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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causality or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ochen
    -0.16
    iverz
    -0.16
    iche
    -0.15
    ünd
    -0.15
    ients
    -0.15
    /goto
    -0.15
    ì°¨
    -0.15
    shan
    -0.15
    -Semit
    -0.14
    raf
    -0.13
    POSITIVE LOGITS
    omanip
    0.15
    iced
    0.14
    pared
    0.14
    ikh
    0.14
     cen
    0.14
    å°±ç®Ĺ
    0.14
    aken
    0.14
    ater
    0.14
    enton
    0.14
    ania
    0.13
    Act Density 0.037%

    No Known Activations