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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     âĸº
    -0.84
    TAIN
    -0.76
     Thumbnails
    -0.72
    catentry
    -0.71
    FTWARE
    -0.71
    ALT
    -0.67
    oyer
    -0.66
    à¥
    -0.64
    "}
    -0.64
    ा
    -0.63
    POSITIVE LOGITS
    ression
    0.75
    oha
    0.75
    rpm
    0.64
    ately
    0.61
    olation
    0.61
    sburgh
    0.59
    packing
    0.59
    ographically
    0.58
     reincarn
    0.58
     sidew
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.