
Feature activation-1.02e-01

Pos logit contributions
aman+0.008
pp+0.007
al+0.006
OO+0.006
 cash+0.006
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.005
 villains-0.005
 exciting-0.004
Token lit
Token ID6578
Feature activation+2.50e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.004
 villains+0.003
 exciting+0.003
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
 cash-0.005
OO-0.005
Token to
Token ID284
Feature activation+3.91e-01

Pos logit contributions
aman+0.030
pp+0.027
al+0.025
OO+0.023
 cash+0.023
Neg logit contributions
 brothers-0.016
 friends-0.016
 importantly-0.014
 villains-0.013
 families-0.013
Token cry
Token ID3960
Feature activation+8.40e-01

Pos logit contributions
aman+0.025
pp+0.023
al+0.021
OO+0.020
 cash+0.019
Neg logit contributions
 brothers-0.017
 friends-0.016
 importantly-0.015
 villains-0.014
 families-0.014
Token and
Token ID290
Feature activation+5.92e-01

Pos logit contributions
aman+0.065
pp+0.058
al+0.052
oph+0.050
use+0.050
Neg logit contributions
 friends-0.030
 brothers-0.030
 importantly-0.025
 having-0.021
 exciting-0.021
Token threw
Token ID9617
Feature activation+1.14e+00

Pos logit contributions
aman+0.039
pp+0.036
al+0.032
OO+0.031
oph+0.029
Neg logit contributions
 friends-0.027
 brothers-0.026
 importantly-0.022
 exciting-0.022
 villains-0.021
Token a
Token ID257
Feature activation+9.24e-01

Pos logit contributions
aman+0.064
pp+0.056
OO+0.047
al+0.046
oph+0.044
Neg logit contributions
 friends-0.062
 brothers-0.062
 importantly-0.054
 exciting-0.053
 villains-0.052
Token tant
Token ID24246
Feature activation+2.66e+00

Pos logit contributions
aman+0.057
pp+0.050
al+0.045
OO+0.042
oph+0.042
Neg logit contributions
 friends-0.043
 brothers-0.043
 importantly-0.039
 villains-0.037
 exciting-0.036
Tokenrum
Token ID6582
Feature activation-5.96e-01

Pos logit contributions
aman+0.202
pp+0.176
al+0.163
 cash+0.161
OO+0.157
Neg logit contributions
 brothers-0.088
 friends-0.082
 importantly-0.077
 villains-0.069
 families-0.062
Token.
Token ID13
Feature activation+2.82e-01

Pos logit contributions
 brothers+0.024
 friends+0.023
 importantly+0.021
 villains+0.019
 families+0.018
Neg logit contributions
aman-0.041
pp-0.037
al-0.033
OO-0.031
 cash-0.031
Token She
Token ID1375
Feature activation-2.44e-02

Pos logit contributions
aman+0.017
pp+0.016
al+0.014
use+0.013
ited+0.012
Neg logit contributions
 brothers-0.013
 friends-0.013
 importantly-0.012
 villains-0.011
 exciting-0.011
Token didn
Token ID1422
Feature activation+6.83e-02

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.001
pp-0.001
al-0.001
OO-0.001
 cash-0.001
Token't
Token ID470
Feature activation+3.52e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.003
OO+0.002
 cash+0.002
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.004
 villains-0.003
 families-0.003
Token car
Token ID1097
Feature activation+9.58e-01

Pos logit contributions
aman+0.010
pp+0.009
al+0.008
OO+0.008
oph+0.008
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.007
 villains-0.007
 families-0.006
Token.
Token ID13
Feature activation-5.10e-01

Pos logit contributions
aman+0.065
pp+0.058
al+0.053
OO+0.051
oph+0.050
Neg logit contributions
 brothers-0.039
 friends-0.037
 importantly-0.033
 villains-0.032
 exciting-0.030
Token
Token ID198
Feature activation-2.52e-01

Pos logit contributions
 brothers+0.020
 friends+0.019
 importantly+0.018
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.034
pp-0.031
al-0.028
OO-0.027
 cash-0.027
Token
Token ID198
Feature activation-3.01e-02

Pos logit contributions
 brothers+0.011
 friends+0.010
 importantly+0.010
 villains+0.010
 families+0.009
Neg logit contributions
aman-0.016
pp-0.013
al-0.012
OO-0.012
ara-0.012
Token"
Token ID1
Feature activation+8.20e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.001
OO-0.001
 cash-0.001
TokenMine
Token ID24461
Feature activation+2.62e+00

Pos logit contributions
aman+0.042
pp+0.038
al+0.031
OO+0.030
 cash+0.028
Neg logit contributions
 brothers-0.046
 friends-0.044
 villains-0.042
 importantly-0.042
 families-0.040
Token!"
Token ID2474
Feature activation+4.53e-01

Pos logit contributions
aman+0.185
pp+0.163
al+0.150
 cash+0.142
 generation+0.140
Neg logit contributions
 brothers-0.102
 friends-0.101
 importantly-0.085
 villains-0.081
 exciting-0.079
Token Anna
Token ID11735
Feature activation+2.86e-01

Pos logit contributions
aman+0.030
pp+0.028
al+0.024
OO+0.024
 cash+0.022
Neg logit contributions
 brothers-0.019
 friends-0.019
 importantly-0.017
 villains-0.016
 families-0.015
Token says
Token ID1139
Feature activation+3.05e-01

Pos logit contributions
aman+0.018
pp+0.016
al+0.015
OO+0.014
 cash+0.014
Neg logit contributions
 brothers-0.013
 friends-0.012
 importantly-0.011
 villains-0.011
 families-0.010
Token.
Token ID13
Feature activation-1.73e-01

Pos logit contributions
aman+0.019
pp+0.017
al+0.015
OO+0.015
 cash+0.014
Neg logit contributions
 brothers-0.014
 friends-0.013
 importantly-0.012
 villains-0.012
 families-0.011
Token
Token ID198
Feature activation+3.96e-02

Pos logit contributions
 brothers+0.007
 friends+0.007
 importantly+0.006
 villains+0.006
 families+0.006
Neg logit contributions
aman-0.011
pp-0.011
al-0.009
OO-0.009
ited-0.008
TokenJimmy
Token ID40335
Feature activation+1.17e-01

Pos logit contributions
aman+0.005
pp+0.004
al+0.004
OO+0.003
ara+0.003
Neg logit contributions
 brothers-0.006
 friends-0.006
 importantly-0.006
 villains-0.006
 exciting-0.006
Token was
Token ID373
Feature activation-1.27e-01

Pos logit contributions
aman+0.008
pp+0.008
 cash+0.007
OO+0.007
al+0.007
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.003
 families-0.003
 exciting-0.003
Token always
Token ID1464
Feature activation-7.63e-02

Pos logit contributions
 brothers+0.005
 friends+0.004
 importantly+0.004
 having+0.003
 exciting+0.003
Neg logit contributions
aman-0.009
pp-0.009
al-0.008
OO-0.008
oph-0.008
Token excited
Token ID6568
Feature activation+3.21e-01

Pos logit contributions
 brothers+0.003
 friends+0.003
 importantly+0.002
 exciting+0.002
 villains+0.002
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
OO-0.004
 cash-0.004
Token for
Token ID329
Feature activation+1.06e-01

Pos logit contributions
aman+0.022
pp+0.020
al+0.018
OO+0.017
 cash+0.017
Neg logit contributions
 brothers-0.013
 friends-0.012
 importantly-0.011
 exciting-0.010
 families-0.010
Token Wed
Token ID3300
Feature activation+2.62e+00

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
 cash+0.005
 generation+0.004
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.005
 villains-0.005
neys-0.004
Tokennes
Token ID2516
Feature activation-3.13e-01

Pos logit contributions
aman+0.185
pp+0.163
al+0.154
OO+0.147
 cash+0.144
Neg logit contributions
 brothers-0.094
 friends-0.089
 importantly-0.087
 villains-0.081
 exciting-0.075
Tokendays
Token ID12545
Feature activation+3.06e-01

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.011
 families+0.011
Neg logit contributions
aman-0.020
pp-0.018
al-0.016
OO-0.015
 cash-0.015
Token because
Token ID780
Feature activation+1.61e-01

Pos logit contributions
aman+0.020
pp+0.018
al+0.016
OO+0.015
 cash+0.015
Neg logit contributions
 brothers-0.013
 friends-0.013
 importantly-0.012
 villains-0.011
 families-0.010
Token it
Token ID340
Feature activation+7.63e-01

Pos logit contributions
aman+0.009
 one+0.007
pp+0.006
 cash+0.006
al+0.006
Neg logit contributions
neys-0.007
 villains-0.007
 brothers-0.007
girls-0.007
ooters-0.006
Token was
Token ID373
Feature activation+2.68e-01

Pos logit contributions
aman+0.043
pp+0.038
al+0.035
 cash+0.031
OO+0.031
Neg logit contributions
 brothers-0.036
 friends-0.035
 importantly-0.035
 villains-0.033
ooters-0.031
Token hand
Token ID1021
Feature activation+7.13e-02

Pos logit contributions
aman+0.009
 cash+0.008
al+0.008
pp+0.008
 salon+0.007
Neg logit contributions
 importantly-0.008
 brothers-0.007
 villains-0.007
 friends-0.006
 families-0.006
Token.
Token ID13
Feature activation-5.09e-01

Pos logit contributions
aman+0.005
pp+0.005
OO+0.004
al+0.004
oph+0.004
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.002
 villains-0.002
 exciting-0.002
Token
Token ID198
Feature activation-8.23e-02

Pos logit contributions
 brothers+0.021
 friends+0.020
 importantly+0.019
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.034
pp-0.030
al-0.028
OO-0.027
 cash-0.026
Token
Token ID198
Feature activation+1.13e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
 friends+0.004
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.004
al-0.004
ara-0.004
OO-0.004
Token"
Token ID1
Feature activation+8.41e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 generation+0.004
Neg logit contributions
 brothers-0.006
 friends-0.006
 importantly-0.006
 villains-0.005
 exciting-0.005
TokenMine
Token ID24461
Feature activation+2.61e+00

Pos logit contributions
aman+0.051
pp+0.049
OO+0.041
al+0.040
 generation+0.037
Neg logit contributions
 brothers-0.035
 friends-0.035
 villains-0.032
 importantly-0.031
 families-0.030
Token!"
Token ID2474
Feature activation+5.78e-01

Pos logit contributions
aman+0.187
pp+0.164
al+0.150
 cash+0.143
 generation+0.142
Neg logit contributions
 friends-0.099
 brothers-0.099
 importantly-0.081
 villains-0.078
 exciting-0.077
Token Tom
Token ID4186
Feature activation-4.22e-01

Pos logit contributions
aman+0.037
pp+0.036
al+0.032
OO+0.031
 generation+0.029
Neg logit contributions
 brothers-0.024
 friends-0.024
 importantly-0.021
 villains-0.019
 exciting-0.019
Token says
Token ID1139
Feature activation+3.46e-01

Pos logit contributions
 brothers+0.020
 importantly+0.020
 friends+0.019
 villains+0.018
 families+0.017
Neg logit contributions
aman-0.024
pp-0.021
al-0.020
 cash-0.019
OO-0.018
Token.
Token ID13
Feature activation-1.25e-01

Pos logit contributions
aman+0.021
pp+0.019
al+0.017
OO+0.016
 cash+0.016
Neg logit contributions
 brothers-0.016
 friends-0.015
 importantly-0.014
 villains-0.013
 families-0.013
Token He
Token ID679
Feature activation-4.31e-02

Pos logit contributions
 brothers+0.004
 friends+0.003
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.010
pp-0.009
al-0.008
OO-0.008
 cash-0.008
Token yell
Token ID28946
Feature activation+6.83e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.005
 friends-0.004
 importantly-0.004
 villains-0.004
 families-0.004
Token.
Token ID13
Feature activation-5.97e-01

Pos logit contributions
aman+0.044
pp+0.039
al+0.036
 cash+0.034
OO+0.033
Neg logit contributions
 brothers-0.030
 friends-0.028
 importantly-0.027
 villains-0.025
 families-0.024
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
 brothers+0.023
 friends+0.021
 importantly+0.020
 villains+0.018
 families+0.018
Neg logit contributions
aman-0.041
pp-0.037
al-0.034
OO-0.033
 cash-0.032
Token
Token ID198
Feature activation-1.20e-01

Pos logit contributions
 brothers+0.016
 friends+0.015
 importantly+0.015
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.022
pp-0.019
al-0.017
OO-0.017
ara-0.016
Token"
Token ID1
Feature activation+7.77e-01

Pos logit contributions
 brothers+0.006
 friends+0.006
 importantly+0.006
 villains+0.005
 families+0.005
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
TokenMine
Token ID24461
Feature activation+2.58e+00

Pos logit contributions
aman+0.040
pp+0.036
al+0.030
OO+0.029
 cash+0.027
Neg logit contributions
 brothers-0.043
 friends-0.042
 importantly-0.040
 villains-0.039
 families-0.037
Token!"
Token ID2474
Feature activation+4.28e-01

Pos logit contributions
aman+0.174
pp+0.154
al+0.141
 cash+0.133
OO+0.130
Neg logit contributions
 brothers-0.107
 friends-0.104
 importantly-0.092
 villains-0.086
 exciting-0.084
Token Ben
Token ID3932
Feature activation+2.95e-01

Pos logit contributions
aman+0.027
pp+0.024
al+0.022
OO+0.021
 cash+0.020
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.017
 villains-0.016
 families-0.015
Token says
Token ID1139
Feature activation+3.09e-01

Pos logit contributions
aman+0.017
pp+0.015
al+0.014
 cash+0.013
OO+0.013
Neg logit contributions
 brothers-0.014
 importantly-0.013
 friends-0.013
 villains-0.012
 families-0.012
Token.
Token ID13
Feature activation-2.25e-01

Pos logit contributions
aman+0.019
pp+0.017
al+0.016
OO+0.015
 cash+0.015
Neg logit contributions
 brothers-0.014
 friends-0.013
 importantly-0.013
 villains-0.012
 families-0.011
Token
Token ID198
Feature activation-7.53e-03

Pos logit contributions
 brothers+0.007
 friends+0.006
 importantly+0.006
 villains+0.006
 families+0.005
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
OO-0.014
 cash-0.014
TokenL
Token ID43
Feature activation+6.23e-01

Pos logit contributions
aman+0.011
pp+0.010
al+0.009
OO+0.008
ho+0.007
Neg logit contributions
 friends-0.011
 brothers-0.011
 importantly-0.010
 exciting-0.010
 villains-0.010
Tokenily
Token ID813
Feature activation-7.54e-02

Pos logit contributions
aman+0.049
pp+0.044
 cash+0.039
al+0.039
+0.038
Neg logit contributions
 friends-0.019
 brothers-0.018
 importantly-0.017
 villains-0.014
 kids-0.013
Token didn
Token ID1422
Feature activation+3.43e-01

Pos logit contributions
 brothers+0.003
 friends+0.003
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.004
al-0.004
OO-0.004
 cash-0.004
Token't
Token ID470
Feature activation+5.10e-01

Pos logit contributions
aman+0.018
pp+0.016
al+0.014
OO+0.013
 cash+0.013
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.017
 villains-0.016
 families-0.016
Token like
Token ID588
Feature activation+1.24e+00

Pos logit contributions
aman+0.031
pp+0.027
al+0.024
OO+0.023
 cash+0.023
Neg logit contributions
 brothers-0.025
 friends-0.024
 importantly-0.022
 villains-0.021
 families-0.020
Token shampoo
Token ID47259
Feature activation+2.55e+00

Pos logit contributions
aman+0.076
pp+0.067
al+0.061
OO+0.058
 cash+0.058
Neg logit contributions
 brothers-0.057
 friends-0.054
 importantly-0.052
 villains-0.048
 families-0.046
Token because
Token ID780
Feature activation+5.17e-01

Pos logit contributions
aman+0.168
pp+0.146
al+0.133
OO+0.130
 cash+0.127
Neg logit contributions
 brothers-0.108
 friends-0.105
 importantly-0.095
 villains-0.087
 families-0.086
Token it
Token ID340
Feature activation+1.23e+00

Pos logit contributions
aman+0.025
pp+0.019
al+0.019
 cash+0.017
ara+0.016
Neg logit contributions
 brothers-0.028
 villains-0.027
 importantly-0.027
 friends-0.026
ooters-0.026
Token made
Token ID925
Feature activation+8.52e-01

Pos logit contributions
aman+0.071
pp+0.065
al+0.059
OO+0.054
 cash+0.054
Neg logit contributions
 brothers-0.058
 friends-0.055
 importantly-0.055
 villains-0.051
 families-0.048
Token her
Token ID607
Feature activation+1.62e-01

Pos logit contributions
aman+0.045
pp+0.044
al+0.036
OO+0.034
use+0.033
Neg logit contributions
 friends-0.049
 brothers-0.049
 importantly-0.043
 exciting-0.042
 fun-0.042
Token eyes
Token ID2951
Feature activation-3.40e-02

Pos logit contributions
aman+0.009
pp+0.008
al+0.007
 cash+0.007
OO+0.007
Neg logit contributions
 brothers-0.007
 importantly-0.007
 villains-0.007
 friends-0.007
neys-0.006
TokenWhy
Token ID5195
Feature activation-1.23e-01

Pos logit contributions
 brothers+0.016
 friends+0.015
 families+0.013
 importantly+0.013
 villains+0.013
Neg logit contributions
aman-0.020
pp-0.019
OO-0.017
al-0.015
 generation-0.015
Token do
Token ID466
Feature activation-1.44e+00

Pos logit contributions
 importantly+0.006
 brothers+0.006
 friends+0.006
 villains+0.005
neys+0.005
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token you
Token ID345
Feature activation+1.36e+00

Pos logit contributions
 brothers+0.079
 importantly+0.078
neys+0.076
 friends+0.071
ooters+0.071
Neg logit contributions
aman-0.056
pp-0.047
al-0.046
 cash-0.046
-0.043
Token w
Token ID266
Feature activation+9.53e-02

Pos logit contributions
aman+0.090
pp+0.079
al+0.072
OO+0.069
 cash+0.069
Neg logit contributions
 brothers-0.059
 friends-0.058
 importantly-0.050
 villains-0.049
 families-0.047
Tokenag
Token ID363
Feature activation-7.06e-01

Pos logit contributions
aman+0.006
pp+0.006
al+0.005
OO+0.005
 cash+0.005
Neg logit contributions
 brothers-0.004
 friends-0.003
 importantly-0.003
 villains-0.003
 families-0.003
Token your
Token ID534
Feature activation+2.54e+00

Pos logit contributions
 brothers+0.032
 friends+0.030
 importantly+0.028
 villains+0.026
 families+0.025
Neg logit contributions
aman-0.046
pp-0.040
al-0.036
 cash-0.035
OO-0.034
Token tail
Token ID7894
Feature activation+5.10e-01

Pos logit contributions
aman+0.159
pp+0.143
al+0.130
OO+0.125
 cash+0.122
Neg logit contributions
 brothers-0.108
 importantly-0.101
 friends-0.100
 villains-0.092
 families-0.088
Token?"
Token ID1701
Feature activation+3.98e-01

Pos logit contributions
aman+0.031
pp+0.027
al+0.024
 cash+0.023
OO+0.023
Neg logit contributions
 brothers-0.025
 friends-0.024
 importantly-0.022
 villains-0.021
 families-0.020
Token Spot
Token ID15899
Feature activation-1.08e+00

Pos logit contributions
aman+0.027
pp+0.025
al+0.023
OO+0.022
 cash+0.021
Neg logit contributions
 brothers-0.015
 friends-0.014
 importantly-0.014
 villains-0.013
 families-0.012
Token laughed
Token ID13818
Feature activation+6.19e-02

Pos logit contributions
 brothers+0.046
 friends+0.044
 importantly+0.039
 villains+0.036
 families+0.035
Neg logit contributions
aman-0.071
pp-0.063
al-0.057
OO-0.055
 generation-0.054
Token and
Token ID290
Feature activation+3.12e-01

Pos logit contributions
aman+0.005
pp+0.004
al+0.004
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.002
 friends-0.002
 importantly-0.002
 exciting-0.002
 villains-0.002
Token kept
Token ID4030
Feature activation+1.72e-02

Pos logit contributions
aman+0.021
pp+0.019
al+0.017
OO+0.016
 cash+0.016
Neg logit contributions
 brothers-0.017
 friends-0.016
 importantly-0.015
 villains-0.014
 families-0.014
Token crying
Token ID13774
Feature activation-1.07e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
OO+0.001
oph+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Token and
Token ID290
Feature activation+4.15e-02

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token throwing
Token ID9644
Feature activation+7.95e-01

Pos logit contributions
aman+0.003
pp+0.002
al+0.002
OO+0.002
oph+0.002
Neg logit contributions
 brothers-0.002
 friends-0.002
 importantly-0.002
 villains-0.002
 having-0.001
Token a
Token ID257
Feature activation+9.53e-01

Pos logit contributions
aman+0.048
pp+0.044
OO+0.038
al+0.036
oph+0.036
Neg logit contributions
 friends-0.039
 brothers-0.039
 importantly-0.032
 exciting-0.032
 families-0.031
Token tant
Token ID24246
Feature activation+2.54e+00

Pos logit contributions
aman+0.051
pp+0.045
al+0.040
OO+0.037
 generation+0.036
Neg logit contributions
 brothers-0.051
 friends-0.051
 importantly-0.047
 villains-0.043
 families-0.043
Tokenrum
Token ID6582
Feature activation-8.39e-01

Pos logit contributions
aman+0.190
pp+0.166
al+0.154
 cash+0.151
OO+0.148
Neg logit contributions
 brothers-0.085
 friends-0.080
 importantly-0.075
 villains-0.068
 families-0.060
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 brothers+0.035
 friends+0.034
 importantly+0.032
 villains+0.029
 families+0.028
Neg logit contributions
aman-0.055
pp-0.050
al-0.045
OO-0.043
 cash-0.042
Token
Token ID198
Feature activation+3.84e-03

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.009
pp-0.008
al-0.007
OO-0.007
 cash-0.007
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
aman+0.000
pp+0.000
al+0.000
OO+0.000
 cash+0.000
Neg logit contributions
 brothers-0.000
 friends-0.000
 importantly-0.000
 villains-0.000
 families-0.000
TokenFinally
Token ID11158
Feature activation+4.31e-01

Pos logit contributions
aman+0.010
pp+0.009
al+0.008
OO+0.007
 cash+0.007
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.007
 villains-0.007
 exciting-0.007
Tokenloo
Token ID29680
Feature activation-3.66e-01

Pos logit contributions
 brothers+0.046
 friends+0.045
 importantly+0.044
 villains+0.042
 families+0.038
Neg logit contributions
aman-0.084
pp-0.075
al-0.069
OO-0.066
 cash-0.064
Token and
Token ID290
Feature activation-9.24e-02

Pos logit contributions
 brothers+0.016
 friends+0.016
 importantly+0.014
 villains+0.013
 families+0.013
Neg logit contributions
aman-0.023
pp-0.021
al-0.019
OO-0.018
 cash-0.018
Token pretended
Token ID36766
Feature activation-1.71e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
 friends+0.004
 villains+0.004
neys+0.003
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
 cash-0.004
OO-0.004
Token to
Token ID284
Feature activation+3.00e-01

Pos logit contributions
 brothers+0.009
 importantly+0.008
 friends+0.008
 villains+0.008
neys+0.007
Neg logit contributions
aman-0.009
pp-0.007
al-0.007
OO-0.006
 cash-0.006
Token be
Token ID307
Feature activation-2.62e-01

Pos logit contributions
aman+0.021
pp+0.019
al+0.017
OO+0.016
oph+0.016
Neg logit contributions
 brothers-0.012
 friends-0.011
 villains-0.010
 importantly-0.010
 exciting-0.010
Token Esk
Token ID47534
Feature activation-4.39e+00

Pos logit contributions
 importantly+0.012
 brothers+0.012
ooters+0.011
 friends+0.011
 villains+0.010
Neg logit contributions
aman-0.013
pp-0.012
al-0.012
 heaven-0.010
OO-0.010
Tokenim
Token ID320
Feature activation-1.45e+00

Pos logit contributions
 brothers+0.238
 importantly+0.234
 friends+0.227
 villains+0.220
 exciting+0.208
Neg logit contributions
aman-0.234
pp-0.197
al-0.174
OO-0.171
 cash-0.151
Tokenos
Token ID418
Feature activation-1.20e+00

Pos logit contributions
 brothers+0.074
 friends+0.071
 importantly+0.067
 villains+0.063
 families+0.061
Neg logit contributions
aman-0.082
pp-0.071
al-0.064
OO-0.061
 cash-0.060
Token.
Token ID13
Feature activation-3.10e-01

Pos logit contributions
 brothers+0.053
 friends+0.051
 importantly+0.049
 villains+0.045
 families+0.043
Neg logit contributions
aman-0.075
pp-0.067
al-0.061
OO-0.058
 cash-0.057
Token After
Token ID2293
Feature activation+3.39e-01

Pos logit contributions
 brothers+0.012
 friends+0.012
 importantly+0.011
 villains+0.011
 families+0.010
Neg logit contributions
aman-0.021
pp-0.018
al-0.017
OO-0.016
 cash-0.016
Token a
Token ID257
Feature activation+5.78e-01

Pos logit contributions
aman+0.020
pp+0.018
al+0.016
OO+0.015
 cash+0.015
Neg logit contributions
 brothers-0.016
 friends-0.016
 importantly-0.015
 villains-0.014
 families-0.013
Token They
Token ID1119
Feature activation+4.97e-01

Pos logit contributions
 brothers+0.000
 friends+0.000
 importantly+0.000
 villains+0.000
 families+0.000
Neg logit contributions
aman-0.000
pp-0.000
al-0.000
OO-0.000
 cash-0.000
Token made
Token ID925
Feature activation+2.04e-02

Pos logit contributions
aman+0.032
pp+0.028
al+0.026
OO+0.025
 cash+0.024
Neg logit contributions
 brothers-0.022
 friends-0.021
 importantly-0.019
 villains-0.018
 families-0.017
Token v
Token ID410
Feature activation-1.66e+00

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
OO+0.001
 cash+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Tokenroom
Token ID3823
Feature activation-1.79e+00

Pos logit contributions
 brothers+0.085
 friends+0.082
neys+0.073
 importantly+0.072
ooters+0.070
Neg logit contributions
aman-0.098
pp-0.078
al-0.073
 generation-0.070
use-0.069
Token-
Token ID12
Feature activation-2.41e+00

Pos logit contributions
 brothers+0.081
 friends+0.080
 exciting+0.068
 villains+0.067
 importantly+0.066
Neg logit contributions
aman-0.114
pp-0.096
al-0.087
 generation-0.085
oph-0.084
Tokenv
Token ID85
Feature activation-3.68e+00

Pos logit contributions
 brothers+0.091
 friends+0.091
ooters+0.082
neys+0.080
 villains+0.078
Neg logit contributions
aman-0.169
pp-0.138
al-0.130
oph-0.129
OO-0.127
Tokenroom
Token ID3823
Feature activation-1.32e+00

Pos logit contributions
 brothers+0.205
 friends+0.197
 importantly+0.193
 villains+0.183
 families+0.176
Neg logit contributions
aman-0.185
pp-0.159
al-0.142
OO-0.134
 cash-0.130
Token noises
Token ID26782
Feature activation-1.24e-01

Pos logit contributions
 brothers+0.060
 friends+0.059
 importantly+0.051
 villains+0.051
 exciting+0.050
Neg logit contributions
aman-0.084
pp-0.072
al-0.065
oph-0.062
OO-0.062
Token as
Token ID355
Feature activation-3.41e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 exciting+0.004
Neg logit contributions
aman-0.008
pp-0.007
al-0.007
OO-0.006
 cash-0.006
Token they
Token ID484
Feature activation+1.36e-01

Pos logit contributions
 brothers+0.013
 importantly+0.013
 friends+0.013
 villains+0.012
ooters+0.011
Neg logit contributions
aman-0.020
pp-0.018
al-0.017
OO-0.016
 cash-0.016
Token moved
Token ID3888
Feature activation-4.20e-01

Pos logit contributions
aman+0.009
pp+0.008
al+0.007
OO+0.007
 cash+0.007
Neg logit contributions
 brothers-0.006
 friends-0.006
 importantly-0.005
 villains-0.005
 families-0.005
Token He
Token ID679
Feature activation-4.54e-01

Pos logit contributions
 brothers+0.019
 friends+0.018
 importantly+0.017
 villains+0.016
 families+0.016
Neg logit contributions
aman-0.036
pp-0.031
al-0.029
 cash-0.028
OO-0.028
Token made
Token ID925
Feature activation-2.46e-01

Pos logit contributions
 brothers+0.020
 friends+0.019
 importantly+0.018
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.029
pp-0.026
al-0.024
OO-0.023
 cash-0.022
Token v
Token ID410
Feature activation-1.03e+00

Pos logit contributions
 brothers+0.011
 friends+0.011
 importantly+0.010
 villains+0.009
 families+0.009
Neg logit contributions
aman-0.016
pp-0.014
al-0.013
OO-0.012
 cash-0.012
Tokenroom
Token ID3823
Feature activation-1.46e+00

Pos logit contributions
 brothers+0.053
 friends+0.051
 importantly+0.047
 villains+0.045
neys+0.044
Neg logit contributions
aman-0.060
pp-0.049
al-0.045
OO-0.043
 cash-0.042
Token-
Token ID12
Feature activation-2.01e+00

Pos logit contributions
 brothers+0.075
 friends+0.074
 importantly+0.065
 villains+0.064
 exciting+0.063
Neg logit contributions
aman-0.084
pp-0.070
al-0.063
OO-0.060
 generation-0.059
Tokenv
Token ID85
Feature activation-3.41e+00

Pos logit contributions
 brothers+0.066
 friends+0.065
 villains+0.056
ooters+0.054
neys+0.053
Neg logit contributions
aman-0.154
pp-0.128
al-0.121
OO-0.120
oph-0.116
Tokenroom
Token ID3823
Feature activation-1.10e+00

Pos logit contributions
 brothers+0.193
 friends+0.185
 importantly+0.185
 villains+0.176
 exciting+0.169
Neg logit contributions
aman-0.163
pp-0.141
al-0.127
OO-0.118
 cash-0.113
Token noises
Token ID26782
Feature activation+2.78e-01

Pos logit contributions
 brothers+0.056
 friends+0.055
 importantly+0.049
 villains+0.048
 exciting+0.046
Neg logit contributions
aman-0.065
pp-0.055
al-0.049
OO-0.047
oph-0.045
Token and
Token ID290
Feature activation-1.22e-01

Pos logit contributions
aman+0.018
pp+0.015
al+0.014
OO+0.013
 cash+0.013
Neg logit contributions
 brothers-0.013
 friends-0.012
 importantly-0.011
 villains-0.011
 exciting-0.010
Token drove
Token ID10357
Feature activation-5.49e-01

Pos logit contributions
 brothers+0.005
 importantly+0.005
 friends+0.005
neys+0.004
 families+0.004
Neg logit contributions
aman-0.007
pp-0.007
al-0.006
 cash-0.006
OO-0.005
Token it
Token ID340
Feature activation-1.42e-01

Pos logit contributions
 brothers+0.029
 importantly+0.028
 friends+0.026
 villains+0.024
neys+0.024
Neg logit contributions
aman-0.029
pp-0.025
al-0.024
 cash-0.023
OO-0.021
Token made
Token ID925
Feature activation-7.76e-02

Pos logit contributions
 brothers+0.025
 importantly+0.025
 friends+0.024
 villains+0.022
 families+0.022
Neg logit contributions
aman-0.026
pp-0.023
al-0.022
 cash-0.021
OO-0.019
Token a
Token ID257
Feature activation-4.70e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.004
al-0.004
OO-0.004
 cash-0.003
Token v
Token ID410
Feature activation-4.03e-01

Pos logit contributions
 brothers+0.017
 friends+0.016
 importantly+0.016
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.033
pp-0.029
al-0.027
OO-0.026
 cash-0.026
Tokenroom
Token ID3823
Feature activation-1.22e+00

Pos logit contributions
 brothers+0.020
 friends+0.019
neys+0.016
 importantly+0.016
 villains+0.016
Neg logit contributions
aman-0.024
pp-0.021
al-0.018
use-0.018
 generation-0.018
Token-
Token ID12
Feature activation-1.57e+00

Pos logit contributions
 brothers+0.049
 friends+0.049
 exciting+0.039
 villains+0.038
 people+0.037
Neg logit contributions
aman-0.087
pp-0.075
al-0.068
use-0.067
oph-0.067
Tokenv
Token ID85
Feature activation-3.25e+00

Pos logit contributions
 brothers+0.045
 friends+0.044
 villains+0.037
ooters+0.037
 importantly+0.036
Neg logit contributions
aman-0.126
pp-0.107
al-0.100
OO-0.099
oph-0.097
Tokenroom
Token ID3823
Feature activation-9.64e-01

Pos logit contributions
 brothers+0.174
 friends+0.168
 importantly+0.154
 villains+0.143
 families+0.142
Neg logit contributions
aman-0.179
pp-0.158
al-0.139
OO-0.130
 cash-0.130
Token sound
Token ID2128
Feature activation+6.89e-02

Pos logit contributions
 brothers+0.040
 friends+0.039
 villains+0.032
 importantly+0.031
 exciting+0.031
Neg logit contributions
aman-0.067
pp-0.058
al-0.053
oph-0.051
use-0.051
Token and
Token ID290
Feature activation+8.86e-02

Pos logit contributions
aman+0.005
pp+0.004
al+0.004
OO+0.004
use+0.004
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.002
 villains-0.002
 exciting-0.002
Token laughed
Token ID13818
Feature activation+1.23e-01

Pos logit contributions
aman+0.005
pp+0.005
al+0.004
 cash+0.004
OO+0.004
Neg logit contributions
 brothers-0.004
 importantly-0.003
 friends-0.003
 villains-0.003
 families-0.003
Token.
Token ID13
Feature activation-5.31e-01

Pos logit contributions
aman+0.008
pp+0.007
al+0.007
OO+0.006
 cash+0.006
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.005
 villains-0.004
 families-0.004
Token loud
Token ID7812
Feature activation+1.20e+00

Pos logit contributions
 brothers+0.006
 friends+0.006
 importantly+0.005
 villains+0.005
 families+0.005
Neg logit contributions
aman-0.008
pp-0.007
al-0.006
OO-0.006
use-0.006
Token noise
Token ID7838
Feature activation+1.29e+00

Pos logit contributions
aman+0.093
pp+0.089
al+0.077
oph+0.075
 cash+0.074
Neg logit contributions
 brothers-0.037
 friends-0.036
 villains-0.029
 importantly-0.027
 boys-0.026
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
aman+0.092
pp+0.084
al+0.075
 cash+0.074
oph+0.073
Neg logit contributions
 brothers-0.049
 friends-0.046
 importantly-0.042
 villains-0.038
 exciting-0.036
Token He
Token ID679
Feature activation-3.37e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
OO+0.001
 cash+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Token sc
Token ID629
Feature activation-1.21e+00

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.012
 villains+0.012
 exciting+0.011
Neg logit contributions
aman-0.022
pp-0.020
al-0.018
OO-0.017
 cash-0.017
Tokenrun
Token ID5143
Feature activation-3.25e+00

Pos logit contributions
 brothers+0.064
 friends+0.061
 importantly+0.059
 villains+0.055
 families+0.053
Neg logit contributions
aman-0.066
pp-0.058
al-0.052
OO-0.049
 cash-0.048
Tokenched
Token ID1740
Feature activation+8.61e-01

Pos logit contributions
 brothers+0.178
 friends+0.173
 importantly+0.161
 villains+0.155
neys+0.148
Neg logit contributions
aman-0.170
pp-0.145
al-0.127
 cash-0.125
OO-0.122
Token his
Token ID465
Feature activation-2.51e-01

Pos logit contributions
aman+0.060
pp+0.054
al+0.048
OO+0.047
 cash+0.046
Neg logit contributions
 brothers-0.034
 friends-0.033
 importantly-0.028
 villains-0.027
 exciting-0.026
Token eyes
Token ID2951
Feature activation-6.57e-01

Pos logit contributions
 brothers+0.011
 friends+0.011
 importantly+0.010
 villains+0.010
 families+0.009
Neg logit contributions
aman-0.015
pp-0.014
al-0.013
OO-0.012
 cash-0.012
Token tightly
Token ID17707
Feature activation-6.86e-01

Pos logit contributions
 brothers+0.018
 friends+0.017
 exciting+0.015
 strong+0.015
 importantly+0.014
Neg logit contributions
aman-0.052
pp-0.046
OO-0.042
oph-0.042
 generation-0.042
Token and
Token ID290
Feature activation+4.41e-01

Pos logit contributions
 brothers+0.024
 friends+0.024
 importantly+0.021
 villains+0.018
 having+0.018
Neg logit contributions
aman-0.050
pp-0.044
oph-0.040
al-0.040
 cash-0.039
Token and
Token ID290
Feature activation-1.41e-01

Pos logit contributions
 brothers+0.037
 friends+0.037
 importantly+0.030
 exciting+0.029
neys+0.029
Neg logit contributions
aman-0.070
pp-0.062
al-0.056
OO-0.056
oph-0.055
Token made
Token ID925
Feature activation-3.62e-02

Pos logit contributions
 brothers+0.007
 importantly+0.007
 friends+0.006
 villains+0.006
 families+0.006
Neg logit contributions
aman-0.008
pp-0.007
al-0.007
 cash-0.006
OO-0.006
Token v
Token ID410
Feature activation-8.47e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.002
OO-0.002
 cash-0.002
Tokenroom
Token ID3823
Feature activation-1.39e+00

Pos logit contributions
 brothers+0.048
 friends+0.047
 importantly+0.047
 villains+0.043
 exciting+0.042
Neg logit contributions
aman-0.041
pp-0.036
al-0.032
OO-0.030
 cash-0.029
Token-
Token ID12
Feature activation-1.65e+00

Pos logit contributions
 brothers+0.053
 friends+0.050
 importantly+0.047
 villains+0.043
 families+0.041
Neg logit contributions
aman-0.096
pp-0.086
al-0.079
OO-0.076
 cash-0.075
Tokenv
Token ID85
Feature activation-3.22e+00

Pos logit contributions
 brothers+0.047
 friends+0.044
 importantly+0.040
 villains+0.036
 families+0.034
Neg logit contributions
aman-0.130
pp-0.118
al-0.110
OO-0.106
 cash-0.104
Tokenroom
Token ID3823
Feature activation-1.07e+00

Pos logit contributions
 importantly+0.190
 brothers+0.187
 villains+0.182
 friends+0.179
 exciting+0.177
Neg logit contributions
aman-0.136
pp-0.115
al-0.107
OO-0.100
 cash-0.086
Token sounds
Token ID5238
Feature activation+1.26e-01

Pos logit contributions
 brothers+0.037
 friends+0.035
 importantly+0.033
 villains+0.030
 families+0.028
Neg logit contributions
aman-0.077
pp-0.070
al-0.065
OO-0.062
 cash-0.061
Token.
Token ID13
Feature activation-4.67e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.005
 cash+0.005
Neg logit contributions
 brothers-0.007
 friends-0.006
 importantly-0.006
 villains-0.006
neys-0.006
Token They
Token ID1119
Feature activation+1.55e-01

Pos logit contributions
 brothers+0.021
 friends+0.020
 importantly+0.019
 villains+0.017
 families+0.017
Neg logit contributions
aman-0.028
pp-0.024
al-0.023
 cash-0.022
OO-0.021
Token laughed
Token ID13818
Feature activation+7.04e-04

Pos logit contributions
aman+0.009
pp+0.009
al+0.008
 cash+0.007
OO+0.007
Neg logit contributions
 brothers-0.007
 importantly-0.006
 friends-0.006
 villains-0.006
 families-0.005
Token He
Token ID679
Feature activation-4.13e-01

Pos logit contributions
 brothers+0.012
 friends+0.012
 importantly+0.011
 families+0.011
 villains+0.011
Neg logit contributions
aman-0.019
pp-0.016
al-0.015
 cash-0.015
OO-0.014
Token makes
Token ID1838
Feature activation+3.68e-01

Pos logit contributions
 brothers+0.020
 friends+0.019
 importantly+0.017
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.025
pp-0.022
al-0.020
OO-0.019
 cash-0.018
Token v
Token ID410
Feature activation-8.54e-01

Pos logit contributions
aman+0.023
pp+0.021
al+0.019
OO+0.018
 cash+0.017
Neg logit contributions
 brothers-0.017
 friends-0.016
 importantly-0.015
 villains-0.014
 families-0.013
Tokenroom
Token ID3823
Feature activation-1.30e+00

Pos logit contributions
 brothers+0.046
 friends+0.044
 importantly+0.042
 villains+0.040
 families+0.039
Neg logit contributions
aman-0.046
pp-0.039
al-0.035
OO-0.033
 cash-0.033
Token-
Token ID12
Feature activation-1.72e+00

Pos logit contributions
 brothers+0.065
 friends+0.064
 importantly+0.056
 villains+0.056
 exciting+0.054
Neg logit contributions
aman-0.077
pp-0.065
al-0.058
OO-0.055
oph-0.054
Tokenv
Token ID85
Feature activation-3.20e+00

Pos logit contributions
 brothers+0.064
 friends+0.064
neys+0.057
 villains+0.055
ooters+0.055
Neg logit contributions
aman-0.123
pp-0.102
oph-0.093
al-0.093
OO-0.093
Tokenroom
Token ID3823
Feature activation-1.03e+00

Pos logit contributions
 brothers+0.183
 importantly+0.178
 friends+0.177
 villains+0.169
 exciting+0.163
Neg logit contributions
aman-0.149
pp-0.128
al-0.116
OO-0.109
 cash-0.102
Token sounds
Token ID5238
Feature activation+1.03e-01

Pos logit contributions
 brothers+0.047
 friends+0.046
 importantly+0.041
 villains+0.040
 exciting+0.039
Neg logit contributions
aman-0.065
pp-0.056
al-0.051
OO-0.048
oph-0.048
Token.
Token ID13
Feature activation-4.87e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.005
 villains-0.004
 families-0.004
Token Kim
Token ID6502
Feature activation-1.34e+00

Pos logit contributions
 brothers+0.020
 friends+0.020
 importantly+0.019
 families+0.018
 villains+0.018
Neg logit contributions
aman-0.030
pp-0.025
 cash-0.023
al-0.023
OO-0.023
Token finds
Token ID7228
Feature activation-2.17e-01

Pos logit contributions
 brothers+0.061
 friends+0.058
 importantly+0.054
 villains+0.051
 families+0.049
Neg logit contributions
aman-0.083
pp-0.073
al-0.066
OO-0.064
 cash-0.062
Token They
Token ID1119
Feature activation+4.29e-01

Pos logit contributions
 brothers+0.011
 friends+0.011
 importantly+0.011
 villains+0.010
 families+0.009
Neg logit contributions
aman-0.014
pp-0.013
al-0.011
OO-0.011
 cash-0.011
Token made
Token ID925
Feature activation+1.18e-01

Pos logit contributions
aman+0.027
pp+0.025
al+0.023
 cash+0.022
OO+0.021
Neg logit contributions
 brothers-0.017
 importantly-0.017
 friends-0.016
 villains-0.014
neys-0.014
Token v
Token ID410
Feature activation-7.65e-01

Pos logit contributions
aman+0.008
pp+0.007
al+0.006
OO+0.006
 cash+0.006
Neg logit contributions
 brothers-0.005
 friends-0.005
 importantly-0.004
 villains-0.004
 exciting-0.004
Tokenroom
Token ID3823
Feature activation-1.35e+00

Pos logit contributions
 brothers+0.041
 friends+0.039
 importantly+0.037
 villains+0.035
 families+0.034
Neg logit contributions
aman-0.042
pp-0.036
al-0.032
OO-0.030
 cash-0.030
Token-
Token ID12
Feature activation-1.64e+00

Pos logit contributions
 brothers+0.066
 friends+0.064
 importantly+0.058
 villains+0.056
 exciting+0.055
Neg logit contributions
aman-0.080
pp-0.068
al-0.063
OO-0.059
 generation-0.058
Tokenv
Token ID85
Feature activation-3.17e+00

Pos logit contributions
 brothers+0.042
 friends+0.039
 importantly+0.035
 villains+0.031
 families+0.028
Neg logit contributions
aman-0.135
pp-0.121
al-0.114
OO-0.110
 cash-0.108
Tokenroom
Token ID3823
Feature activation-1.15e+00

Pos logit contributions
 brothers+0.178
 friends+0.171
 importantly+0.169
 villains+0.161
 exciting+0.154
Neg logit contributions
aman-0.156
pp-0.134
al-0.121
OO-0.112
 cash-0.109
Token noises
Token ID26782
Feature activation+5.70e-01

Pos logit contributions
 brothers+0.051
 friends+0.050
 importantly+0.044
 villains+0.043
 exciting+0.042
Neg logit contributions
aman-0.073
pp-0.063
al-0.058
OO-0.055
oph-0.053
Token and
Token ID290
Feature activation-1.35e-01

Pos logit contributions
aman+0.040
pp+0.035
al+0.031
OO+0.031
oph+0.030
Neg logit contributions
 brothers-0.023
 friends-0.022
 importantly-0.020
 villains-0.019
 exciting-0.018
Token pretended
Token ID36766
Feature activation-4.14e-01

Pos logit contributions
 brothers+0.006
 importantly+0.006
 friends+0.005
neys+0.005
 families+0.005
Neg logit contributions
aman-0.007
pp-0.007
al-0.006
 cash-0.006
 lear-0.006
Token to
Token ID284
Feature activation+3.05e-01

Pos logit contributions
 brothers+0.021
 importantly+0.020
 friends+0.019
 villains+0.018
 families+0.016
Neg logit contributions
aman-0.022
pp-0.019
al-0.018
OO-0.017
 cash-0.017
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.012
 exciting+0.011
neys+0.011
Neg logit contributions
aman-0.031
pp-0.027
oph-0.025
OO-0.025
al-0.024
Token It
Token ID632
Feature activation+1.89e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.012
pp-0.011
al-0.010
OO-0.010
 cash-0.010
Token had
Token ID550
Feature activation+6.13e-02

Pos logit contributions
aman+0.012
pp+0.010
al+0.010
OO+0.009
 cash+0.009
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.008
 villains-0.007
 families-0.007
Token some
Token ID617
Feature activation+2.29e-01

Pos logit contributions
aman+0.004
pp+0.003
al+0.003
OO+0.003
 cash+0.003
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.003
 villains-0.002
 exciting-0.002
Token car
Token ID1097
Feature activation+4.31e-01

Pos logit contributions
aman+0.015
pp+0.013
al+0.013
 cash+0.012
OO+0.012
Neg logit contributions
 brothers-0.009
 friends-0.008
 importantly-0.008
 villains-0.007
 families-0.007
Tokenv
Token ID85
Feature activation-3.15e+00

Pos logit contributions
aman+0.028
pp+0.024
al+0.022
OO+0.022
oph+0.021
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.017
 villains-0.016
 exciting-0.015
Tokenings
Token ID654
Feature activation+8.61e-01

Pos logit contributions
 brothers+0.176
 friends+0.170
 importantly+0.166
 villains+0.157
 families+0.151
Neg logit contributions
aman-0.159
pp-0.137
al-0.122
OO-0.114
 cash-0.110
Token and
Token ID290
Feature activation-2.47e-01

Pos logit contributions
aman+0.060
pp+0.053
OO+0.048
oph+0.047
al+0.046
Neg logit contributions
 brothers-0.034
 friends-0.032
 importantly-0.029
 villains-0.027
 exciting-0.026
Token letters
Token ID7475
Feature activation-1.10e-01

Pos logit contributions
 brothers+0.012
 friends+0.011
 importantly+0.011
 villains+0.010
 families+0.010
Neg logit contributions
aman-0.015
pp-0.013
al-0.012
OO-0.011
 cash-0.011
Token on
Token ID319
Feature activation-3.87e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.004
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.008
pp-0.007
OO-0.006
al-0.006
oph-0.006
Token it
Token ID340
Feature activation-8.16e-02

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.012
 villains+0.012
 exciting+0.011
Neg logit contributions
aman-0.027
pp-0.025
al-0.022
OO-0.022
oph-0.021
Token be
Token ID307
Feature activation-2.85e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.003
OO+0.002
 cash+0.002
Neg logit contributions
 brothers-0.002
 friends-0.002
 importantly-0.002
 villains-0.002
 families-0.002
Token cow
Token ID9875
Feature activation-6.93e-01

Pos logit contributions
 brothers+0.013
 importantly+0.012
 friends+0.012
 villains+0.011
 families+0.011
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
 cash-0.013
OO-0.013
Tokenboys
Token ID13202
Feature activation-1.84e+00

Pos logit contributions
 brothers+0.032
 importantly+0.032
 friends+0.029
 villains+0.029
 exciting+0.026
Neg logit contributions
aman-0.040
pp-0.037
al-0.033
 cash-0.031
OO-0.029
Token and
Token ID290
Feature activation-1.45e-01

Pos logit contributions
 brothers+0.070
 friends+0.070
 villains+0.059
 families+0.053
 importantly+0.053
Neg logit contributions
aman-0.133
pp-0.110
OO-0.104
al-0.103
 cash-0.099
Token cow
Token ID9875
Feature activation-2.73e-01

Pos logit contributions
 brothers+0.005
 importantly+0.005
 friends+0.005
 villains+0.004
neys+0.004
Neg logit contributions
aman-0.009
pp-0.009
al-0.008
 cash-0.008
OO-0.007
Tokengirls
Token ID36960
Feature activation-3.12e+00

Pos logit contributions
 importantly+0.007
 brothers+0.007
 friends+0.006
 villains+0.005
 exciting+0.005
Neg logit contributions
aman-0.021
pp-0.020
al-0.019
 cash-0.018
OO-0.017
Token.
Token ID13
Feature activation-4.20e-02

Pos logit contributions
 brothers+0.131
 friends+0.126
 importantly+0.114
 villains+0.109
 families+0.104
Neg logit contributions
aman-0.207
pp-0.181
al-0.164
OO-0.159
 cash-0.157
Token They
Token ID1119
Feature activation+4.05e-01

Pos logit contributions
 brothers+0.002
 importantly+0.002
 friends+0.002
 villains+0.002
 families+0.001
Neg logit contributions
aman-0.003
pp-0.002
al-0.002
OO-0.002
 cash-0.002
Token put
Token ID1234
Feature activation-6.76e-01

Pos logit contributions
aman+0.024
pp+0.022
al+0.020
 cash+0.019
OO+0.019
Neg logit contributions
 brothers-0.018
 importantly-0.017
 friends-0.017
 villains-0.015
neys-0.015
Token on
Token ID319
Feature activation-2.84e-01

Pos logit contributions
 brothers+0.028
 friends+0.026
 importantly+0.024
 villains+0.022
 families+0.021
Neg logit contributions
aman-0.046
pp-0.040
al-0.037
OO-0.036
 cash-0.035
Token hats
Token ID23910
Feature activation+7.79e-02

Pos logit contributions
 brothers+0.012
 friends+0.012
 exciting+0.010
 families+0.009
 villains+0.009
Neg logit contributions
aman-0.019
pp-0.017
OO-0.016
al-0.016
oph-0.014
Token They
Token ID1119
Feature activation+4.81e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.004
al-0.004
OO-0.004
 cash-0.004
Token make
Token ID787
Feature activation-5.05e-01

Pos logit contributions
aman+0.029
pp+0.027
al+0.024
 cash+0.023
OO+0.023
Neg logit contributions
 brothers-0.021
 friends-0.020
 importantly-0.020
 villains-0.018
 families-0.017
Token v
Token ID410
Feature activation-7.03e-01

Pos logit contributions
 brothers+0.021
 friends+0.020
 importantly+0.017
 villains+0.017
 exciting+0.017
Neg logit contributions
aman-0.035
pp-0.032
al-0.028
OO-0.027
oph-0.026
Tokenroom
Token ID3823
Feature activation-1.31e+00

Pos logit contributions
 brothers+0.039
 friends+0.037
 importantly+0.036
 villains+0.034
 families+0.033
Neg logit contributions
aman-0.037
pp-0.032
al-0.028
OO-0.027
 cash-0.026
Token-
Token ID12
Feature activation-1.47e+00

Pos logit contributions
 brothers+0.062
 friends+0.060
 importantly+0.054
 villains+0.052
 exciting+0.051
Neg logit contributions
aman-0.079
pp-0.068
al-0.062
OO-0.059
oph-0.057
Tokenv
Token ID85
Feature activation-3.09e+00

Pos logit contributions
 brothers+0.039
 friends+0.036
 importantly+0.031
 villains+0.029
 families+0.026
Neg logit contributions
aman-0.120
pp-0.107
al-0.101
OO-0.098
 cash-0.096
Tokenroom
Token ID3823
Feature activation-1.18e+00

Pos logit contributions
 brothers+0.174
 importantly+0.168
 friends+0.167
 villains+0.160
 exciting+0.154
Neg logit contributions
aman-0.148
pp-0.127
al-0.115
OO-0.106
 cash-0.102
Token noises
Token ID26782
Feature activation+4.56e-01

Pos logit contributions
 brothers+0.052
 friends+0.051
 importantly+0.045
 villains+0.044
 exciting+0.042
Neg logit contributions
aman-0.075
pp-0.065
al-0.060
OO-0.057
oph-0.056
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
aman+0.031
pp+0.027
al+0.025
OO+0.024
 cash+0.024
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.016
 villains-0.016
 exciting-0.015
Token pretend
Token ID16614
Feature activation-1.80e-01

Pos logit contributions
 brothers+0.007
 importantly+0.007
 friends+0.007
 families+0.006
neys+0.006
Neg logit contributions
aman-0.010
pp-0.009
al-0.009
 cash-0.008
OO-0.008
Token to
Token ID284
Feature activation+1.82e-01

Pos logit contributions
 brothers+0.009
 importantly+0.009
 friends+0.008
 villains+0.008
 pals+0.008
Neg logit contributions
aman-0.009
pp-0.008
al-0.007
OO-0.007
 cash-0.007
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
 friends+0.022
 brothers+0.022
 importantly+0.019
 exciting+0.019
 families+0.019
Neg logit contributions
aman-0.022
pp-0.020
OO-0.017
al-0.017
oph-0.016
Token park
Token ID3952
Feature activation-4.55e-01

Pos logit contributions
 brothers+0.042
 friends+0.040
 importantly+0.036
 villains+0.034
 families+0.033
Neg logit contributions
aman-0.072
pp-0.066
al-0.058
OO-0.057
oph-0.055
Token her
Token ID607
Feature activation-6.23e-01

Pos logit contributions
 brothers+0.020
 friends+0.019
 importantly+0.018
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.029
pp-0.025
al-0.023
OO-0.022
 cash-0.022
Token "
Token ID366
Feature activation+1.50e-02

Pos logit contributions
 brothers+0.023
 importantly+0.021
 friends+0.021
 villains+0.020
 families+0.018
Neg logit contributions
aman-0.043
pp-0.038
al-0.035
 cash-0.033
OO-0.033
Tokenuse
Token ID1904
Feature activation+9.66e-01

Pos logit contributions
aman+0.001
pp+0.001
 cash+0.001
OO+0.001
al+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
neys-0.001
 families-0.001
Tokenful
Token ID913
Feature activation-3.08e+00

Pos logit contributions
aman+0.052
pp+0.049
al+0.041
OO+0.041
 generation+0.039
Neg logit contributions
 friends-0.049
 brothers-0.047
 families-0.042
 exciting-0.040
 importantly-0.040
Token-
Token ID12
Feature activation-2.48e+00

Pos logit contributions
 brothers+0.148
 friends+0.147
 families+0.118
 importantly+0.117
 pals+0.111
Neg logit contributions
aman-0.190
pp-0.165
al-0.151
OO-0.144
 cash-0.142
Tokenpark
Token ID20928
Feature activation-9.76e-01

Pos logit contributions
 friends+0.113
 brothers+0.109
 importantly+0.097
 exciting+0.094
 villains+0.094
Neg logit contributions
aman-0.142
pp-0.122
OO-0.118
al-0.105
oph-0.102
Token".
Token ID1911
Feature activation+2.91e-01

Pos logit contributions
 brothers+0.046
 friends+0.044
 importantly+0.037
 families+0.035
 boys+0.035
Neg logit contributions
aman-0.056
pp-0.047
 cash-0.043
 generation-0.042
 heaven-0.042
Token<|endoftext|>
Token ID50256
Feature activation+1.94e-01

Pos logit contributions
aman+0.022
pp+0.021
al+0.019
OO+0.019
ited+0.018
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.007
 having-0.006
 families-0.006
TokenOnce
Token ID7454
Feature activation+2.09e-01

Pos logit contributions
aman+0.010
pp+0.008
al+0.008
OO+0.007
ara+0.007
Neg logit contributions
 brothers-0.011
 friends-0.010
 importantly-0.010
 villains-0.010
 families-0.010
Token man
Token ID582
Feature activation+5.40e-02

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.011
 families+0.010
Neg logit contributions
aman-0.023
pp-0.021
al-0.019
OO-0.019
oph-0.018
Token was
Token ID373
Feature activation-3.49e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.003
OO+0.003
 cash+0.003
Neg logit contributions
 brothers-0.002
 friends-0.002
 importantly-0.002
 villains-0.002
 families-0.002
Token called
Token ID1444
Feature activation-1.19e+00

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.011
 families+0.011
Neg logit contributions
aman-0.024
pp-0.021
al-0.020
 cash-0.019
OO-0.019
Token a
Token ID257
Feature activation-5.40e-01

Pos logit contributions
 brothers+0.045
 friends+0.044
 boys+0.034
 kids+0.034
 importantly+0.033
Neg logit contributions
aman-0.082
pp-0.078
ited-0.069
OO-0.069
oph-0.068
Token "
Token ID366
Feature activation-7.53e-02

Pos logit contributions
 brothers+0.020
 friends+0.020
 importantly+0.017
 families+0.016
 exciting+0.016
Neg logit contributions
aman-0.038
pp-0.035
al-0.032
OO-0.030
oph-0.029
Tokenv
Token ID85
Feature activation-3.07e+00

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.003
neys+0.003
 families+0.003
Neg logit contributions
aman-0.004
pp-0.003
OO-0.003
 heaven-0.003
oph-0.003
Tokenendor
Token ID18738
Feature activation-1.04e+00

Pos logit contributions
 brothers+0.164
 friends+0.159
 importantly+0.136
 families+0.133
neys+0.128
Neg logit contributions
aman-0.170
pp-0.153
al-0.129
 cash-0.123
oph-0.121
Token".
Token ID1911
Feature activation+3.39e-01

Pos logit contributions
 brothers+0.047
 friends+0.045
 importantly+0.039
 families+0.037
neys+0.036
Neg logit contributions
aman-0.064
pp-0.056
al-0.050
OO-0.049
 generation-0.048
Token Tim
Token ID5045
Feature activation-9.06e-01

Pos logit contributions
aman+0.023
pp+0.021
al+0.019
OO+0.018
 cash+0.018
Neg logit contributions
 brothers-0.013
 friends-0.013
 importantly-0.012
 villains-0.011
 families-0.010
Tokenmy
Token ID1820
Feature activation-1.18e-01

Pos logit contributions
 brothers+0.055
 friends+0.054
 importantly+0.052
 villains+0.050
 families+0.048
Neg logit contributions
aman-0.042
pp-0.035
al-0.031
OO-0.028
 cash-0.028
Token wanted
Token ID2227
Feature activation+4.09e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.008
pp-0.007
al-0.006
OO-0.006
 cash-0.006
Token f
Token ID277
Feature activation-6.13e-01

Pos logit contributions
 friends+0.073
 brothers+0.071
 importantly+0.056
 families+0.056
 boys+0.054
Neg logit contributions
aman-0.100
pp-0.088
OO-0.082
oph-0.081
 generation-0.073
Tokenenn
Token ID1697
Feature activation-2.18e+00

Pos logit contributions
 brothers+0.027
 friends+0.026
 importantly+0.024
ooters+0.023
neys+0.022
Neg logit contributions
aman-0.036
 cash-0.032
pp-0.030
 generation-0.030
 heaven-0.030
Tokenel
Token ID417
Feature activation-1.91e+00

Pos logit contributions
 brothers+0.123
 friends+0.120
 importantly+0.109
 families+0.102
 pals+0.100
Neg logit contributions
aman-0.111
pp-0.096
 cash-0.087
OO-0.081
al-0.080
Token and
Token ID290
Feature activation-1.56e+00

Pos logit contributions
 brothers+0.089
 friends+0.089
 importantly+0.069
 families+0.069
neys+0.067
Neg logit contributions
aman-0.121
pp-0.104
 cash-0.096
oph-0.096
 generation-0.090
Token an
Token ID281
Feature activation-1.17e+00

Pos logit contributions
 friends+0.072
 brothers+0.070
 importantly+0.056
 families+0.056
 boys+0.054
Neg logit contributions
aman-0.100
pp-0.088
OO-0.080
oph-0.079
 generation-0.072
Tokenise
Token ID786
Feature activation-3.05e+00

Pos logit contributions
 brothers+0.038
 friends+0.036
 importantly+0.032
 villains+0.028
 families+0.027
Neg logit contributions
aman-0.088
pp-0.082
al-0.074
 cash-0.072
OO-0.071
Token and
Token ID290
Feature activation-1.51e+00

Pos logit contributions
 friends+0.123
 brothers+0.120
 families+0.089
 importantly+0.086
 having+0.086
Neg logit contributions
aman-0.202
pp-0.181
 cash-0.169
oph-0.165
OO-0.162
Token car
Token ID1097
Feature activation-8.03e-01

Pos logit contributions
 friends+0.070
 brothers+0.069
 importantly+0.055
 families+0.055
 boys+0.053
Neg logit contributions
aman-0.096
pp-0.085
OO-0.077
oph-0.076
 generation-0.069
Tokenaway
Token ID8272
Feature activation-8.42e-01

Pos logit contributions
 friends+0.031
 brothers+0.030
 families+0.023
 villains+0.023
neys+0.023
Neg logit contributions
aman-0.056
pp-0.049
oph-0.047
OO-0.044
 generation-0.044
Token and
Token ID290
Feature activation-1.47e+00

Pos logit contributions
 friends+0.043
 brothers+0.040
 families+0.035
 importantly+0.034
 villains+0.033
Neg logit contributions
aman-0.049
pp-0.043
oph-0.037
OO-0.037
 cash-0.036
Token c
Token ID269
Feature activation-2.22e+00

Pos logit contributions
 friends+0.069
 brothers+0.068
 importantly+0.055
 families+0.055
 villains+0.054
Neg logit contributions
aman-0.093
pp-0.082
OO-0.074
oph-0.072
al-0.067
Token They
Token ID1119
Feature activation+4.10e-01

Pos logit contributions
 brothers+0.007
 villains+0.007
 importantly+0.007
 friends+0.007
 families+0.006
Neg logit contributions
aman-0.008
pp-0.006
al-0.006
OO-0.006
 cash-0.006
Token make
Token ID787
Feature activation-5.32e-01

Pos logit contributions
aman+0.025
pp+0.022
al+0.021
 cash+0.019
OO+0.019
Neg logit contributions
 brothers-0.018
 friends-0.017
 importantly-0.017
 villains-0.016
 families-0.015
Token v
Token ID410
Feature activation-6.11e-01

Pos logit contributions
 friends+0.022
 brothers+0.022
 exciting+0.018
 villains+0.017
 families+0.017
Neg logit contributions
aman-0.038
pp-0.035
al-0.031
OO-0.030
use-0.030
Tokenroom
Token ID3823
Feature activation-1.21e+00

Pos logit contributions
 brothers+0.033
 friends+0.031
 importantly+0.030
 villains+0.028
 families+0.027
Neg logit contributions
aman-0.034
pp-0.029
al-0.026
OO-0.024
 cash-0.024
Token-
Token ID12
Feature activation-1.56e+00

Pos logit contributions
 brothers+0.055
 friends+0.055
 villains+0.046
 exciting+0.046
 importantly+0.045
Neg logit contributions
aman-0.077
pp-0.065
al-0.060
OO-0.058
 generation-0.057
Tokenv
Token ID85
Feature activation-3.05e+00

Pos logit contributions
 brothers+0.048
 friends+0.046
 villains+0.039
ooters+0.037
 importantly+0.037
Neg logit contributions
aman-0.124
pp-0.105
al-0.100
OO-0.099
oph-0.096
Tokenroom
Token ID3823
Feature activation-1.04e+00

Pos logit contributions
 brothers+0.172
 importantly+0.166
 friends+0.165
 villains+0.157
 exciting+0.151
Neg logit contributions
aman-0.145
pp-0.125
al-0.113
OO-0.105
 cash-0.101
Token noises
Token ID26782
Feature activation+4.20e-01

Pos logit contributions
 brothers+0.042
 friends+0.042
 villains+0.035
 importantly+0.035
 exciting+0.034
Neg logit contributions
aman-0.072
pp-0.062
al-0.057
OO-0.055
oph-0.054
Token and
Token ID290
Feature activation-7.31e-02

Pos logit contributions
aman+0.029
pp+0.025
al+0.023
OO+0.022
 cash+0.022
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.015
 villains-0.014
 exciting-0.014
Token pretend
Token ID16614
Feature activation-1.15e-01

Pos logit contributions
 brothers+0.003
 importantly+0.003
 friends+0.003
 families+0.002
neys+0.002
Neg logit contributions
aman-0.004
pp-0.004
al-0.004
 cash-0.004
OO-0.003
Token to
Token ID284
Feature activation+2.41e-01

Pos logit contributions
 brothers+0.006
 importantly+0.005
 friends+0.005
 villains+0.005
 pals+0.005
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
OO-0.005
 cash-0.004
Token and
Token ID290
Feature activation-3.21e-01

Pos logit contributions
 friends+0.015
 brothers+0.014
 importantly+0.012
 having+0.011
 exciting+0.011
Neg logit contributions
aman-0.029
pp-0.026
al-0.023
OO-0.023
oph-0.022
Token make
Token ID787
Feature activation-6.42e-01

Pos logit contributions
 brothers+0.016
 importantly+0.016
 friends+0.015
 villains+0.013
neys+0.013
Neg logit contributions
aman-0.017
pp-0.016
al-0.014
 cash-0.014
 generation-0.013
Token v
Token ID410
Feature activation-5.53e-01

Pos logit contributions
 brothers+0.024
 importantly+0.023
 friends+0.022
 villains+0.020
neys+0.019
Neg logit contributions
aman-0.043
pp-0.037
al-0.035
 cash-0.034
OO-0.034
Tokenroom
Token ID3823
Feature activation-1.44e+00

Pos logit contributions
 brothers+0.030
 friends+0.029
 importantly+0.028
 villains+0.027
 families+0.026
Neg logit contributions
aman-0.029
pp-0.025
al-0.022
OO-0.021
 cash-0.020
Token-
Token ID12
Feature activation-1.42e+00

Pos logit contributions
 brothers+0.060
 friends+0.057
 importantly+0.054
 villains+0.050
 families+0.048
Neg logit contributions
aman-0.094
pp-0.084
al-0.077
OO-0.073
 cash-0.072
Tokenv
Token ID85
Feature activation-3.04e+00

Pos logit contributions
 brothers+0.039
 friends+0.036
 importantly+0.033
 villains+0.029
 families+0.027
Neg logit contributions
aman-0.113
pp-0.103
al-0.096
OO-0.093
 cash-0.092
Tokenroom
Token ID3823
Feature activation-1.25e+00

Pos logit contributions
 brothers+0.174
 importantly+0.169
 friends+0.168
 villains+0.160
 exciting+0.156
Neg logit contributions
aman-0.139
pp-0.120
al-0.109
OO-0.102
 cash-0.096
Token noises
Token ID26782
Feature activation+3.15e-01

Pos logit contributions
 brothers+0.048
 friends+0.045
 importantly+0.043
 villains+0.039
 families+0.037
Neg logit contributions
aman-0.086
pp-0.077
al-0.071
OO-0.068
 cash-0.067
Token.
Token ID13
Feature activation-5.46e-01

Pos logit contributions
aman+0.019
pp+0.017
al+0.015
OO+0.014
 cash+0.014
Neg logit contributions
 brothers-0.015
 friends-0.014
 importantly-0.013
 villains-0.013
 families-0.012
Token One
Token ID1881
Feature activation-1.37e-01

Pos logit contributions
 brothers+0.030
 friends+0.029
 importantly+0.029
 villains+0.028
 families+0.027
Neg logit contributions
aman-0.028
pp-0.023
 cash-0.020
al-0.020
OO-0.020
Token day
Token ID1110
Feature activation-8.60e-02

Pos logit contributions
 brothers+0.006
 importantly+0.006
 friends+0.006
 villains+0.006
neys+0.005
Neg logit contributions
aman-0.008
pp-0.007
OO-0.006
al-0.006
ah-0.006
Token He
Token ID679
Feature activation-3.64e-01

Pos logit contributions
 brothers+0.002
 importantly+0.001
 friends+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
 cash-0.002
al-0.002
OO-0.002
Token made
Token ID925
Feature activation+9.47e-02

Pos logit contributions
 brothers+0.019
 importantly+0.018
 friends+0.018
 villains+0.017
neys+0.016
Neg logit contributions
aman-0.019
pp-0.017
al-0.015
 cash-0.015
OO-0.014
Token v
Token ID410
Feature activation-5.04e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.005
 friends-0.004
 importantly-0.004
 villains-0.004
 exciting-0.004
Tokenroom
Token ID3823
Feature activation-1.14e+00

Pos logit contributions
 brothers+0.026
 friends+0.025
 importantly+0.023
 villains+0.022
neys+0.022
Neg logit contributions
aman-0.028
pp-0.024
al-0.022
OO-0.021
 cash-0.020
Token-
Token ID12
Feature activation-1.49e+00

Pos logit contributions
 brothers+0.055
 friends+0.054
 importantly+0.047
 villains+0.046
 exciting+0.045
Neg logit contributions
aman-0.070
pp-0.060
al-0.054
OO-0.052
oph-0.050
Tokenv
Token ID85
Feature activation-3.04e+00

Pos logit contributions
 friends+0.064
 brothers+0.064
 villains+0.057
ooters+0.056
 importantly+0.055
Neg logit contributions
aman-0.098
pp-0.079
OO-0.075
al-0.074
oph-0.070
Tokenroom
Token ID3823
Feature activation-9.37e-01

Pos logit contributions
 brothers+0.171
 importantly+0.165
 friends+0.165
 villains+0.157
 exciting+0.151
Neg logit contributions
aman-0.147
pp-0.126
al-0.114
OO-0.106
 cash-0.102
Token noises
Token ID26782
Feature activation+7.48e-01

Pos logit contributions
 brothers+0.041
 friends+0.040
 importantly+0.035
 villains+0.034
 exciting+0.033
Neg logit contributions
aman-0.061
pp-0.053
al-0.049
OO-0.047
oph-0.045
Token and
Token ID290
Feature activation-9.49e-02

Pos logit contributions
aman+0.047
pp+0.042
al+0.038
OO+0.036
 cash+0.035
Neg logit contributions
 brothers-0.034
 friends-0.032
 importantly-0.030
 villains-0.028
 families-0.027
Token drove
Token ID10357
Feature activation-3.09e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
 friends+0.004
neys+0.003
 families+0.003
Neg logit contributions
aman-0.005
pp-0.005
al-0.005
 cash-0.004
OO-0.004
Token it
Token ID340
Feature activation-3.51e-02

Pos logit contributions
 brothers+0.017
 importantly+0.016
 friends+0.016
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.016
pp-0.014
al-0.013
 cash-0.012
OO-0.011
Token They
Token ID1119
Feature activation+4.62e-01

Pos logit contributions
 brothers+0.011
 friends+0.011
 importantly+0.010
 villains+0.010
 families+0.009
Neg logit contributions
aman-0.016
pp-0.014
al-0.013
OO-0.013
 cash-0.013
Token called
Token ID1444
Feature activation-1.10e+00

Pos logit contributions
aman+0.028
pp+0.025
al+0.022
OO+0.021
 cash+0.021
Neg logit contributions
 brothers-0.022
 friends-0.021
 importantly-0.020
 villains-0.018
 families-0.018
Token it
Token ID340
Feature activation-3.93e-01

Pos logit contributions
 brothers+0.050
 friends+0.048
 importantly+0.046
 villains+0.043
 families+0.041
Neg logit contributions
aman-0.067
pp-0.059
al-0.054
OO-0.051
 cash-0.051
Token a
Token ID257
Feature activation-5.95e-01

Pos logit contributions
 brothers+0.018
 friends+0.017
 importantly+0.015
 villains+0.014
 families+0.014
Neg logit contributions
aman-0.025
pp-0.022
al-0.020
OO-0.019
 cash-0.019
Token "
Token ID366
Feature activation-1.04e-02

Pos logit contributions
 brothers+0.018
 friends+0.017
 importantly+0.016
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.045
pp-0.041
al-0.039
OO-0.037
 cash-0.036
Tokenv
Token ID85
Feature activation-3.03e+00

Pos logit contributions
 brothers+0.000
 friends+0.000
 importantly+0.000
 villains+0.000
neys+0.000
Neg logit contributions
aman-0.001
pp-0.001
al-0.000
 cash-0.000
OO-0.000
Tokenac
Token ID330
Feature activation-1.28e+00

Pos logit contributions
 brothers+0.160
 friends+0.155
 importantly+0.132
 families+0.130
 villains+0.127
Neg logit contributions
aman-0.172
pp-0.156
al-0.131
 cash-0.127
oph-0.125
Tokenation
Token ID341
Feature activation+3.74e-01

Pos logit contributions
 importantly+0.064
 brothers+0.063
 villains+0.059
 friends+0.058
 exciting+0.054
Neg logit contributions
aman-0.069
pp-0.058
al-0.055
OO-0.051
 cash-0.050
Token".
Token ID1911
Feature activation+1.08e-01

Pos logit contributions
aman+0.023
pp+0.021
al+0.018
 cash+0.017
OO+0.017
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.015
 villains-0.014
 families-0.014
Token They
Token ID1119
Feature activation+2.59e-01

Pos logit contributions
aman+0.007
pp+0.007
al+0.006
OO+0.006
 cash+0.006
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.004
 villains-0.003
 families-0.003
Token packed
Token ID11856
Feature activation+3.85e-01

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
OO+0.012
 cash+0.012
Neg logit contributions
 brothers-0.012
 friends-0.011
 importantly-0.011
 villains-0.010
 families-0.010
Token it
Token ID340
Feature activation-1.21e-01

Pos logit contributions
aman+0.019
pp+0.017
al+0.016
OO+0.015
 cash+0.015
Neg logit contributions
 brothers-0.011
 friends-0.010
 importantly-0.009
 villains-0.009
 families-0.008
Token go
Token ID467
Feature activation-2.81e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.005
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.008
pp-0.007
al-0.006
OO-0.006
 cash-0.006
Token v
Token ID410
Feature activation-6.12e-01

Pos logit contributions
 brothers+0.010
 friends+0.009
 importantly+0.009
 villains+0.008
 families+0.008
Neg logit contributions
aman-0.020
pp-0.018
al-0.017
OO-0.016
 cash-0.016
Tokenroom
Token ID3823
Feature activation-1.45e+00

Pos logit contributions
 brothers+0.035
 friends+0.034
 importantly+0.034
 villains+0.031
 families+0.031
Neg logit contributions
aman-0.029
pp-0.026
al-0.023
OO-0.021
 cash-0.021
Token-
Token ID12
Feature activation-1.22e+00

Pos logit contributions
 brothers+0.060
 friends+0.058
 importantly+0.052
 villains+0.051
 exciting+0.048
Neg logit contributions
aman-0.098
pp-0.086
al-0.079
OO-0.075
oph-0.074
Tokenv
Token ID85
Feature activation-3.03e+00

Pos logit contributions
 brothers+0.051
 friends+0.049
 importantly+0.044
 villains+0.043
neys+0.041
Neg logit contributions
aman-0.081
pp-0.070
al-0.065
OO-0.062
oph-0.061
Tokenroom
Token ID3823
Feature activation-1.22e+00

Pos logit contributions
 brothers+0.175
 importantly+0.174
 friends+0.167
 villains+0.162
 exciting+0.160
Neg logit contributions
aman-0.132
pp-0.113
al-0.106
OO-0.099
 cash-0.090
Token.
Token ID13
Feature activation-4.25e-01

Pos logit contributions
 brothers+0.050
 friends+0.048
 importantly+0.044
 villains+0.042
 families+0.040
Neg logit contributions
aman-0.082
pp-0.073
al-0.067
OO-0.063
 cash-0.062
Token The
Token ID383
Feature activation-5.62e-01

Pos logit contributions
 brothers+0.023
 friends+0.023
 importantly+0.022
 families+0.021
 villains+0.021
Neg logit contributions
aman-0.021
pp-0.017
al-0.016
 cash-0.016
OO-0.014
Token truck
Token ID7779
Feature activation+5.29e-02

Pos logit contributions
 importantly+0.033
 villains+0.031
neys+0.029
 brothers+0.029
 friends+0.029
Neg logit contributions
aman-0.024
 cash-0.021
pp-0.017
 one-0.016
al-0.016
Token loved
Token ID6151
Feature activation+7.36e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.002
 cash+0.002
OO+0.002
Neg logit contributions
 importantly-0.003
 brothers-0.002
 friends-0.002
 villains-0.002
 families-0.002
Token and
Token ID290
Feature activation-1.78e-01

Pos logit contributions
aman+0.021
pp+0.019
oph+0.017
OO+0.016
use+0.016
Neg logit contributions
 brothers-0.010
 friends-0.010
 villains-0.007
 importantly-0.007
 exciting-0.007
Token made
Token ID925
Feature activation+2.00e-01

Pos logit contributions
 brothers+0.008
 friends+0.008
 importantly+0.008
 villains+0.007
 families+0.007
Neg logit contributions
aman-0.011
pp-0.009
al-0.009
OO-0.008
 cash-0.008
Token v
Token ID410
Feature activation-4.78e-01

Pos logit contributions
aman+0.013
pp+0.011
al+0.010
OO+0.010
 cash+0.009
Neg logit contributions
 brothers-0.009
 friends-0.009
 importantly-0.008
 villains-0.008
 families-0.007
Tokenroom
Token ID3823
Feature activation-1.12e+00

Pos logit contributions
 brothers+0.024
 friends+0.023
 importantly+0.021
neys+0.021
 villains+0.021
Neg logit contributions
aman-0.028
pp-0.024
al-0.021
OO-0.020
 cash-0.020
Token-
Token ID12
Feature activation-1.31e+00

Pos logit contributions
 brothers+0.036
 friends+0.035
 importantly+0.028
 villains+0.028
 exciting+0.027
Neg logit contributions
aman-0.087
pp-0.077
al-0.071
OO-0.068
oph-0.068
Tokenv
Token ID85
Feature activation-3.02e+00

Pos logit contributions
 brothers+0.033
 friends+0.032
 villains+0.027
 importantly+0.026
neys+0.025
Neg logit contributions
aman-0.110
pp-0.096
al-0.090
oph-0.088
OO-0.088
Tokenroom
Token ID3823
Feature activation-9.16e-01

Pos logit contributions
 brothers+0.169
 friends+0.163
 importantly+0.161
 villains+0.153
 families+0.147
Neg logit contributions
aman-0.150
pp-0.129
al-0.116
OO-0.108
 cash-0.104
Token noises
Token ID26782
Feature activation+8.52e-01

Pos logit contributions
 brothers+0.027
 friends+0.026
 importantly+0.021
 villains+0.021
 exciting+0.019
Neg logit contributions
aman-0.073
pp-0.066
al-0.061
OO-0.058
oph-0.058
Token.
Token ID13
Feature activation-4.14e-01

Pos logit contributions
aman+0.054
pp+0.048
al+0.044
OO+0.041
 cash+0.041
Neg logit contributions
 brothers-0.038
 friends-0.036
 importantly-0.034
 villains-0.032
 families-0.030
Token
Token ID198
Feature activation-2.90e-01

Pos logit contributions
 brothers+0.017
 importantly+0.016
 friends+0.016
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.026
pp-0.021
OO-0.021
 cash-0.021
al-0.021
Token
Token ID198
Feature activation-9.71e-02

Pos logit contributions
 brothers+0.015
 importantly+0.014
 friends+0.014
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.015
pp-0.012
ara-0.011
OO-0.011
al-0.011
Token back
Token ID736
Feature activation-9.92e-01

Pos logit contributions
 brothers+0.022
 friends+0.021
 importantly+0.020
 villains+0.019
 families+0.018
Neg logit contributions
aman-0.028
pp-0.024
al-0.022
OO-0.021
 cash-0.021
Token to
Token ID284
Feature activation+3.52e-01

Pos logit contributions
 brothers+0.051
 importantly+0.050
 villains+0.046
 friends+0.045
 families+0.042
Neg logit contributions
aman-0.055
pp-0.048
al-0.044
OO-0.040
 cash-0.039
Token Mom
Token ID11254
Feature activation+5.65e-03

Pos logit contributions
aman+0.024
pp+0.021
al+0.019
 cash+0.019
OO+0.018
Neg logit contributions
 brothers-0.014
 friends-0.013
 importantly-0.013
 villains-0.012
neys-0.011
Tokenmy
Token ID1820
Feature activation-6.66e-01

Pos logit contributions
aman+0.000
pp+0.000
al+0.000
OO+0.000
 cash+0.000
Neg logit contributions
 brothers-0.000
 friends-0.000
 importantly-0.000
 villains-0.000
 families-0.000
Token and
Token ID290
Feature activation-8.01e-02

Pos logit contributions
 brothers+0.026
 friends+0.025
 importantly+0.022
 families+0.020
 exciting+0.019
Neg logit contributions
aman-0.045
pp-0.040
al-0.037
OO-0.037
 cash-0.035
Token Daddy
Token ID26926
Feature activation+1.51e+00

Pos logit contributions
 brothers+0.003
 friends+0.003
 importantly+0.003
 families+0.002
 exciting+0.002
Neg logit contributions
aman-0.005
pp-0.005
al-0.004
OO-0.004
 generation-0.004
Token and
Token ID290
Feature activation-4.09e-02

Pos logit contributions
aman+0.094
pp+0.083
al+0.076
OO+0.073
 cash+0.071
Neg logit contributions
 brothers-0.068
 friends-0.065
 importantly-0.061
 villains-0.056
 families-0.055
Token asked
Token ID1965
Feature activation+5.43e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.003
pp-0.002
al-0.002
OO-0.002
 cash-0.002
Token them
Token ID606
Feature activation-7.80e-01

Pos logit contributions
aman+0.032
pp+0.028
al+0.025
OO+0.024
 cash+0.023
Neg logit contributions
 brothers-0.027
 friends-0.026
 importantly-0.024
 villains-0.022
 families-0.022
Token if
Token ID611
Feature activation+7.02e-02

Pos logit contributions
 brothers+0.045
 importantly+0.045
 villains+0.043
 friends+0.042
neys+0.041
Neg logit contributions
aman-0.034
pp-0.030
al-0.026
 cash-0.025
OO-0.022
Token they
Token ID484
Feature activation-1.14e-01

Pos logit contributions
aman+0.005
pp+0.004
al+0.004
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.003
 friends-0.002
 importantly-0.002
 villains-0.002
 families-0.002
Token
Token ID6184
Feature activation+6.68e-01

Pos logit contributions
aman+0.003
pp+0.003
al+0.002
OO+0.002
oph+0.002
Neg logit contributions
 brothers-0.002
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Token
Token ID95
Feature activation+5.66e-01

Pos logit contributions
aman+0.033
pp+0.028
al+0.024
OO+0.023
 cash+0.023
Neg logit contributions
 brothers-0.038
 friends-0.037
 importantly-0.036
 villains-0.035
 exciting-0.033
Token
Token ID26391
Feature activation-5.16e-01

Pos logit contributions
aman+0.028
pp+0.024
al+0.021
OO+0.020
 cash+0.020
Neg logit contributions
 brothers-0.033
 friends-0.031
 importantly-0.030
 villains-0.029
 families-0.028
Token
Token ID129
Feature activation-1.16e+00

Pos logit contributions
 brothers+0.029
 importantly+0.028
 friends+0.027
 villains+0.026
 exciting+0.025
Neg logit contributions
aman-0.025
pp-0.023
OO-0.020
-0.019
al-0.019
Token
Token ID241
Feature activation-4.08e-01

Pos logit contributions
 brothers+0.058
 friends+0.056
 importantly+0.053
 villains+0.051
 exciting+0.049
Neg logit contributions
aman-0.066
pp-0.058
al-0.052
OO-0.048
 cash-0.048
TokenLook
Token ID8567
Feature activation+1.76e+00

Pos logit contributions
 brothers+0.017
 friends+0.017
 importantly+0.016
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.026
pp-0.023
al-0.021
OO-0.020
 cash-0.020
Token at
Token ID379
Feature activation+2.59e-01

Pos logit contributions
aman+0.108
pp+0.096
al+0.086
 cash+0.084
OO+0.081
Neg logit contributions
 brothers-0.081
 friends-0.080
 importantly-0.073
 families-0.066
 villains-0.065
Token the
Token ID262
Feature activation+3.83e-01

Pos logit contributions
aman+0.017
pp+0.015
al+0.013
OO+0.013
 cash+0.013
Neg logit contributions
 brothers-0.011
 friends-0.011
 importantly-0.010
 villains-0.009
 families-0.009
Token fire
Token ID2046
Feature activation+1.07e+00

Pos logit contributions
aman+0.023
pp+0.019
al+0.018
OO+0.017
 cash+0.017
Neg logit contributions
 brothers-0.018
 importantly-0.017
 friends-0.017
 villains-0.016
ooters-0.015
Tokenwork
Token ID1818
Feature activation+9.97e-01

Pos logit contributions
aman+0.043
pp+0.035
al+0.029
OO+0.027
 cash+0.027
Neg logit contributions
 brothers-0.073
 friends-0.070
 importantly-0.068
 villains-0.064
 families-0.063
Token.
Token ID13
Feature activation-8.64e-02

Pos logit contributions
aman+0.063
pp+0.057
al+0.051
OO+0.049
 cash+0.049
Neg logit contributions
 brothers-0.045
 friends-0.043
 importantly-0.040
 families-0.036
 villains-0.036
Token joy
Token ID8716
Feature activation+2.56e-01

Pos logit contributions
 brothers+0.004
 friends+0.004
 importantly+0.004
 villains+0.004
 families+0.003
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
 cash-0.004
OO-0.004
Token because
Token ID780
Feature activation+2.61e-01

Pos logit contributions
aman+0.017
pp+0.015
 cash+0.014
al+0.014
OO+0.013
Neg logit contributions
 brothers-0.011
 friends-0.010
 importantly-0.010
 villains-0.008
 families-0.008
Token of
Token ID286
Feature activation-1.51e-02

Pos logit contributions
aman+0.016
pp+0.013
al+0.013
 cash+0.012
 generation+0.012
Neg logit contributions
 brothers-0.010
 friends-0.010
 villains-0.010
 importantly-0.009
ooters-0.009
Token the
Token ID262
Feature activation+5.67e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.001
pp-0.001
al-0.001
OO-0.001
 cash-0.001
Token brilliant
Token ID10457
Feature activation-4.15e-01

Pos logit contributions
aman+0.034
pp+0.030
al+0.027
OO+0.025
 cash+0.025
Neg logit contributions
 brothers-0.027
 friends-0.026
 importantly-0.025
 villains-0.023
 families-0.022
Token mirror
Token ID10162
Feature activation+2.22e+00

Pos logit contributions
 brothers+0.024
 friends+0.023
 importantly+0.022
 villains+0.020
 families+0.020
Neg logit contributions
aman-0.021
pp-0.019
al-0.016
OO-0.015
 cash-0.015
Token.
Token ID13
Feature activation-2.67e-01

Pos logit contributions
aman+0.148
pp+0.130
al+0.117
OO+0.117
 cash+0.115
Neg logit contributions
 brothers-0.093
 friends-0.090
 importantly-0.082
 villains-0.074
 families-0.073
Token<|endoftext|>
Token ID50256
Feature activation-7.98e-02

Pos logit contributions
 brothers+0.011
 friends+0.010
 importantly+0.010
 villains+0.009
 families+0.009
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
OO-0.013
 cash-0.013
TokenOnce
Token ID7454
Feature activation-1.03e-01

Pos logit contributions
 brothers+0.005
 importantly+0.005
 friends+0.004
 villains+0.004
 exciting+0.004
Neg logit contributions
aman-0.004
pp-0.003
al-0.003
ara-0.003
OO-0.002
Token upon
Token ID2402
Feature activation+8.01e-03

Pos logit contributions
 brothers+0.007
 villains+0.006
 importantly+0.006
 friends+0.006
neys+0.006
Neg logit contributions
aman-0.004
pp-0.003
al-0.003
OO-0.003
oph-0.002
Token a
Token ID257
Feature activation+4.48e-01

Pos logit contributions
aman+0.000
pp+0.000
al+0.000
OO+0.000
 cash+0.000
Neg logit contributions
 brothers-0.000
 friends-0.000
 importantly-0.000
 villains-0.000
 families-0.000
Token smiled
Token ID13541
Feature activation+6.13e-01

Pos logit contributions
aman+0.025
pp+0.022
al+0.020
OO+0.020
 cash+0.019
Neg logit contributions
 brothers-0.016
 friends-0.016
 importantly-0.015
 villains-0.013
 families-0.013
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
aman+0.040
pp+0.036
al+0.033
OO+0.031
 cash+0.031
Neg logit contributions
 brothers-0.026
 friends-0.025
 importantly-0.023
 villains-0.021
 families-0.021
Token said
Token ID531
Feature activation+4.71e-01

Pos logit contributions
aman+0.034
pp+0.031
OO+0.028
al+0.028
 generation+0.027
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.017
 exciting-0.014
 villains-0.014
Token,
Token ID11
Feature activation+2.24e-01

Pos logit contributions
aman+0.034
pp+0.030
al+0.027
 generation+0.026
OO+0.026
Neg logit contributions
 friends-0.018
 brothers-0.018
 importantly-0.016
 villains-0.014
 families-0.013
Token "
Token ID366
Feature activation+1.20e-01

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
OO+0.013
oph+0.012
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.007
 villains-0.006
 families-0.006
TokenHello
Token ID15496
Feature activation+1.59e+00

Pos logit contributions
aman+0.008
pp+0.007
OO+0.007
al+0.006
oph+0.006
Neg logit contributions
 importantly-0.005
 brothers-0.005
 friends-0.005
 villains-0.004
 exciting-0.004
Token,
Token ID11
Feature activation+2.35e-01

Pos logit contributions
aman+0.095
pp+0.084
al+0.076
OO+0.072
 cash+0.071
Neg logit contributions
 brothers-0.076
 friends-0.072
 importantly-0.069
 villains-0.065
 families-0.062
Token kids
Token ID3988
Feature activation-2.23e-01

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
 cash+0.012
OO+0.012
Neg logit contributions
 brothers-0.009
 friends-0.009
 importantly-0.008
 villains-0.008
neys-0.008
Token.
Token ID13
Feature activation+2.60e-01

Pos logit contributions
 brothers+0.009
 friends+0.009
 importantly+0.008
 villains+0.007
 families+0.007
Neg logit contributions
aman-0.015
pp-0.013
al-0.012
OO-0.012
 cash-0.012
Token This
Token ID770
Feature activation+7.57e-01

Pos logit contributions
aman+0.017
pp+0.015
al+0.013
OO+0.013
oph+0.013
Neg logit contributions
 brothers-0.011
 friends-0.011
 importantly-0.010
 villains-0.010
 families-0.009
Token bike
Token ID7161
Feature activation+4.16e-01

Pos logit contributions
aman+0.049
pp+0.044
al+0.040
OO+0.039
oph+0.038
Neg logit contributions
 brothers-0.033
 friends-0.032
 importantly-0.027
 villains-0.027
 exciting-0.026
Token being
Token ID852
Feature activation-9.17e-01

Pos logit contributions
aman+0.041
pp+0.037
al+0.034
OO+0.033
 cash+0.032
Neg logit contributions
 brothers-0.021
 friends-0.020
 importantly-0.019
 villains-0.018
 families-0.016
Token kind
Token ID1611
Feature activation-8.50e-01

Pos logit contributions
 brothers+0.033
 friends+0.030
 importantly+0.030
 villains+0.029
neys+0.027
Neg logit contributions
aman-0.060
pp-0.056
al-0.053
 cash-0.048
OO-0.048
Token and
Token ID290
Feature activation+3.55e-01

Pos logit contributions
 brothers+0.038
 friends+0.036
 importantly+0.035
 villains+0.032
 families+0.031
Neg logit contributions
aman-0.052
pp-0.046
al-0.043
OO-0.040
 cash-0.039
Token sharing
Token ID7373
Feature activation+2.76e-01

Pos logit contributions
aman+0.021
pp+0.021
al+0.019
 cash+0.018
 generation+0.017
Neg logit contributions
 brothers-0.013
 villains-0.012
 importantly-0.012
 friends-0.012
ooters-0.011
Token the
Token ID262
Feature activation+5.25e-01

Pos logit contributions
aman+0.017
pp+0.015
al+0.014
OO+0.013
 cash+0.013
Neg logit contributions
 brothers-0.012
 friends-0.011
 importantly-0.011
 villains-0.010
 families-0.010
Token diamond
Token ID15291
Feature activation+1.52e+00

Pos logit contributions
aman+0.032
pp+0.028
al+0.026
 cash+0.024
OO+0.024
Neg logit contributions
 brothers-0.024
 friends-0.023
 importantly-0.022
 villains-0.021
 families-0.020
Token with
Token ID351
Feature activation+5.00e-01

Pos logit contributions
aman+0.091
pp+0.082
al+0.075
OO+0.069
 cash+0.069
Neg logit contributions
 brothers-0.069
 friends-0.065
 importantly-0.065
 villains-0.060
 families-0.057
Token them
Token ID606
Feature activation-4.89e-01

Pos logit contributions
aman+0.032
pp+0.028
al+0.026
OO+0.024
 cash+0.024
Neg logit contributions
 brothers-0.022
 friends-0.020
 importantly-0.020
 villains-0.018
 families-0.017
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 brothers+0.022
 friends+0.020
 importantly+0.020
 villains+0.019
 families+0.018
Neg logit contributions
aman-0.030
pp-0.027
al-0.025
OO-0.023
 cash-0.023
Token From
Token ID3574
Feature activation-1.48e-01

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 exciting+0.001
Neg logit contributions
aman-0.001
pp-0.001
al-0.001
 cash-0.001
OO-0.001
Token then
Token ID788
Feature activation+1.42e-01

Pos logit contributions
 brothers+0.008
 friends+0.008
 importantly+0.007
 villains+0.007
 families+0.007
Neg logit contributions
aman-0.008
pp-0.007
al-0.006
 cash-0.006
OO-0.005
Token was
Token ID373
Feature activation+1.13e-01

Pos logit contributions
 brothers+0.007
 friends+0.007
 importantly+0.007
 villains+0.006
 families+0.006
Neg logit contributions
aman-0.010
pp-0.009
al-0.008
 cash-0.008
OO-0.008
Token cozy
Token ID37438
Feature activation-1.11e+00

Pos logit contributions
aman+0.008
pp+0.007
al+0.007
OO+0.006
 cash+0.006
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.004
 villains-0.003
 families-0.003
Token once
Token ID1752
Feature activation-1.02e+00

Pos logit contributions
 brothers+0.051
 friends+0.049
 importantly+0.047
 villains+0.043
 families+0.042
Neg logit contributions
aman-0.068
pp-0.060
al-0.055
OO-0.052
 cash-0.051
Token again
Token ID757
Feature activation-3.23e-01

Pos logit contributions
 brothers+0.051
 friends+0.048
 importantly+0.047
 villains+0.045
 families+0.042
Neg logit contributions
aman-0.058
pp-0.050
al-0.046
OO-0.043
 cash-0.042
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.010
 families+0.010
Neg logit contributions
aman-0.022
pp-0.019
al-0.018
 cash-0.017
OO-0.017
Token<|endoftext|>
Token ID50256
Feature activation-4.45e-02

Pos logit contributions
 brothers+0.009
 friends+0.008
 villains+0.008
 importantly+0.008
 families+0.008
Neg logit contributions
aman-0.012
pp-0.011
al-0.010
OO-0.010
 cash-0.009
TokenOnce
Token ID7454
Feature activation-2.44e-01

Pos logit contributions
 brothers+0.002
 importantly+0.002
 friends+0.002
 villains+0.002
 exciting+0.002
Neg logit contributions
aman-0.002
al-0.002
pp-0.002
ara-0.002
OO-0.002
Token upon
Token ID2402
Feature activation-1.15e-01

Pos logit contributions
 villains+0.016
 brothers+0.016
 importantly+0.016
 friends+0.015
neys+0.015
Neg logit contributions
aman-0.009
pp-0.007
OO-0.005
al-0.005
ara-0.005
Token a
Token ID257
Feature activation+2.75e-01

Pos logit contributions
 brothers+0.006
 friends+0.006
 importantly+0.006
 villains+0.005
 families+0.005
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
OO-0.005
 cash-0.004
Token time
Token ID640
Feature activation-1.76e-01

Pos logit contributions
aman+0.019
pp+0.018
al+0.017
 cash+0.016
OO+0.015
Neg logit contributions
 brothers-0.010
 friends-0.009
 importantly-0.009
 exciting-0.008
 villains-0.007
Token there
Token ID612
Feature activation-4.33e-01

Pos logit contributions
 brothers+0.009
 friends+0.008
 importantly+0.008
 villains+0.008
 families+0.007
Neg logit contributions
aman-0.010
pp-0.009
al-0.008
OO-0.008
 cash-0.007
Token coat
Token ID13209
Feature activation+2.54e-02

Pos logit contributions
 friends+0.007
 brothers+0.006
 trees+0.005
 legs+0.005
 days+0.005
Neg logit contributions
aman-0.012
pp-0.011
oph-0.009
ited-0.009
OO-0.009
Token.
Token ID13
Feature activation+1.90e-02

Pos logit contributions
aman+0.002
pp+0.002
OO+0.002
oph+0.002
use+0.002
Neg logit contributions
 brothers-0.001
 friends-0.001
 of-0.000
 having-0.000
 importantly-0.000
Token It
Token ID632
Feature activation+4.18e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
 cash+0.001
OO+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.000
Token is
Token ID318
Feature activation+2.38e-01

Pos logit contributions
aman+0.029
pp+0.025
OO+0.023
oph+0.022
al+0.022
Neg logit contributions
 brothers-0.018
 friends-0.017
 villains-0.014
 importantly-0.014
 exciting-0.014
Token rough
Token ID5210
Feature activation+1.86e-01

Pos logit contributions
aman+0.015
pp+0.013
al+0.012
OO+0.011
 cash+0.011
Neg logit contributions
 brothers-0.010
 friends-0.010
 importantly-0.010
 villains-0.009
 families-0.009
Token and
Token ID290
Feature activation+5.18e-01

Pos logit contributions
aman+0.012
pp+0.010
al+0.010
OO+0.009
 cash+0.009
Neg logit contributions
 brothers-0.008
 friends-0.008
 importantly-0.007
 villains-0.007
 families-0.007
Token sc
Token ID629
Feature activation-6.91e-02

Pos logit contributions
aman+0.032
pp+0.029
al+0.027
OO+0.025
 cash+0.025
Neg logit contributions
 brothers-0.020
 friends-0.019
 importantly-0.018
 families-0.017
 pals-0.017
Tokenaly
Token ID3400
Feature activation+1.72e-01

Pos logit contributions
 brothers+0.003
 friends+0.003
 importantly+0.003
 villains+0.003
ooters+0.003
Neg logit contributions
aman-0.004
pp-0.004
al-0.004
 cash-0.003
oph-0.003
Token.
Token ID13
Feature activation+2.13e-02

Pos logit contributions
aman+0.012
pp+0.011
 cash+0.009
al+0.009
oph+0.009
Neg logit contributions
 brothers-0.007
 friends-0.007
 importantly-0.006
 villains-0.006
 families-0.005
Token He
Token ID679
Feature activation-3.71e-03

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
 cash+0.001
OO+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Token says
Token ID1139
Feature activation-4.64e-01

Pos logit contributions
 brothers+0.000
 friends+0.000
 importantly+0.000
 villains+0.000
 families+0.000
Neg logit contributions
aman-0.000
pp-0.000
al-0.000
OO-0.000
 cash-0.000
Token cleaning
Token ID12724
Feature activation+2.79e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
ooters+0.004
neys+0.004
 friends+0.004
Neg logit contributions
aman-0.004
pp-0.004
al-0.003
 cash-0.003
 generation-0.003
Token a
Token ID257
Feature activation+5.44e-01

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
OO+0.012
 cash+0.011
Neg logit contributions
 brothers-0.013
 importantly-0.013
 friends-0.012
 villains-0.012
ooters-0.011
Token wound
Token ID11699
Feature activation-4.77e-01

Pos logit contributions
aman+0.035
pp+0.030
al+0.028
OO+0.027
 cash+0.027
Neg logit contributions
 brothers-0.022
 importantly-0.021
 friends-0.020
 villains-0.019
neys-0.018
Token can
Token ID460
Feature activation+3.98e-01

Pos logit contributions
 brothers+0.021
 friends+0.020
 importantly+0.018
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.031
pp-0.027
al-0.025
OO-0.024
 cash-0.024
Token help
Token ID1037
Feature activation-6.86e-01

Pos logit contributions
aman+0.026
pp+0.023
al+0.021
OO+0.020
 cash+0.020
Neg logit contributions
 brothers-0.017
 friends-0.016
 importantly-0.015
 villains-0.014
 families-0.014
Token make
Token ID787
Feature activation+1.30e-02

Pos logit contributions
 brothers+0.033
 importantly+0.032
 friends+0.031
 villains+0.028
 families+0.027
Neg logit contributions
aman-0.039
pp-0.034
al-0.031
OO-0.029
 cash-0.029
Token it
Token ID340
Feature activation+2.32e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
 cash+0.001
OO+0.001
Neg logit contributions
 brothers-0.001
 importantly-0.001
 friends-0.000
 villains-0.000
 families-0.000
Token better
Token ID1365
Feature activation-2.86e-01

Pos logit contributions
aman+0.014
pp+0.013
al+0.011
OO+0.011
 cash+0.011
Neg logit contributions
 brothers-0.010
 importantly-0.010
 friends-0.010
 villains-0.009
 families-0.008
Token,
Token ID11
Feature activation+7.52e-02

Pos logit contributions
 brothers+0.014
 friends+0.013
 importantly+0.013
 villains+0.012
 families+0.011
Neg logit contributions
aman-0.017
pp-0.015
al-0.013
OO-0.013
 cash-0.012
Token but
Token ID475
Feature activation-6.55e-01

Pos logit contributions
aman+0.005
pp+0.004
al+0.004
 cash+0.004
OO+0.004
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.003
 villains-0.003
 families-0.003
Token sometimes
Token ID3360
Feature activation-8.38e-01

Pos logit contributions
 brothers+0.029
 friends+0.027
 importantly+0.026
 villains+0.025
 families+0.024
Neg logit contributions
aman-0.041
pp-0.036
al-0.032
 cash-0.031
OO-0.030
Token scared
Token ID12008
Feature activation-2.87e-01

Pos logit contributions
 importantly+0.016
 brothers+0.015
 villains+0.015
 friends+0.014
 families+0.013
Neg logit contributions
aman-0.018
pp-0.017
 cash-0.016
al-0.016
OO-0.014
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
 brothers+0.015
 importantly+0.015
 villains+0.015
 friends+0.014
neys+0.014
Neg logit contributions
aman-0.013
al-0.011
pp-0.010
OO-0.009
y-0.009
Token Sam
Token ID3409
Feature activation-6.44e-01

Pos logit contributions
aman+0.016
OO+0.013
al+0.013
 cash+0.013
pp+0.013
Neg logit contributions
 importantly-0.011
 brothers-0.010
 friends-0.010
 families-0.010
 villains-0.010
Token saw
Token ID2497
Feature activation-4.54e-02

Pos logit contributions
 importantly+0.034
 brothers+0.033
 friends+0.031
neys+0.029
 villains+0.029
Neg logit contributions
aman-0.032
pp-0.028
al-0.028
 cash-0.025
OO-0.025
Token Tim
Token ID5045
Feature activation-9.46e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.002
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.003
pp-0.003
al-0.003
OO-0.002
 cash-0.002
Token and
Token ID290
Feature activation+3.08e-01

Pos logit contributions
 brothers+0.044
 friends+0.042
 importantly+0.042
 villains+0.039
 families+0.037
Neg logit contributions
aman-0.056
pp-0.050
al-0.045
OO-0.043
 cash-0.042
Token ran
Token ID4966
Feature activation-1.03e-01

Pos logit contributions
aman+0.017
pp+0.015
al+0.014
 cash+0.013
OO+0.013
Neg logit contributions
 importantly-0.014
 brothers-0.014
 friends-0.013
 villains-0.013
neys-0.012
Token to
Token ID284
Feature activation+3.10e-01

Pos logit contributions
 brothers+0.005
 friends+0.005
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.006
pp-0.005
al-0.005
OO-0.005
 cash-0.005
Token get
Token ID651
Feature activation-5.82e-01

Pos logit contributions
aman+0.019
pp+0.016
al+0.015
 cash+0.015
OO+0.014
Neg logit contributions
 brothers-0.014
 importantly-0.014
 friends-0.013
 villains-0.012
neys-0.012
Token help
Token ID1037
Feature activation-4.21e-01

Pos logit contributions
 importantly+0.030
 brothers+0.029
 villains+0.027
 friends+0.026
neys+0.026
Neg logit contributions
aman-0.028
pp-0.025
al-0.025
 cash-0.024
use-0.021
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
 importantly+0.024
 brothers+0.023
 friends+0.021
 villains+0.021
neys+0.020
Neg logit contributions
aman-0.020
pp-0.017
al-0.016
 cash-0.015
OO-0.014
Token So
Token ID1406
Feature activation-5.20e-01

Pos logit contributions
 brothers+0.002
 friends+0.002
 importantly+0.001
 villains+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
al-0.002
OO-0.002
 cash-0.002
Token,
Token ID11
Feature activation+6.41e-02

Pos logit contributions
 friends+0.023
 brothers+0.022
 importantly+0.020
 exciting+0.018
 families+0.018
Neg logit contributions
aman-0.034
pp-0.031
OO-0.027
al-0.027
 cash-0.025
Token she
Token ID673
Feature activation-3.53e-01

Pos logit contributions
aman+0.004
pp+0.003
OO+0.003
al+0.003
oph+0.003
Neg logit contributions
 friends-0.003
 brothers-0.003
 importantly-0.003
 families-0.003
 exciting-0.003
Token opened
Token ID4721
Feature activation+4.51e-02

Pos logit contributions
 brothers+0.017
 friends+0.017
 importantly+0.015
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.021
pp-0.018
al-0.016
OO-0.016
 cash-0.015
Token her
Token ID607
Feature activation-6.34e-01

Pos logit contributions
aman+0.003
pp+0.003
OO+0.003
use+0.003
 cash+0.003
Neg logit contributions
 friends-0.001
 brothers-0.001
 exciting-0.001
 trees-0.001
 having-0.001
Token hands
Token ID2832
Feature activation-4.99e-01

Pos logit contributions
 brothers+0.025
 friends+0.024
 importantly+0.022
 villains+0.020
 families+0.020
Neg logit contributions
aman-0.043
pp-0.039
al-0.035
OO-0.034
 cash-0.034
Token and
Token ID290
Feature activation-3.13e-01

Pos logit contributions
 friends+0.016
 brothers+0.016
 importantly+0.012
 having+0.011
 exciting+0.011
Neg logit contributions
aman-0.037
pp-0.033
OO-0.032
 cash-0.030
use-0.030
Token the
Token ID262
Feature activation-6.68e-02

Pos logit contributions
 friends+0.014
 brothers+0.013
 families+0.011
 importantly+0.011
 exciting+0.010
Neg logit contributions
aman-0.021
pp-0.018
OO-0.017
 cash-0.015
al-0.015
Token butterfly
Token ID35113
Feature activation+9.07e-01

Pos logit contributions
 brothers+0.004
 friends+0.003
 importantly+0.003
 villains+0.003
 families+0.003
Neg logit contributions
aman-0.004
pp-0.003
al-0.003
OO-0.003
 cash-0.003
Token flew
Token ID13112
Feature activation+4.62e-01

Pos logit contributions
aman+0.056
pp+0.047
OO+0.044
 cash+0.042
al+0.041
Neg logit contributions
 friends-0.044
 brothers-0.041
 importantly-0.036
 families-0.035
 exciting-0.035
Token away
Token ID1497
Feature activation+2.70e-01

Pos logit contributions
aman+0.029
pp+0.025
OO+0.023
al+0.022
 cash+0.022
Neg logit contributions
 friends-0.021
 brothers-0.021
 importantly-0.018
 exciting-0.018
 villains-0.017
Token no
Token ID645
Feature activation+4.88e-01

Pos logit contributions
 brothers+0.000
 friends+0.000
 importantly+0.000
 villains+0.000
 families+0.000
Neg logit contributions
aman-0.001
pp-0.001
al-0.000
OO-0.000
 cash-0.000
Token!
Token ID0
Feature activation+1.61e-01

Pos logit contributions
aman+0.028
pp+0.024
al+0.022
OO+0.022
 cash+0.021
Neg logit contributions
 brothers-0.024
 friends-0.023
 importantly-0.022
 villains-0.021
 families-0.020
Token What
Token ID1867
Feature activation+1.64e-01

Pos logit contributions
aman+0.010
pp+0.009
al+0.008
oph+0.007
 cash+0.007
Neg logit contributions
 brothers-0.008
 friends-0.007
 importantly-0.007
 villains-0.006
 families-0.006
Token did
Token ID750
Feature activation-5.71e-01

Pos logit contributions
aman+0.007
pp+0.006
OO+0.006
al+0.006
 heaven+0.005
Neg logit contributions
 importantly-0.009
 brothers-0.009
ooters-0.008
 friends-0.008
 olds-0.008
Token you
Token ID345
Feature activation+1.02e+00

Pos logit contributions
 brothers+0.031
 importantly+0.029
 friends+0.029
neys+0.026
 villains+0.026
Neg logit contributions
aman-0.028
pp-0.023
al-0.022
 cash-0.020
OO-0.020
Token do
Token ID466
Feature activation-8.30e-01

Pos logit contributions
aman+0.089
pp+0.081
al+0.075
 cash+0.073
 generation+0.072
Neg logit contributions
 brothers-0.024
 friends-0.022
 importantly-0.015
 exciting-0.014
 villains-0.013
Token?
Token ID30
Feature activation+4.19e-01

Pos logit contributions
 brothers+0.053
 friends+0.051
 importantly+0.050
 villains+0.048
 families+0.047
Neg logit contributions
aman-0.035
pp-0.029
al-0.026
OO-0.023
 cash-0.023
Token You
Token ID921
Feature activation+7.33e-01

Pos logit contributions
aman+0.027
pp+0.023
oph+0.020
al+0.020
OO+0.019
Neg logit contributions
 brothers-0.020
 friends-0.018
 importantly-0.017
 villains-0.016
neys-0.016
Token should
Token ID815
Feature activation-8.54e-01

Pos logit contributions
aman+0.040
pp+0.036
al+0.034
OO+0.031
 cash+0.030
Neg logit contributions
 brothers-0.035
 importantly-0.035
 friends-0.033
 villains-0.031
 exciting-0.030
Token not
Token ID407
Feature activation-2.87e-01

Pos logit contributions
 brothers+0.029
 friends+0.028
 importantly+0.023
 villains+0.023
 families+0.022
Neg logit contributions
aman-0.064
pp-0.059
al-0.053
OO-0.052
oph-0.050
Token play
Token ID711
Feature activation+1.38e-01

Pos logit contributions
 brothers+0.013
 friends+0.013
 importantly+0.012
 villains+0.011
 families+0.011
Neg logit contributions
aman-0.018
pp-0.016
al-0.014
OO-0.013
 cash-0.013
Token than
Token ID621
Feature activation+9.76e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
OO+0.001
+0.001
Neg logit contributions
 brothers-0.001
 importantly-0.001
 villains-0.001
 friends-0.001
 Seek-0.001
Token being
Token ID852
Feature activation-9.19e-01

Pos logit contributions
aman+0.062
pp+0.055
al+0.050
OO+0.048
 cash+0.048
Neg logit contributions
 brothers-0.042
 friends-0.039
 importantly-0.038
 villains-0.035
 families-0.033
Token strong
Token ID1913
Feature activation-8.59e-01

Pos logit contributions
 brothers+0.034
 importantly+0.032
 friends+0.031
 villains+0.031
ooters+0.028
Neg logit contributions
aman-0.057
pp-0.054
al-0.050
OO-0.047
 cash-0.045
Token.
Token ID13
Feature activation+6.65e-02

Pos logit contributions
 brothers+0.040
 friends+0.038
 importantly+0.038
 villains+0.035
 families+0.033
Neg logit contributions
aman-0.049
pp-0.044
al-0.041
OO-0.038
 cash-0.037
Token<|endoftext|>
Token ID50256
Feature activation-3.04e-01

Pos logit contributions
aman+0.004
pp+0.004
al+0.003
OO+0.003
 cash+0.003
Neg logit contributions
 brothers-0.003
 friends-0.003
 importantly-0.002
 villains-0.002
 families-0.002
TokenTom
Token ID13787
Feature activation-9.11e-01

Pos logit contributions
 brothers+0.019
 importantly+0.019
 friends+0.019
 villains+0.019
 exciting+0.018
Neg logit contributions
aman-0.011
pp-0.010
al-0.009
OO-0.007
ara-0.007
Token and
Token ID290
Feature activation-6.47e-01

Pos logit contributions
 brothers+0.039
 friends+0.035
 boys+0.027
 kids+0.026
 families+0.026
Neg logit contributions
aman-0.065
pp-0.058
 cash-0.051
 generation-0.051
OO-0.051
Token Anna
Token ID11735
Feature activation+8.62e-02

Pos logit contributions
 brothers+0.029
 friends+0.027
 importantly+0.027
 villains+0.025
neys+0.024
Neg logit contributions
aman-0.039
pp-0.035
al-0.032
 cash-0.030
OO-0.030
Token were
Token ID547
Feature activation-1.45e-01

Pos logit contributions
aman+0.007
pp+0.006
OO+0.005
 cash+0.005
oph+0.005
Neg logit contributions
 brothers-0.003
 friends-0.003
 families-0.002
 kids-0.002
 boys-0.002
Token twins
Token ID20345
Feature activation-5.09e-01

Pos logit contributions
 brothers+0.004
 importantly+0.004
 villains+0.004
 friends+0.004
neys+0.004
Neg logit contributions
aman-0.011
pp-0.010
al-0.009
OO-0.009
 cash-0.009
Token,
Token ID11
Feature activation+2.49e-01

Pos logit contributions
 brothers+0.022
 friends+0.021
 importantly+0.020
 villains+0.019
 families+0.018
Neg logit contributions
aman-0.032
pp-0.028
al-0.026
OO-0.025
 cash-0.024
Token lovely
Token ID14081
Feature activation-4.21e-01

Pos logit contributions
 brothers+0.008
 friends+0.007
 importantly+0.007
 villains+0.006
 families+0.006
Neg logit contributions
aman-0.014
pp-0.012
al-0.011
OO-0.011
 cash-0.011
Token yell
Token ID28946
Feature activation+5.09e-01

Pos logit contributions
 brothers+0.016
 friends+0.016
 importantly+0.015
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.029
pp-0.026
al-0.024
OO-0.023
 cash-0.022
Tokenows
Token ID1666
Feature activation-1.71e+00

Pos logit contributions
aman+0.036
pp+0.031
al+0.028
 cash+0.027
OO+0.027
Neg logit contributions
 brothers-0.021
 friends-0.020
 importantly-0.017
 villains-0.016
 exciting-0.016
Token,
Token ID11
Feature activation+2.99e-01

Pos logit contributions
 friends+0.058
 brothers+0.057
 exciting+0.048
 importantly+0.047
 families+0.044
Neg logit contributions
aman-0.123
pp-0.114
OO-0.103
al-0.101
 cash-0.100
Token so
Token ID523
Feature activation-2.60e-01

Pos logit contributions
aman+0.019
pp+0.017
al+0.016
 cash+0.015
OO+0.015
Neg logit contributions
 brothers-0.013
 friends-0.012
 importantly-0.011
 villains-0.011
neys-0.010
Token she
Token ID673
Feature activation-5.64e-01

Pos logit contributions
 brothers+0.014
 friends+0.014
 importantly+0.013
 villains+0.012
 families+0.012
Neg logit contributions
aman-0.014
pp-0.012
al-0.011
OO-0.010
 cash-0.010
Token opened
Token ID4721
Feature activation+4.99e-02

Pos logit contributions
 brothers+0.027
 friends+0.026
 importantly+0.025
 villains+0.023
 families+0.022
Neg logit contributions
aman-0.033
pp-0.029
al-0.027
OO-0.025
 cash-0.025
Token her
Token ID607
Feature activation-5.40e-01

Pos logit contributions
pp+0.004
aman+0.004
OO+0.004
lder+0.003
use+0.003
Neg logit contributions
 friends-0.002
 brothers-0.001
 trees-0.001
 exciting-0.001
 having-0.001
Token window
Token ID4324
Feature activation-6.78e-01

Pos logit contributions
 brothers+0.022
 friends+0.021
 importantly+0.020
 villains+0.019
 families+0.018
Neg logit contributions
aman-0.036
pp-0.031
al-0.029
OO-0.028
 cash-0.027
Token.
Token ID13
Feature activation-2.47e-01

Pos logit contributions
 brothers+0.021
 friends+0.021
 importantly+0.018
 exciting+0.017
 families+0.015
Neg logit contributions
aman-0.049
pp-0.047
OO-0.043
al-0.041
 cash-0.040
Token But
Token ID887
Feature activation-1.80e-01

Pos logit contributions
 brothers+0.010
 friends+0.010
 importantly+0.009
 villains+0.008
 exciting+0.008
Neg logit contributions
aman-0.016
pp-0.015
al-0.013
 cash-0.012
OO-0.012
Token fun
Token ID1257
Feature activation+3.43e-01

Pos logit contributions
aman+0.016
pp+0.014
al+0.013
 cash+0.012
OO+0.012
Neg logit contributions
 brothers-0.009
 friends-0.009
 importantly-0.008
 villains-0.008
 families-0.007
Token to
Token ID284
Feature activation+8.08e-01

Pos logit contributions
aman+0.021
pp+0.018
al+0.017
OO+0.016
 cash+0.015
Neg logit contributions
 brothers-0.016
 friends-0.015
 importantly-0.015
 villains-0.014
 families-0.013
Token do
Token ID466
Feature activation-6.83e-01

Pos logit contributions
aman+0.053
pp+0.047
al+0.043
OO+0.041
 cash+0.040
Neg logit contributions
 brothers-0.034
 friends-0.033
 importantly-0.030
 villains-0.029
 families-0.028
Token things
Token ID1243
Feature activation+6.63e-01

Pos logit contributions
 brothers+0.029
 friends+0.028
 importantly+0.027
 villains+0.025
 families+0.024
Neg logit contributions
aman-0.044
pp-0.039
al-0.036
OO-0.034
 cash-0.034
Token all
Token ID477
Feature activation-5.53e-02

Pos logit contributions
aman+0.041
pp+0.036
al+0.033
OO+0.032
 cash+0.031
Neg logit contributions
 brothers-0.030
 friends-0.029
 importantly-0.027
 villains-0.025
 families-0.024
Token by
Token ID416
Feature activation-5.50e-01

Pos logit contributions
 brothers+0.003
 friends+0.002
 importantly+0.002
 villains+0.002
 families+0.002
Neg logit contributions
aman-0.003
pp-0.003
al-0.003
OO-0.002
 cash-0.002
Token yourself
Token ID3511
Feature activation+9.37e-01

Pos logit contributions
 brothers+0.023
 friends+0.023
 importantly+0.020
 families+0.019
 having+0.018
Neg logit contributions
aman-0.036
pp-0.032
al-0.029
OO-0.029
 cash-0.029
Token,
Token ID11
Feature activation-9.74e-02

Pos logit contributions
aman+0.061
pp+0.055
al+0.049
OO+0.048
 cash+0.048
Neg logit contributions
 brothers-0.039
 friends-0.038
 importantly-0.035
 villains-0.033
 families-0.032
Token it
Token ID340
Feature activation+2.26e-01

Pos logit contributions
 brothers+0.005
 friends+0.004
 importantly+0.004
 villains+0.004
neys+0.004
Neg logit contributions
aman-0.005
pp-0.005
al-0.004
 cash-0.004
OO-0.004
Token is
Token ID318
Feature activation+2.05e-03

Pos logit contributions
aman+0.012
pp+0.011
al+0.010
OO+0.009
 cash+0.009
Neg logit contributions
 brothers-0.012
 friends-0.011
 importantly-0.011
 villains-0.010
 families-0.010
Token always
Token ID1464
Feature activation-2.49e-01

Pos logit contributions
aman+0.000
pp+0.000
al+0.000
OO+0.000
 cash+0.000
Neg logit contributions
 brothers-0.000
 friends-0.000
 importantly-0.000
 exciting-0.000
 villains-0.000
Token share
Token ID2648
Feature activation-2.02e-01

Pos logit contributions
aman+0.026
pp+0.024
al+0.021
OO+0.021
oph+0.020
Neg logit contributions
 brothers-0.017
 friends-0.017
 importantly-0.015
 villains-0.014
 exciting-0.014
Token,
Token ID11
Feature activation+4.33e-01

Pos logit contributions
 brothers+0.009
 importantly+0.008
 friends+0.008
 villains+0.008
neys+0.007
Neg logit contributions
aman-0.013
pp-0.011
al-0.010
 cash-0.010
OO-0.009
Token instead
Token ID2427
Feature activation-6.45e-01

Pos logit contributions
aman+0.027
pp+0.023
al+0.021
 cash+0.020
OO+0.019
Neg logit contributions
 brothers-0.019
 friends-0.018
 importantly-0.017
 villains-0.017
 families-0.016
Token of
Token ID286
Feature activation+9.78e-02

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.013
 villains+0.011
 families+0.010
Neg logit contributions
aman-0.053
pp-0.048
al-0.046
OO-0.043
 cash-0.043
Token always
Token ID1464
Feature activation+7.81e-01

Pos logit contributions
aman+0.007
pp+0.006
al+0.006
OO+0.005
 cash+0.005
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.003
 villains-0.003
 families-0.003
Token being
Token ID852
Feature activation-1.05e+00

Pos logit contributions
aman+0.051
pp+0.045
al+0.041
OO+0.040
 cash+0.039
Neg logit contributions
 brothers-0.034
 friends-0.033
 importantly-0.031
 villains-0.028
 exciting-0.027
Token nos
Token ID43630
Feature activation-1.20e+00

Pos logit contributions
 brothers+0.035
 friends+0.032
 importantly+0.032
 villains+0.030
 families+0.027
Neg logit contributions
aman-0.073
pp-0.067
al-0.063
OO-0.059
 cash-0.059
Tokeny
Token ID88
Feature activation+8.41e-01

Pos logit contributions
 brothers+0.102
 friends+0.099
 importantly+0.097
 villains+0.094
 families+0.092
Neg logit contributions
aman-0.026
pp-0.018
al-0.012
OO-0.009
 cash-0.007
Token and
Token ID290
Feature activation+1.05e-01

Pos logit contributions
aman+0.051
pp+0.045
al+0.041
OO+0.039
 cash+0.038
Neg logit contributions
 brothers-0.038
 friends-0.036
 importantly-0.035
 villains-0.033
 families-0.031
Token wanting
Token ID10291
Feature activation-4.68e-01

Pos logit contributions
aman+0.007
pp+0.006
al+0.006
OO+0.005
 cash+0.005
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.004
 villains-0.003
 families-0.003
Token to
Token ID284
Feature activation+3.66e-01

Pos logit contributions
 brothers+0.021
 importantly+0.019
 friends+0.019
 villains+0.018
neys+0.017
Neg logit contributions
aman-0.028
pp-0.025
al-0.023
 cash-0.022
OO-0.021
Token castle
Token ID16669
Feature activation-1.43e-02

Pos logit contributions
aman+0.050
pp+0.045
al+0.041
OO+0.040
 cash+0.038
Neg logit contributions
 brothers-0.022
 friends-0.022
 importantly-0.019
 villains-0.018
 exciting-0.017
Token that
Token ID326
Feature activation-1.03e+00

Pos logit contributions
 friends+0.001
 brothers+0.001
 importantly+0.000
 villains+0.000
 families+0.000
Neg logit contributions
aman-0.001
pp-0.001
OO-0.001
al-0.001
 cash-0.001
Token was
Token ID373
Feature activation-6.04e-02

Pos logit contributions
 friends+0.042
 brothers+0.042
 importantly+0.033
 exciting+0.032
 families+0.032
Neg logit contributions
aman-0.074
pp-0.063
OO-0.061
 cash-0.056
oph-0.056
Token one
Token ID530
Feature activation+1.77e-01

Pos logit contributions
 brothers+0.003
 friends+0.002
 importantly+0.002
 villains+0.002
 exciting+0.002
Neg logit contributions
aman-0.004
pp-0.004
al-0.003
OO-0.003
 cash-0.003
Token hundred
Token ID3470
Feature activation-8.59e-01

Pos logit contributions
aman+0.013
pp+0.012
al+0.011
OO+0.010
 cash+0.010
Neg logit contributions
 brothers-0.006
 friends-0.006
 importantly-0.005
 villains-0.005
 families-0.005
Token inches
Token ID8331
Feature activation-2.53e+00

Pos logit contributions
 brothers+0.031
 villains+0.029
 importantly+0.028
 friends+0.027
ooters+0.027
Neg logit contributions
aman-0.052
pp-0.048
al-0.047
 heaven-0.042
 cash-0.041
Token high
Token ID1029
Feature activation-4.10e-01

Pos logit contributions
 brothers+0.102
 friends+0.096
 importantly+0.092
 villains+0.085
 families+0.081
Neg logit contributions
aman-0.168
pp-0.152
al-0.140
OO-0.132
 cash-0.130
Token.
Token ID13
Feature activation-1.25e-01

Pos logit contributions
 brothers+0.017
 friends+0.016
 importantly+0.014
 villains+0.013
 families+0.013
Neg logit contributions
aman-0.028
pp-0.025
OO-0.022
oph-0.021
 cash-0.021
Token She
Token ID1375
Feature activation-4.07e-01

Pos logit contributions
 brothers+0.006
 friends+0.006
 importantly+0.005
 villains+0.005
 families+0.005
Neg logit contributions
aman-0.008
pp-0.007
al-0.006
OO-0.006
 cash-0.006
Token said
Token ID531
Feature activation-2.96e-01

Pos logit contributions
 brothers+0.018
 friends+0.017
 importantly+0.016
 villains+0.015
 families+0.014
Neg logit contributions
aman-0.026
pp-0.023
al-0.021
OO-0.021
 cash-0.020
Token her
Token ID607
Feature activation-4.07e-01

Pos logit contributions
 brothers+0.014
 friends+0.014
 importantly+0.013
 villains+0.012
 families+0.012
Neg logit contributions
aman-0.018
pp-0.016
al-0.014
OO-0.014
 cash-0.013
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 brothers+0.023
 friends+0.023
 importantly+0.020
 families+0.018
 villains+0.018
Neg logit contributions
aman-0.039
pp-0.035
al-0.032
OO-0.031
 cash-0.031
Token Grand
Token ID5675
Feature activation-1.13e-01

Pos logit contributions
 brothers+0.011
 friends+0.010
 importantly+0.010
 villains+0.009
 families+0.009
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
OO-0.013
 cash-0.013
Tokenma
Token ID2611
Feature activation+3.17e-02

Pos logit contributions
 brothers+0.006
 friends+0.005
 importantly+0.005
 villains+0.005
 families+0.005
Neg logit contributions
aman-0.007
pp-0.006
al-0.005
OO-0.005
 cash-0.005
Token shows
Token ID2523
Feature activation+1.38e-01

Pos logit contributions
aman+0.002
pp+0.002
al+0.002
OO+0.001
 cash+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
 families-0.001
Token them
Token ID606
Feature activation-1.27e+00

Pos logit contributions
aman+0.008
pp+0.007
OO+0.007
+0.006
al+0.006
Neg logit contributions
 friends-0.007
 brothers-0.007
 families-0.006
 importantly-0.006
 villains-0.006
Token how
Token ID703
Feature activation-2.48e+00

Pos logit contributions
 brothers+0.063
 friends+0.061
 importantly+0.058
 villains+0.054
 families+0.053
Neg logit contributions
aman-0.073
pp-0.064
al-0.058
OO-0.055
 cash-0.054
Token to
Token ID284
Feature activation-4.27e-02

Pos logit contributions
 brothers+0.132
 importantly+0.129
 villains+0.124
 friends+0.112
 tires+0.110
Neg logit contributions
aman-0.108
pp-0.098
al-0.083
ho-0.082
 heaven-0.082
Token pick
Token ID2298
Feature activation-3.53e-02

Pos logit contributions
 brothers+0.002
 friends+0.002
 exciting+0.002
 importantly+0.002
 families+0.002
Neg logit contributions
aman-0.003
pp-0.002
OO-0.002
al-0.002
oph-0.002
Token the
Token ID262
Feature activation-9.63e-01

Pos logit contributions
 friends+0.001
 brothers+0.001
 exciting+0.001
 trees+0.001
 families+0.001
Neg logit contributions
aman-0.002
pp-0.002
OO-0.002
 salon-0.002
 cash-0.002
Token ripe
Token ID29036
Feature activation-1.40e+00

Pos logit contributions
 brothers+0.037
 friends+0.035
 importantly+0.033
 villains+0.031
 families+0.029
Neg logit contributions
aman-0.066
pp-0.059
al-0.054
OO-0.052
 cash-0.051
Token ones
Token ID3392
Feature activation+6.03e-02

Pos logit contributions
 brothers+0.053
 friends+0.052
 importantly+0.044
 families+0.041
 exciting+0.040
Neg logit contributions
aman-0.098
pp-0.088
OO-0.079
al-0.079
 cash-0.076
Token bird
Token ID6512
Feature activation-1.47e+00

Pos logit contributions
 brothers+0.028
 friends+0.026
 importantly+0.026
 villains+0.024
 families+0.022
Neg logit contributions
aman-0.041
pp-0.037
al-0.034
OO-0.032
 cash-0.032
Token fly
Token ID6129
Feature activation-8.29e-01

Pos logit contributions
 friends+0.064
 brothers+0.061
 exciting+0.051
 importantly+0.050
 families+0.050
Neg logit contributions
aman-0.100
pp-0.082
oph-0.080
 cash-0.079
al-0.077
Token from
Token ID422
Feature activation-1.02e+00

Pos logit contributions
 friends+0.036
 brothers+0.033
 exciting+0.031
 fun+0.028
 families+0.028
Neg logit contributions
aman-0.054
pp-0.046
 cash-0.045
oph-0.042
al-0.041
Token the
Token ID262
Feature activation-3.44e-01

Pos logit contributions
 friends+0.042
 brothers+0.042
 exciting+0.036
 importantly+0.034
 trees+0.034
Neg logit contributions
aman-0.069
pp-0.066
oph-0.056
 cash-0.055
OO-0.054
Token chim
Token ID18205
Feature activation-1.06e+00

Pos logit contributions
 brothers+0.013
 friends+0.012
 importantly+0.011
 villains+0.010
 families+0.010
Neg logit contributions
aman-0.024
pp-0.022
al-0.020
OO-0.019
 cash-0.019
Tokenney
Token ID1681
Feature activation-2.49e+00

Pos logit contributions
 brothers+0.026
 friends+0.024
 importantly+0.022
 villains+0.019
 families+0.017
Neg logit contributions
aman-0.087
pp-0.079
al-0.074
OO-0.072
 cash-0.071
Token."
Token ID526
Feature activation+1.24e-01

Pos logit contributions
 brothers+0.097
 friends+0.095
 importantly+0.083
 exciting+0.077
 families+0.075
Neg logit contributions
aman-0.170
pp-0.151
al-0.137
OO-0.136
 cash-0.136
Token
Token ID198
Feature activation-1.12e-01

Pos logit contributions
aman+0.009
pp+0.008
al+0.007
OO+0.007
 cash+0.007
Neg logit contributions
 brothers-0.005
 friends-0.004
 importantly-0.004
 villains-0.004
 families-0.004
Token
Token ID198
Feature activation+9.23e-02

Pos logit contributions
 brothers+0.005
 friends+0.004
 importantly+0.004
 villains+0.004
 families+0.004
Neg logit contributions
aman-0.007
pp-0.006
al-0.006
 cash-0.005
OO-0.005
TokenL
Token ID43
Feature activation+6.51e-01

Pos logit contributions
aman+0.006
pp+0.005
al+0.005
OO+0.004
 cash+0.004
Neg logit contributions
 brothers-0.004
 friends-0.004
 importantly-0.004
 villains-0.004
 families-0.003
Tokenily
Token ID813
Feature activation+1.21e-01

Pos logit contributions
aman+0.055
pp+0.050
+0.047
 cash+0.045
 generation+0.044
Neg logit contributions
 brothers-0.016
 friends-0.015
 importantly-0.011
 villains-0.010
 kids-0.010
Token He
Token ID679
Feature activation-4.54e-01

Pos logit contributions
 importantly+0.024
 brothers+0.024
 friends+0.023
 families+0.022
 villains+0.022
Neg logit contributions
aman-0.024
 cash-0.021
OO-0.020
al-0.020
pp-0.019
Token imagined
Token ID15758
Feature activation-3.01e-01

Pos logit contributions
 importantly+0.024
 brothers+0.023
 friends+0.022
 villains+0.021
neys+0.021
Neg logit contributions
aman-0.022
pp-0.021
al-0.019
 cash-0.018
OO-0.017
Token he
Token ID339
Feature activation-7.01e-01

Pos logit contributions
 brothers+0.015
 friends+0.014
 importantly+0.014
 villains+0.013
 families+0.012
Neg logit contributions
aman-0.017
pp-0.015
al-0.014
OO-0.013
 cash-0.013
Token was
Token ID373
Feature activation-8.77e-01

Pos logit contributions
 brothers+0.029
 friends+0.027
 importantly+0.026
 villains+0.024
 families+0.023
Neg logit contributions
aman-0.045
pp-0.041
al-0.038
OO-0.036
 cash-0.035
Token a
Token ID257
Feature activation-9.52e-01

Pos logit contributions
 importantly+0.045
 brothers+0.044
ooters+0.041
 families+0.041
neys+0.040
Neg logit contributions
aman-0.035
pp-0.035
al-0.033
 cash-0.029
 one-0.028
Token brave
Token ID14802
Feature activation-2.53e+00

Pos logit contributions
 brothers+0.038
 importantly+0.035
 friends+0.035
neys+0.032
 villains+0.031
Neg logit contributions
aman-0.060
pp-0.054
al-0.050
 cash-0.049
OO-0.048
Token warrior
Token ID16491
Feature activation-3.46e-01

Pos logit contributions
 brothers+0.116
 friends+0.110
 importantly+0.109
neys+0.100
 families+0.099
Neg logit contributions
aman-0.147
pp-0.129
al-0.123
OO-0.115
 cash-0.114
Token with
Token ID351
Feature activation-4.37e-01

Pos logit contributions
 brothers+0.016
 friends+0.015
 importantly+0.015
 villains+0.014
 families+0.013
Neg logit contributions
aman-0.021
pp-0.019
al-0.017
OO-0.016
 cash-0.016
Token a
Token ID257
Feature activation-2.40e-01

Pos logit contributions
 brothers+0.019
 importantly+0.019
 friends+0.018
 villains+0.017
 families+0.016
Neg logit contributions
aman-0.024
pp-0.022
al-0.021
 cash-0.020
OO-0.019
Token big
Token ID1263
Feature activation-3.89e-01

Pos logit contributions
 brothers+0.009
 importantly+0.009
neys+0.008
 friends+0.008
 families+0.008
Neg logit contributions
aman-0.015
pp-0.013
OO-0.012
al-0.012
 cash-0.012
Token spear
Token ID17514
Feature activation+1.31e-01

Pos logit contributions
 importantly+0.017
 brothers+0.017
neys+0.016
 friends+0.015
 villains+0.015
Neg logit contributions
aman-0.022
pp-0.019
al-0.018
OO-0.018
 cash-0.017
Token thing
Token ID1517
Feature activation+6.63e-01

Pos logit contributions
 brothers+0.047
 importantly+0.044
 friends+0.044
 villains+0.041
 families+0.040
Neg logit contributions
aman-0.047
pp-0.039
al-0.036
 cash-0.034
OO-0.034
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
aman+0.043
pp+0.038
al+0.034
OO+0.033
 cash+0.033
Neg logit contributions
 brothers-0.028
 friends-0.027
 importantly-0.025
 villains-0.023
 families-0.023
Token She
Token ID1375
Feature activation-2.04e-01

Pos logit contributions
 brothers+0.018
 friends+0.017
 importantly+0.017
 villains+0.016
 families+0.015
Neg logit contributions
aman-0.017
pp-0.014
al-0.013
OO-0.012
 cash-0.012
Token shouted
Token ID17293
Feature activation+3.32e-02

Pos logit contributions
 importantly+0.011
 brothers+0.011
 friends+0.010
 villains+0.010
neys+0.010
Neg logit contributions
aman-0.010
pp-0.009
al-0.008
 cash-0.007
ah-0.007
Token "
Token ID366
Feature activation-2.53e-02

Pos logit contributions
aman+0.002
pp+0.002
al+0.002
use+0.002
oph+0.002
Neg logit contributions
 friends-0.001
 brothers-0.001
 importantly-0.001
 exciting-0.001
 villains-0.001
Tokenv
Token ID85
Feature activation-2.51e+00

Pos logit contributions
 brothers+0.001
 friends+0.001
 importantly+0.001
 villains+0.001
 Seek+0.001
Neg logit contributions
aman-0.002
pp-0.001
al-0.001
OO-0.001
 heaven-0.001
Tokenroom
Token ID3823
Feature activation-7.03e-01

Pos logit contributions
 brothers+0.135
 friends+0.130
 importantly+0.119
 villains+0.112
 families+0.111
Neg logit contributions
aman-0.138
pp-0.121
al-0.105
 cash-0.100
OO-0.097
Token v
Token ID410
Feature activation+2.20e-02

Pos logit contributions
 brothers+0.029
 friends+0.029
 importantly+0.025
 villains+0.023
 families+0.023
Neg logit contributions
aman-0.046
pp-0.041
al-0.036
 generation-0.036
 cash-0.035
Tokenroom
Token ID3823
Feature activation-7.70e-01

Pos logit contributions
aman+0.001
pp+0.001
al+0.001
OO+0.001
 cash+0.001
Neg logit contributions
 brothers-0.001
 friends-0.001
 importantly-0.001
 villains-0.001
neys-0.001
Token"
Token ID1
Feature activation+1.75e-01

Pos logit contributions
 brothers+0.031
 friends+0.030
 importantly+0.025
 villains+0.025
 families+0.024
Neg logit contributions
aman-0.052
pp-0.046
al-0.041
 generation-0.040
 cash-0.039
Token and
Token ID290
Feature activation-7.12e-01

Pos logit contributions
aman+0.012
pp+0.010
al+0.009
 cash+0.009
OO+0.009
Neg logit contributions
 brothers-0.007
 friends-0.007
 importantly-0.006
 villains-0.006
 exciting-0.005