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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their distribution in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahas
    -0.18
    -pdf
    -0.15
     Král
    -0.15
    γγελ
    -0.15
    uml
    -0.14
     Patreon
    -0.14
    Äĥr
    -0.14
    okino
    -0.13
    adaki
    -0.13
    aggi
    -0.13
    POSITIVE LOGITS
    ptime
    0.16
    but
    0.15
    then
    0.15
    iry
    0.15
    xbd
    0.15
    alus
    0.14
     INCIDENTAL
    0.14
     but
    0.14
    pt
    0.14
     then
    0.14
    Act Density 0.176%

    No Known Activations