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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or the potential for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ìķĦì§ģ
    -0.17
    already
    -0.16
    ialis
    -0.16
    eses
    -0.16
     already
    -0.15
     ↵↵
    -0.15
     continued
    -0.15
     bisher
    -0.14
    继ç»Ń
    -0.14
    mdi
    -0.14
    POSITIVE LOGITS
     fully
    0.22
    338
    0.17
     Fully
    0.16
     officially
    0.16
    official
    0.15
     official
    0.15
    /full
    0.14
    tility
    0.14
     oficial
    0.14
    pler
    0.13
    Act Density 0.023%

    No Known Activations