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

    Neuronpedia

    INDEX
    Explanations

    monetary amounts and corresponding punishments in legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating maximum limits or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maker
    -0.70
     Abyss
    -0.63
    >"
    -0.62
    ¯¯¯¯
    -0.61
    gee
    -0.61
    ====
    -0.61
    ________________________
    -0.60
    [/
    -0.59
     bis
    -0.57
     Blues
    -0.56
    POSITIVE LOGITS
    graded
    1.14
    grades
    1.08
    grading
    1.06
    dates
    1.01
    stairs
    0.99
    dating
    0.98
    votes
    0.88
    river
    0.87
    erd
    0.86
    rights
    0.86
    Act Density 0.076%

    No Known Activations