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

    Neuronpedia

    INDEX
    Explanations

    spoken numbers in the format of "number" plus "percent"

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and quantitative comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inform
    -0.56
     pat
    -0.54
    natureconservancy
    -0.54
     WARN
    -0.52
     FORM
    -0.48
     proced
    -0.48
     senses
    -0.47
     myst
    -0.47
     emotion
    -0.45
     delic
    -0.45
    POSITIVE LOGITS
     respectively
    0.85
     etc
    0.76
    ))))
    0.72
    itto
    0.67
    etc
    0.66
    rador
    0.65
    aukee
    0.64
     Jr
    0.62
    BSD
    0.60
    uez
    0.60
    Act Density 0.396%

    No Known Activations