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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enture
    -1.01
    cffff
    -0.94
    raq
    -0.80
    mental
    -0.80
    flies
    -0.79
    lege
    -0.79
    apple
    -0.78
    rador
    -0.75
    nexus
    -0.75
    pmwiki
    -0.74
    POSITIVE LOGITS
     Foley
    0.95
     von
    0.94
     Von
    0.93
     Robertson
    0.91
     Nolan
    0.86
     Yor
    0.86
     Kessler
    0.85
     Singer
    0.85
     Agu
    0.85
     Slater
    0.85
    Act Density 0.024%

    No Known Activations