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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     seiz
    -0.72
    ieg
    -0.72
    aith
    -0.68
     IMAGES
    -0.68
     WARN
    -0.65
    abor
    -0.64
    asers
    -0.64
    iquid
    -0.64
    aus
    -0.64
    itting
    -0.63
    POSITIVE LOGITS
    stals
    0.71
    WF
    0.69
    rin
    0.65
     Faw
    0.63
    stal
    0.63
    PF
    0.62
    âĶģ
    0.61
     insanity
    0.59
    ochond
    0.59
    %:
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.