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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to legal punishments or repercussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Echoes
    -0.95
    aclysm
    -0.83
    NetMessage
    -0.80
     iceberg
    -0.78
     Views
    -0.76
    yip
    -0.76
     Fault
    -0.72
    tones
    -0.71
     Ideas
    -0.71
     scandals
    -0.69
    POSITIVE LOGITS
     probation
    1.48
     suspended
    1.18
     rehabilitation
    1.01
     supervised
    0.99
     suspension
    0.99
     confinement
    0.97
     forfeiture
    0.97
     parole
    0.97
     bail
    0.96
     medically
    0.94
    Act Density 0.357%

    No Known Activations