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

    Neuronpedia

    INDEX
    Explanations

    legal and punishment-related terms and sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal sentencing and judicial outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reply
    -0.72
    idth
    -0.70
     invading
    -0.67
    oward
    -0.66
    earth
    -0.65
    \":
    -0.65
    Untitled
    -0.63
     invaders
    -0.63
    aclysm
    -0.63
     silhou
    -0.63
    POSITIVE LOGITS
     probation
    1.52
     parole
    1.25
     rehabilitation
    1.15
     restitution
    1.13
     sentencing
    1.11
     suspended
    1.07
     supervised
    1.00
     forfeiture
    1.00
     plea
    0.97
     waived
    0.95
    Act Density 0.192%

    No Known Activations