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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¾ĭ
    -0.14
    |(↵
    -0.14
    ych
    -0.13
    roe
    -0.13
    å¤
    -0.13
    }//
    -0.13
    burg
    -0.12
    xmm
    -0.12
    åł¡
    -0.12
    碼
    -0.12
    POSITIVE LOGITS
     \
    0.19
     (\
    0.18
    using
    0.16
    572
    0.16
    0.16
     [~,
    0.16
    /mainwindow
    0.16
     &&
    0.16
     ?");↵
    0.14
     |
    0.14
    Act Density 0.218%

    No Known Activations