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

    Neuronpedia

    INDEX
    Explanations

    references to personal accountability and societal expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rita
    -0.15
    uve
    -0.15
    ahat
    -0.14
    utex
    -0.14
     tert
    -0.14
    ERM
    -0.14
    asurement
    -0.14
    uguay
    -0.14
    clipse
    -0.13
    grese
    -0.13
    POSITIVE LOGITS
    962
    0.16
    ç´
    0.14
    ÅĻad
    0.14
     correl
    0.14
    764
    0.14
    'gc
    0.13
    íijľ
    0.13
     íijľ
    0.13
    898
    0.12
    985
    0.12
    Act Density 1.975%

    No Known Activations