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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating urgency or imperative advice directed at the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inst
    -0.15
    braco
    -0.14
    nowrap
    -0.14
    COPE
    -0.14
    orge
    -0.14
    cope
    -0.14
    TemplateName
    -0.14
    ergus
    -0.14
    orical
    -0.14
    enor
    -0.14
    POSITIVE LOGITS
    æ¯
    0.15
    ivé
    0.14
    kes
    0.14
    805
    0.14
    pais
    0.13
    arias
    0.13
    yth
    0.13
    584
    0.13
    eru
    0.13
    001
    0.12
    Act Density 0.049%

    No Known Activations