INDEX
Explanations
words related to direction or decision-making
expressions related to "direction."
New Auto-Interp
Negative Logits
esters
-0.67
tics
-0.64
Average
-0.63
TED
-0.61
riots
-0.60
Myth
-0.60
Scores
-0.58
Pelosi
-0.58
quished
-0.57
latable
-0.57
POSITIVE LOGITS
direction
4.13
directions
2.89
Direction
2.27
direction
2.27
Directions
1.59
orientation
1.35
irection
1.25
trajectory
1.19
guidance
1.19
directional
1.15
Activations Density 0.010%