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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ebted
    -0.80
    alty
    -0.77
    ury
    -0.71
    redits
    -0.67
     reinvest
    -0.66
    ibling
    -0.66
    appropriate
    -0.63
    thur
    -0.63
     lucid
    -0.63
    rir
    -0.63
    POSITIVE LOGITS
    externalActionCode
    0.66
     Hyder
    0.64
    Chel
    0.63
    Wil
    0.63
     Prov
    0.63
    Ò
    0.61
     Scarborough
    0.61
     Tracks
    0.60
    artney
    0.60
    cod
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.