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

    Neuronpedia

    INDEX
    Explanations

    references to toxic substances and their harmful effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¼ı
    -0.15
    osaur
    -0.14
    ë§IJ
    -0.14
    onas
    -0.14
    Gatt
    -0.13
    yre
    -0.13
    ãĥ³ãĥĢ
    -0.13
     baÅŁÄ±na
    -0.13
    ao
    -0.13
    peater
    -0.13
    POSITIVE LOGITS
    /to
    0.17
    atern
    0.16
    osis
    0.15
     HCI
    0.15
    rea
    0.15
    ulent
    0.14
    ologically
    0.14
    ancia
    0.14
    iveness
    0.14
    æĽľ
    0.14
    Act Density 0.055%

    No Known Activations