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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific identifiers associated with people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Banking
    -0.69
     fulfillment
    -0.68
     circuits
    -0.68
     distance
    -0.66
     spl
    -0.64
     fallacy
    -0.63
     metaphors
    -0.63
     appointment
    -0.63
    INESS
    -0.62
     disguise
    -0.62
    POSITIVE LOGITS
    cia
    1.13
    imir
    1.11
    yna
    1.10
    chuk
    1.07
    ko
    1.05
    chev
    1.00
    chel
    0.98
    iq
    0.97
    nik
    0.97
    nikov
    0.97
    Act Density 0.233%

    No Known Activations