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

    Neuronpedia

    INDEX
    Explanations

    individuals charged with criminal offenses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe legal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.83
    Tokens
    -0.81
    soDeliveryDate
    -0.73
    isSpecialOrderable
    -0.71
    bytes
    -0.70
    unny
    -0.66
    liam
    -0.66
    args
    -0.65
    Sov
    -0.65
    Reviewed
    -0.65
    POSITIVE LOGITS
     misdemeanor
    1.38
     felony
    1.38
     aggravated
    1.26
     misdem
    1.22
     disorderly
    1.16
     conspiring
    1.13
     manslaughter
    1.10
     violating
    1.09
     obstruction
    1.05
     assaulting
    1.05
    Act Density 0.061%

    No Known Activations