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

    Neuronpedia

    INDEX
    Explanations

    symbols and specific language characters that indicate quotes or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bea
    -0.33
    Regards
    -0.32
     Kies
    -0.31
     Kloster
    -0.31
     Mittel
    -0.31
     quis
    -0.31
    мите
    -0.31
    度は
    -0.31
    Dear
    -0.31
     Werk
    -0.31
    POSITIVE LOGITS
     surla
    0.77
    fjspx
    0.76
     kasarigan
    0.71
    enderror
    0.71
    AddTagHelper
    0.69
    𝟹
    0.68
     propOrder
    0.68
    ロウィン
    0.67
     ModelExpression
    0.67
    parsedMessage
    0.66
    Act Density 0.058%

    No Known Activations