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

    Neuronpedia

    INDEX
    Explanations

    punctuation and syntax elements in programming or code-related text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orr
    -0.17
    132
    -0.17
    131
    -0.16
    /REC
    -0.16
    135
    -0.16
    133
    -0.15
    /Foundation
    -0.15
    17
    -0.14
    332
    -0.14
    19
    -0.14
    POSITIVE LOGITS
    0.39
    0.38
    0.26
    --------------------
    0.25
    0.24
    104
    0.24
    105
    0.24
                        ↵
    0.23
                        č↵
    0.23
    ↵                    ↵
    0.23
    Act Density 0.009%

    No Known Activations