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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation and conjunctions in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inka
    -0.16
    êu
    -0.15
    iaux
    -0.15
    dÄĽ
    -0.14
    102
    -0.14
     Tul
    -0.13
    arf
    -0.13
     Gareth
    -0.13
    inki
    -0.13
    arto
    -0.13
    POSITIVE LOGITS
    istry
    0.16
    uzey
    0.14
    istrat
    0.14
    /TT
    0.14
    ÙıÙĪا
    0.14
    ispers
    0.13
    Ľi
    0.13
    æ¬
    0.13
    ToDevice
    0.13
    pson
    0.13
    Act Density 0.180%

    No Known Activations