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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks indicating emphasis or transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /her
    -0.18
    ãĥ«ãĥķ
    -0.16
    ses
    -0.16
    ialis
    -0.14
    horn
    -0.14
    sse
    -0.14
    acer
    -0.14
    ILA
    -0.14
    ry
    -0.14
    ceb
    -0.14
    POSITIVE LOGITS
    apgolly
    0.19
    _<
    0.18
    >↵
    0.18
    lying
    0.18
    ..<
    0.17
    ingly
    0.16
    >↵↵↵
    0.16
    >↵↵
    0.16
    ture
    0.16
    민êµŃ
    0.16
    Act Density 0.049%

    No Known Activations