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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     corrid
    -1.02
     misunder
    -0.90
    Money
    -0.85
    âĸ¬
    -0.84
    ikuman
    -0.81
     Stain
    -0.79
     compr
    -0.79
    ADRA
    -0.77
     deflation
    -0.77
    TextColor
    -0.75
    POSITIVE LOGITS
    ghan
    1.08
    cean
    0.92
    ird
    0.86
    etus
    0.86
    rily
    0.86
    hea
    0.83
    phant
    0.82
    ank
    0.80
    vironment
    0.80
    ionage
    0.78
    Act Density 12.202%

    No Known Activations