INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     church
    -0.07
     increments
    -0.07
    _boot
    -0.07
     lengths
    -0.06
     alcan
    -0.06
    -0.06
       	
    -0.06
     neighborhood
    -0.06
    gment
    -0.06
     empty
    -0.06
    POSITIVE LOGITS
     pose
    0.18
     Pose
    0.16
     posing
    0.15
     poses
    0.14
     posed
    0.14
    Pose
    0.12
    pose
    0.10
     useForm
    0.09
    _pose
    0.09
    posing
    0.09
    Act Density 0.006%

    No Known Activations