INDEX
Explanations
informal phrases like "OK," "so," and "but."
conversational phrases indicating agreement or acknowledgment
New Auto-Interp
Negative Logits
âĵĺ
-0.80
conservancy
-0.77
cit
-0.74
ache
-0.73
reated
-0.73
nai
-0.71
igious
-0.70
endor
-0.70
paralleled
-0.69
ļéĨĴ
-0.69
POSITIVE LOGITS
bye
0.99
congratulations
0.95
congr
0.91
bye
0.87
maybe
0.83
yeah
0.80
Lets
0.80
Okay
0.80
goodbye
0.78
Alright
0.77
Activations Density 0.065%