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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning specific names such as "Karen Higgins" or "Percy Higgins"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Higgins" and related individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cers
    -0.82
    ĪĴ
    -0.79
    axter
    -0.78
    icate
    -0.78
    pron
    -0.75
    ggle
    -0.74
    inition
    -0.73
    iquid
    -0.71
    argon
    -0.71
    cer
    -0.71
    POSITIVE LOGITS
     Lans
    0.82
     Yards
    0.74
     Publication
    0.71
     hanged
    0.71
     Cummings
    0.70
     LLP
    0.68
    utenberg
    0.68
     Digest
    0.68
    alez
    0.66
     Gow
    0.66
    Act Density 0.019%

    No Known Activations