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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and question marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inv
    -0.16
     esl
    -0.15
    iva
    -0.15
    Grid
    -0.15
    pal
    -0.15
    pta
    -0.15
     Faith
    -0.14
    apan
    -0.14
    ker
    -0.14
    rint
    -0.14
    POSITIVE LOGITS
    rics
    0.16
    olib
    0.15
    zung
    0.15
    ÏĥÏĦη
    0.15
    aravel
    0.15
    artz
    0.14
    .Nodes
    0.14
    udic
    0.14
    หมà¸Ķ
    0.14
    ERG
    0.14
    Act Density 0.003%

    No Known Activations