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

    Neuronpedia

    INDEX
    Explanations

    Alphanumeric patterns and structured information within a document

    oai_token-act-pair · gpt-3.5-turbo

    specific and significant numerical or symbolic data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ake
    -0.75
    ials
    -0.72
    367
    -0.69
    ucci
    -0.69
     63
    -0.68
     367
    -0.67
    483
    -0.65
     Lamar
    -0.65
    inant
    -0.64
    ymm
    -0.63
    POSITIVE LOGITS
    10
    1.10
     10
    0.90
    0010
    0.77
     tenth
    0.77
    940
    0.76
    110
    0.76
     Afgh
    0.75
    910
    0.73
    100
    0.73
    2020
    0.72
    Act Density 0.089%

    No Known Activations