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

    Neuronpedia

    INDEX
    Explanations

    words related to legal or financial penalties

    oai_token-act-pair · gpt-3.5-turbo

    references to penalties and punitive measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.87
    rina
    -0.77
    atters
    -0.76
    ership
    -0.74
    Local
    -0.73
    Street
    -0.73
    ERN
    -0.72
    ECD
    -0.72
    ILE
    -0.72
     Corridor
    -0.70
    POSITIVE LOGITS
     penalties
    1.47
     penalty
    1.14
     levied
    1.02
     punishments
    1.00
     imposed
    0.99
    alties
    0.98
     confir
    0.97
     sanction
    0.95
     punishment
    0.94
     punish
    0.93
    Act Density 0.009%

    No Known Activations