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

    Neuronpedia

    INDEX
    Explanations

    actions related to spending time doing specific activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate effort and striving towards goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.80
    eka
    -0.70
     Skies
    -0.68
    lihood
    -0.66
    i
    -0.65
    prov
    -0.64
     proceeding
    -0.64
    ensable
    -0.63
    fortunately
    -0.63
    ca
    -0.62
    POSITIVE LOGITS
    BIL
    0.75
    maxwell
    0.70
     frivolous
    0.68
     Maur
    0.65
    BAT
    0.64
     mundane
    0.63
     Dudley
    0.62
     Sheldon
    0.62
     delinquent
    0.61
     Gators
    0.61
    Act Density 0.195%

    No Known Activations