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

    Neuronpedia

    INDEX
    Explanations

    names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaughan
    -0.67
    inary
    -0.65
    YP
    -0.65
     Hole
    -0.64
    Lew
    -0.62
     programmed
    -0.62
    ndum
    -0.61
    rehens
    -0.61
    ary
    -0.60
    hex
    -0.60
    POSITIVE LOGITS
    REDACTED
    0.86
    gha
    0.85
    nen
    0.80
    ews
    0.78
    kered
    0.75
    sbm
    0.74
    keleton
    0.71
    lihood
    0.71
    ãĤ¿
    0.68
    hma
    0.68
    Act Density 0.051%

    No Known Activations