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

    Neuronpedia

    INDEX
    Explanations

    examples showcasing financial misconduct or irregularities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sleep
    -0.70
    lean
    -0.68
    ISO
    -0.65
    luaj
    -0.63
    alty
    -0.60
    lav
    -0.60
    obos
    -0.60
    alus
    -0.59
    bel
    -0.57
    ancies
    -0.56
    POSITIVE LOGITS
     examples
    0.85
     scratching
    0.80
     facet
    0.77
    Ware
    0.73
     example
    0.73
     sympt
    0.71
     manifestation
    0.69
    £ı
    0.69
    yk
    0.67
    Examples
    0.67
    Act Density 0.093%

    No Known Activations