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

    Neuronpedia

    INDEX
    Explanations

    words related to skills, expertise, and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to broad appeal and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursday
    -0.70
     Gleaming
    -0.67
    BuyableInstoreAndOnline
    -0.66
    ?!"
    -0.60
     Shutdown
    -0.59
    !?"
    -0.59
     Confederate
    -0.58
     underwear
    -0.58
     expired
    -0.55
    bestos
    -0.55
    POSITIVE LOGITS
     irrespective
    1.26
     whilst
    1.02
     regardless
    0.97
     wherever
    0.91
     amongst
    0.90
     insofar
    0.86
     whereas
    0.86
     rather
    0.85
     across
    0.81
    .
    0.80
    Act Density 0.471%

    No Known Activations