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

    Neuronpedia

    INDEX
    Explanations

    terms related to punishment and revenge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imanapun
    -0.58
     Wikimedijinoj
    -0.56
    Statuses
    -0.56
     postData
    -0.55
    rfloor
    -0.55
     grø
    -0.54
    OrderStatus
    -0.54
    ########.
    -0.53
     않았
    -0.53
    httphttps
    -0.51
    POSITIVE LOGITS
     punishment
    1.52
     punish
    1.49
     reward
    1.42
     punishments
    1.36
     punished
    1.33
     punishing
    1.32
     revenge
    1.30
     Punishment
    1.29
     rewards
    1.27
     Reward
    1.24
    Act Density 0.306%

    No Known Activations