Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     heck
    -0.65
     box
    -0.64
     Horowitz
    -0.64
     Dh
    -0.64
    mbuds
    -0.62
     Mister
    -0.60
     BOX
    -0.59
     Rosenthal
    -0.59
    raq
    -0.59
     Eisen
    -0.58
    POSITIVE LOGITS
    Pokemon
    0.85
    past
    0.76
    fing
    0.70
    [_
    0.68
    crop
    0.66
    ippi
    0.65
    obia
    0.64
    Drag
    0.63
    pick
    0.63
    catch
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.