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

    Neuronpedia

    INDEX
    Explanations

    references to legal issues and penalties related to crimes and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysa
    -0.16
     lum
    -0.14
    ren
    -0.14
    sold
    -0.13
    ilo
    -0.13
    cert
    -0.13
    azor
    -0.13
    esinin
    -0.13
    ela
    -0.13
    iet
    -0.13
    POSITIVE LOGITS
     penalty
    0.46
     penalties
    0.43
     Penalty
    0.34
     penal
    0.33
     fines
    0.30
     punishable
    0.29
     punishment
    0.28
    _penalty
    0.28
    pen
    0.27
     punishments
    0.26
    Act Density 0.287%

    No Known Activations