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

    Neuronpedia

    INDEX
    Explanations

    references to variable names or components in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ganu
    -0.53
     autorytatywna
    -0.50
     blessés
    -0.50
     surface
    -0.47
    atrici
    -0.47
    표
    -0.46
     Национальный
    -0.46
    alnız
    -0.46
    iempos
    -0.46
    surface
    -0.46
    POSITIVE LOGITS
    ynes
    0.62
    |}{}
    0.55
    CppCodeGen
    0.48
    race
    0.48
    Eloquent
    0.48
    BASELINE
    0.48
    DoubleQuotes
    0.48
    ůli
    0.48
    dova
    0.48
     tả
    0.47
    Act Density 0.128%

    No Known Activations