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

    Neuronpedia

    INDEX
    Explanations

    notable events or entities in history

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with security, performance metrics, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruciating
    -0.65
    kas
    -0.64
     unfocusedRange
    -0.64
    天
    -0.62
     subur
    -0.61
    aleb
    -0.61
    instead
    -0.60
     srfAttach
    -0.60
    ymes
    -0.59
    ritz
    -0.58
    POSITIVE LOGITS
     imaginable
    1.97
     EVER
    1.72
     ever
    1.68
    ever
    1.42
     Ever
    1.23
    Ever
    1.13
     possible
    1.13
     conceivable
    1.13
     anywhere
    1.12
     available
    0.87
    Act Density 0.372%

    No Known Activations