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

    Neuronpedia

    INDEX
    Explanations

    references to decision-making and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¦
    -2.47
    ī
    -2.35
    IJ
    -2.21
    ¨
    -2.14
    ¾
    -2.12
    Ĭ
    -2.12
    Ľ
    -2.06
    İ
    -2.05
    Ļ
    -2.02
    ¤
    -2.01
    POSITIVE LOGITS
    áĢ¯
    2.00
    sed
    1.82
    áŁ
    1.67
    refs
    1.51
    EXT
    1.51
    áĢ¬
    1.50
    $).
    1.49
    \\
    1.49
    оÐ
    1.48
    à³
    1.46
    Act Density 3.720%

    No Known Activations