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

    Neuronpedia

    INDEX
    Explanations

    references to punitive actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to punishment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eds
    -0.89
    ergy
    -0.80
    rote
    -0.75
    oir
    -0.75
    NetMessage
    -0.73
    aug
    -0.72
    ocal
    -0.72
    sonian
    -0.71
    roots
    -0.70
    soDeliveryDate
    -0.69
    POSITIVE LOGITS
     punishment
    1.29
     punishments
    1.16
     punish
    1.05
     punished
    1.04
     inflicted
    0.97
     sanction
    0.93
    ishment
    0.92
     humiliation
    0.89
     lashes
    0.89
     exha
    0.87
    Act Density 0.015%

    No Known Activations