INDEX
Explanations
adverbs describing emotions such as 'angrily' and 'calmly'
emotional expressions, particularly related to anger and aggression
New Auto-Interp
Negative Logits
willingness
-0.72
ties
-0.71
ilion
-0.68
reservations
-0.67
therapists
-0.66
spoilers
-0.66
servants
-0.66
linkage
-0.65
subscriptions
-0.65
collaborators
-0.64
POSITIVE LOGITS
addressed
0.83
detonated
0.82
ãĤ©
0.81
planted
0.78
pursued
0.76
aimed
0.74
kissed
0.73
preceded
0.73
shoved
0.72
dressed
0.72
Activations Density 0.048%