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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to honorary or retired titles

    oai_token-act-pair · gpt-3.5-turbo

    names and titles, particularly academic and professional honors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    saf
    -0.86
    ggles
    -0.84
    sheet
    -0.83
    sy
    -0.73
    gur
    -0.70
    esty
    -0.67
    ramid
    -0.65
    fman
    -0.64
     vector
    -0.63
    sie
    -0.63
    POSITIVE LOGITS
    itus
    1.13
    entimes
    0.91
     Canaver
    0.82
    ername
    0.74
     Augustus
    0.72
    atos
    0.69
     Jed
    0.68
    algia
    0.68
    XM
    0.68
    inguished
    0.67
    Act Density 0.008%

    No Known Activations