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

    Neuronpedia

    INDEX
    Explanations

    end-of-statement indicators or delimiters in code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Salts
    -0.80
     Gier
    -0.77
     Plum
    -0.77
     Kaur
    -0.76
    Plum
    -0.73
    beutel
    -0.73
     Cabot
    -0.73
     entanto
    -0.71
    väg
    -0.71
    ceb
    -0.69
    POSITIVE LOGITS
    )";
    1.28
    ]";
    1.27
    ";
    1.25
    )".
    1.23
    '".
    1.23
    ')";
    1.21
    '";
    1.19
    __*/
    1.17
    )":
    1.14
     ")";
    1.10
    Act Density 0.015%

    No Known Activations