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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ctors
    -0.73
    gged
    -0.71
    asure
    -0.68
     listeners
    -0.67
    cknow
    -0.67
    Synopsis
    -0.66
    phrine
    -0.64
    ptin
    -0.64
     respondents
    -0.63
     polyg
    -0.58
    POSITIVE LOGITS
    onne
    0.74
     Rav
    0.68
    yss
    0.66
    ween
    0.66
    enegger
    0.65
    minster
    0.65
     Wars
    0.60
    saf
    0.60
     Motorsport
    0.60
     Sind
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.