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

    Neuronpedia

    INDEX
    Explanations

    instances of compulsion or coercion in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Simpson
    -0.15
    vides
    -0.14
     Cooper
    -0.14
     Hud
    -0.14
     Kh
    -0.14
    omnia
    -0.14
    ccd
    -0.14
    ÑĮе
    -0.14
    Ģ
    -0.13
     Hardy
    -0.13
    POSITIVE LOGITS
    afd
    0.17
    ATER
    0.15
    idebar
    0.15
    ater
    0.14
    Å¡Å¥
    0.14
    elerik
    0.14
    .liferay
    0.14
     Genius
    0.14
    evin
    0.14
     FileOutputStream
    0.14
    Act Density 0.044%

    No Known Activations