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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Dec D", where D is a number

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly those in December

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.80
    finder
    -0.71
     priv
    -0.71
     Archdemon
    -0.67
    aird
    -0.66
    DragonMagazine
    -0.65
     NIC
    -0.63
     Kush
    -0.63
     Curse
    -0.62
     Nicarag
    -0.62
    POSITIVE LOGITS
    isions
    1.12
    ibel
    1.12
    rypted
    1.12
    enture
    1.06
    rypt
    1.04
    oded
    1.04
    EMBER
    1.02
    oder
    1.01
    ryption
    0.99
    orah
    0.95
    Act Density 0.009%

    No Known Activations