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

    Neuronpedia

    INDEX
    Explanations

    references to conditions and qualifications within statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioni
    -0.18
    hiba
    -0.18
    atar
    -0.15
    inkle
    -0.15
    æİ¡
    -0.15
     knot
    -0.15
    á»Ļi
    -0.15
    estar
    -0.14
    _FATAL
    -0.14
    parsed
    -0.14
    POSITIVE LOGITS
     tune
    0.16
    768
    0.15
    ash
    0.15
     Geb
    0.15
    ye
    0.14
    Af
    0.14
    linger
    0.14
    orraine
    0.14
    etc
    0.13
    å°ij
    0.13
    Act Density 0.197%

    No Known Activations