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

    Neuronpedia

    INDEX
    Explanations

    patterns involving numerical values and arithmetic operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.93
    LayoutPanel
    -0.82
     auroit
    -0.79
    IUrlHelper
    -0.78
     "..\..\
    -0.78
     étoit
    -0.77
     feroit
    -0.73
     Houſe
    -0.72
     autorytatywna
    -0.71
     pouvoit
    -0.70
    POSITIVE LOGITS
    ';
    0.65
    >();
    0.64
    ";
    0.53
    >();
    0.50
     članak
    0.49
     ?";
    0.49
    ';
    0.48
    classmethod
    0.47
    <bos>
    0.47
    ?'
    0.46
    Act Density 0.634%

    No Known Activations