INDEX
Explanations
phrases related to mechanical or physical actions involving pushing or pulling
phrases related to communication or connection dynamics
New Auto-Interp
Negative Logits
Ashes
-0.75
Daylight
-0.63
Polaris
-0.61
toast
-0.61
ashtra
-0.61
Obj
-0.60
Continental
-0.59
Alter
-0.59
Breakfast
-0.59
Bastard
-0.58
POSITIVE LOGITS
pull
0.91
Pull
0.79
strings
0.78
button
0.76
Button
0.73
ongyang
0.72
metab
0.70
ãĤ±
0.69
ands
0.68
accompan
0.68
Activations Density 0.091%