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

    Neuronpedia

    INDEX
    Explanations

    terms related to gender identities and differences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    href
    -0.74
    orio
    -0.72
    edIn
    -0.70
    iPhone
    -0.69
    eper
    -0.68
    ensable
    -0.66
    igmat
    -0.65
    ickets
    -0.65
     Arbor
    -0.63
    igmatic
    -0.62
    POSITIVE LOGITS
    udeau
    0.76
     Females
    0.66
    lda
    0.64
    ESA
    0.64
     armor
    0.60
     srf
    0.60
     XL
    0.60
     Female
    0.59
    reau
    0.59
     |--
    0.58
    Act Density 0.478%

    No Known Activations