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

    Neuronpedia

    INDEX
    Explanations

    terms related to economic and social demographics

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to demographics and social categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hift
    -0.73
     Goodbye
    -0.73
     Jail
    -0.69
    bye
    -0.68
    haw
    -0.65
     mockery
    -0.64
     joke
    -0.63
     kicker
    -0.63
    ileaks
    -0.62
     Mercy
    -0.62
    POSITIVE LOGITS
     categories
    1.63
    types
    1.53
     types
    1.50
     configurations
    1.45
    groups
    1.43
     contexts
    1.42
     groups
    1.42
     formats
    1.41
     classes
    1.38
     domains
    1.36
    Act Density 0.369%

    No Known Activations