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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formulas

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting elements in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guest
    -0.76
    ity
    -0.74
     Thompson
    -0.73
     GER
    -0.72
    hend
    -0.69
    agged
    -0.69
     Grayson
    -0.66
    gger
    -0.66
     Guth
    -0.64
     Gott
    -0.64
    POSITIVE LOGITS
    8
    1.34
     8
    1.11
    08
    0.94
     IX
    0.91
    esian
    0.86
    833
    0.85
     eight
    0.85
    866
    0.83
    eight
    0.83
    808
    0.82
    Act Density 0.174%

    No Known Activations