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

    Neuronpedia

    INDEX
    Explanations

    mentions of male and female titles or honorifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.78
     actionGroup
    -0.77
     appre
    -0.75
     tremend
    -0.72
     exting
    -0.70
     wheelchair
    -0.69
     eleph
    -0.68
     pione
    -0.67
    rawdownloadcloneembedreportprint
    -0.63
    catentry
    -0.63
    POSITIVE LOGITS
    .,
    1.07
    ./
    0.89
    .,"
    0.83
    .;
    0.81
    .?
    0.81
     Blasio
    0.76
    iggins
    0.75
    .-
    0.73
    .),
    0.70
    izer
    0.70
    Act Density 0.022%

    No Known Activations