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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements, such as distances, percentages, and numeric values

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollah
    -0.66
    SON
    -0.63
     SAY
    -0.61
    Reply
    -0.60
    rely
    -0.56
    ortment
    -0.55
    irect
    -0.55
    abus
    -0.54
     dissenting
    -0.54
     Wong
    -0.53
    POSITIVE LOGITS
     apiece
    1.02
    hz
    0.91
     intervals
    0.90
    +.
    0.88
    +,
    0.86
    fps
    0.85
     increments
    0.80
    bps
    0.79
    MHz
    0.79
    rez
    0.78
    Act Density 0.268%

    No Known Activations