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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and structure within programming-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ABCDEFGHIJKLMNOP
    -0.16
     Sür
    -0.15
    ῶ
    -0.15
    /***/
    -0.14
    -corner
    -0.14
    ---</
    -0.14
    /***
    -0.14
    MLS
    -0.14
    &);↵
    -0.14
    lore
    -0.14
    POSITIVE LOGITS
     *
    0.35
     *↵
    0.28
     *↵↵
    0.22
     *č↵
    0.18
    *
    0.17
     *}
    0.17
     *----------------------------------------------------------------
    0.16
    aid
    0.16
     *,
    0.15
    dux
    0.15
    Act Density 0.032%

    No Known Activations