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

    Neuronpedia

    INDEX
    Explanations

    mentions of a person or people

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or the term "someone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.78
    osterone
    -0.77
    DOS
    -0.75
    irth
    -0.74
    EngineDebug
    -0.73
    ory
    -0.72
    UV
    -0.67
    inders
    -0.65
    ean
    -0.64
    ortex
    -0.64
    POSITIVE LOGITS
     else
    1.81
    Else
    1.41
     Else
    1.25
    else
    1.16
    WithNo
    0.95
     knowledgeable
    0.85
     who
    0.85
    uscript
    0.76
     forgot
    0.76
     skilled
    0.74
    Act Density 0.045%

    No Known Activations