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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and characters often used in code or programming statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orr
    -0.17
    332
    -0.17
    /REC
    -0.17
    132
    -0.16
    17
    -0.16
    /Foundation
    -0.14
     пов
    -0.14
    18
    -0.14
    grave
    -0.14
    ãĥ³ãĥĸ
    -0.14
    POSITIVE LOGITS
    0.44
    0.40
    0.30
    0.28
    ↵                    ↵
    0.25
                        ↵
    0.25
    105
    0.25
    --------------------
    0.24
                        č↵
    0.23
    104
    0.23
    Act Density 0.006%

    No Known Activations