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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.85
    OIL
    -0.82
    Ô
    -0.79
    ~~~~
    -0.75
    EStreamFrame
    -0.70
    ãĥ´
    -0.65
    Comment
    -0.65
    ENC
    -0.64
    FORE
    -0.64
     Liang
    -0.64
    POSITIVE LOGITS
    ptoms
    0.75
    heny
    0.69
     rally
    0.66
    etsk
    0.65
    ceed
    0.65
     hottest
    0.64
    brate
    0.63
    wcsstore
    0.63
    brates
    0.63
    ests
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.