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

    Neuronpedia

    INDEX
    Explanations

    references to safety or health concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -quarters
    -0.20
    rd
    -0.19
    /or
    -0.18
    ness
    -0.17
    ãģ¨ãģĵãĤį
    -0.16
    zeit
    -0.16
    à¸ķ
    -0.15
    zeitig
    -0.15
    umbles
    -0.15
    ÚĨÙĩ
    -0.15
    POSITIVE LOGITS
    yonel
    0.20
    elli
    0.20
    ëģĶ
    0.20
    ä¹Ī
    0.16
    estro
    0.16
    ../
    0.15
    ivre
    0.15
    éĩı
    0.15
    nier
    0.15
    TURE
    0.15
    Act Density 0.038%

    No Known Activations