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

    Neuronpedia

    INDEX
    Explanations

    quotes indicating moral or ethical dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iesen
    -0.17
    rist
    -0.17
    irk
    -0.17
     Dün
    -0.16
    alse
    -0.16
    gis
    -0.15
    iferay
    -0.15
     intro
    -0.15
    avl
    -0.15
     Jacqu
    -0.15
    POSITIVE LOGITS
    uren
    0.15
    /stats
    0.14
    -tm
    0.14
    çĹ
    0.14
    éģĵ
    0.14
     Cou
    0.14
    Å¡et
    0.14
     Cast
    0.14
     Empty
    0.14
    ìľ¼ëĭĪ
    0.14
    Act Density 0.143%

    No Known Activations