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

    Neuronpedia

    INDEX
    Explanations

    mentions of the degree or extent of something, often related to difficulty, care, or level of a specific quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating varying levels of something, particularly intensity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.97
    ãĤ·
    -0.74
    orative
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.70
     Picks
    -0.69
    nets
    -0.68
    oons
    -0.68
    ÄŁ
    -0.67
    iers
    -0.66
    çİĭ
    -0.65
    POSITIVE LOGITS
     sophistication
    1.15
     maturity
    1.11
     professionalism
    0.95
     confidence
    0.91
     abstraction
    0.91
     accomplishment
    0.90
     significance
    0.89
     urgency
    0.88
     attainment
    0.87
     scrutiny
    0.87
    Act Density 0.061%

    No Known Activations