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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    berman
    -0.69
    Joined
    -0.68
    theless
    -0.68
     arsen
    -0.66
     resign
    -0.64
     contribut
    -0.63
     battalion
    -0.62
     FML
    -0.62
    izen
    -0.61
    ãģ®å®
    -0.59
    POSITIVE LOGITS
    idav
    0.88
    berra
    0.72
     Deal
    0.66
    iotics
    0.66
    ible
    0.66
    iple
    0.66
    gif
    0.63
    itta
    0.63
    ingu
    0.63
    oko
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.