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

    Neuronpedia

    INDEX
    Explanations

    various types of opening and closing parentheses and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rena
    -0.16
    ÃŃrk
    -0.14
    ýv
    -0.14
    uden
    -0.14
    OrNull
    -0.14
    Traversal
    -0.14
    ì°©
    -0.14
    ninger
    -0.14
    ourt
    -0.13
    styl
    -0.13
    POSITIVE LOGITS
    onde
    0.17
     earth
    0.16
    ewis
    0.16
     urn
    0.16
    achuset
    0.15
     kabil
    0.15
    ount
    0.15
    oÄŁ
    0.15
     :
    0.15
    oles
    0.14
    Act Density 0.056%

    No Known Activations