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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values or identifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.64
     createSprite
    -0.58
     onOptions
    -0.56
     lẻ
    -0.52
    قایناق‌لار
    -0.50
     kasarigan
    -0.50
     doing
    -0.49
     standing
    -0.48
    횟
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     الحره
    0.64
    ,:]
    0.63
    %";
    0.62
    KommentareTeilen
    0.61
    DockStyle
    0.59
    migrationBuilder
    0.56
     duquel
    0.54
     annexed
    0.53
     Blackwood
    0.52
     linseed
    0.52
    Act Density 0.032%

    No Known Activations