INDEX
Explanations
terms and phrases related to injuries, particularly in the context of joints and tendons
New Auto-Interp
Negative Logits
gewater
-0.16
torso
-0.14
toi
-0.14
stranger
-0.14
elter
-0.14
خاطر
-0.14
-imm
-0.14
brain
-0.14
imm
-0.13
istrat
-0.13
POSITIVE LOGITS
Tears
0.18
ext
0.18
tendon
0.17
tend
0.17
infer
0.15
/Sub
0.14
ãĤ±ãĥĥãĥĪ
0.14
ac
0.14
iran
0.14
pict
0.14
Activations Density 0.015%