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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical values related to growth or change

    oai_token-act-pair · gpt-3.5-turbo

    data related to percentages and statistical measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liction
    -0.59
    ãĤ¦ãĤ¹
    -0.59
     medi
    -0.57
     misc
    -0.57
    values
    -0.57
    ullah
    -0.57
     ty
    -0.57
    vice
    -0.56
     sparse
    -0.55
    lict
    -0.54
    POSITIVE LOGITS
     compared
    0.93
     annually
    0.91
    bps
    0.90
     Yo
    0.80
     during
    0.75
     apiece
    0.73
    Footnote
    0.70
     Fahrenheit
    0.70
     overnight
    0.69
     ABV
    0.67
    Act Density 0.101%

    No Known Activations