INDEX
Explanations
phrases ending with 'ya' or 'yr'
informal expressions of familiarity or casual conversation
New Auto-Interp
Negative Logits
lessly
-0.78
OWER
-0.77
HCR
-0.75
assisted
-0.73
Oracle
-0.69
Dayton
-0.69
inct
-0.68
lycer
-0.67
driver
-0.67
ienced
-0.67
POSITIVE LOGITS
Ya
0.93
guys
0.86
ÅĤ
0.80
ya
0.79
ta
0.78
darn
0.76
bara
0.73
joints
0.72
ishi
0.71
Guys
0.71
Activations Density 0.011%