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

    Neuronpedia

    INDEX
    Explanations

    symbols and characters in programming or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erson
    -0.20
    rog
    -0.18
    /or
    -0.17
    emme
    -0.17
    ese
    -0.16
    ract
    -0.16
    elson
    -0.16
    uyá»ĩt
    -0.16
    etsk
    -0.15
    ence
    -0.15
    POSITIVE LOGITS
    ::|
    0.18
    ius
    0.17
     else
    0.16
    vette
    0.15
    arsi
    0.15
    tea
    0.15
    ===↵
    0.14
    íģ¼
    0.14
    .SIG
    0.14
    زÙĬز
    0.14
    Act Density 0.077%

    No Known Activations