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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Bombay
    -0.73
     Shiv
    -0.64
     PF
    -0.62
    JB
    -0.62
    unknown
    -0.61
     Maz
    -0.60
     HC
    -0.59
     Parm
    -0.58
     Cham
    -0.57
    rypt
    -0.57
    POSITIVE LOGITS
    perty
    0.76
    etting
    0.72
    ¯
    0.71
    fters
    0.71
    essa
    0.70
    Dialogue
    0.69
    PLIED
    0.69
    peak
    0.67
    ancies
    0.67
    ê
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.