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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or character named "Pe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.94
     EDITION
    -0.78
    etheless
    -0.74
    stretched
    -0.73
    orage
    -0.71
    70710
    -0.71
    doms
    -0.69
    EngineDebug
    -0.69
    é¾įå¥ij士
    -0.69
    naire
    -0.67
    POSITIVE LOGITS
    anut
    1.28
    asant
    1.08
    anuts
    1.03
    ek
    1.02
    eps
    1.02
    eking
    0.96
    phrine
    0.95
    pperc
    0.93
    cker
    0.93
    eper
    0.92
    Act Density 0.011%

    No Known Activations