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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nown
    -0.79
    orthy
    -0.73
    rh
    -0.69
     Rebell
    -0.68
     indu
    -0.66
    CHA
    -0.66
     Bearing
    -0.66
     Devils
    -0.62
     Typhoon
    -0.62
    ilit
    -0.62
    POSITIVE LOGITS
    imar
    0.87
    NetMessage
    0.77
    panic
    0.74
    ongyang
    0.74
    INA
    0.72
    Fal
    0.69
    abeth
    0.68
    orescence
    0.67
    pei
    0.66
    arch
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.