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

    Neuronpedia

    INDEX
    Explanations

    references to behavioral guidelines and moral teachings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peria
    -0.18
    apur
    -0.17
    elix
    -0.15
    swick
    -0.15
    ç¤
    -0.14
    ÑĢай
    -0.14
    _peer
    -0.14
     maur
    -0.14
    ritz
    -0.14
    æ¿
    -0.14
    POSITIVE LOGITS
    Acts
    0.18
     Acts
    0.18
     Revel
    0.18
     Gal
    0.18
    clin
    0.17
     chapter
    0.16
    985
    0.16
     Phil
    0.16
     Romans
    0.16
     kj
    0.15
    Act Density 0.085%

    No Known Activations