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

    Neuronpedia

    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals related to controversies or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ument
    -0.96
    urat
    -0.92
    nces
    -0.87
    gments
    -0.84
    seys
    -0.84
    itsu
    -0.83
    gers
    -0.82
    ctive
    -0.82
    erald
    -0.81
    bly
    -0.81
    POSITIVE LOGITS
     Allan
    0.95
     Giles
    0.86
     Blackwell
    0.83
     Cullen
    0.82
     Rebell
    0.80
     Lowell
    0.77
     Baird
    0.76
     Burgess
    0.76
     Holden
    0.73
     Vaugh
    0.73
    Act Density 0.017%

    No Known Activations