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

    Neuronpedia

    INDEX
    Explanations

    paragraph breaks or introductory phrases like "Below"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Below" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥı
    -0.73
    ãĤ¹ãĥĪ
    -0.68
    natureconservancy
    -0.63
    ãĥ¼ãĥĨ
    -0.62
    Deal
    -0.61
    hya
    -0.60
    ragon
    -0.60
    assic
    -0.58
     Ern
    -0.57
    ËĪ
    -0.56
    POSITIVE LOGITS
     Thumbnails
    0.90
     depicts
    0.86
    ground
    0.85
     screenshot
    0.84
    neath
    0.81
     charts
    0.81
     screenshots
    0.77
     tables
    0.76
     chart
    0.75
     summarizes
    0.74
    Act Density 0.030%

    No Known Activations