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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal judgments and criminal convictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal guilt and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horn
    -0.82
    iverse
    -0.76
    isSpecialOrderable
    -0.75
    fff
    -0.74
    soType
    -0.73
    kered
    -0.72
    prises
    -0.69
    Tokens
    -0.68
     Forums
    -0.68
     restrooms
    -0.67
    POSITIVE LOGITS
     manslaughter
    1.08
     felony
    1.00
     offences
    0.84
     homicide
    0.84
     misdemeanor
    0.84
    querque
    0.83
     DUI
    0.81
     perjury
    0.80
     wrongful
    0.79
     treason
    0.76
    Act Density 0.120%

    No Known Activations