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

    Neuronpedia

    INDEX
    Explanations

    words related to punishment and disciplinary actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to punishment and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortment
    -0.80
    yip
    -0.77
     livest
    -0.74
    ophe
    -0.73
    psey
    -0.73
    gow
    -0.71
    ãĤ¤ãĥĪ
    -0.69
    ullivan
    -0.68
    ocent
    -0.67
    rians
    -0.66
    POSITIVE LOGITS
     harshly
    1.04
     punishments
    1.02
     penalties
    0.91
     punishment
    0.91
     punished
    0.89
     severely
    0.85
     inflicted
    0.84
     tant
    0.83
     sanction
    0.82
     levied
    0.80
    Act Density 0.081%

    No Known Activations