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

    Neuronpedia

    INDEX
    Explanations

    terms related to punishment and punitive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -1.01
     propOrder
    -0.97
     переписи
    -0.77
    ThroughAttribute
    -0.76
     AssemblyCompany
    -0.73
    ########.
    -0.73
     مشين
    -0.73
    sidemargin
    -0.72
    lgari
    -0.72
    MigrationBuilder
    -0.72
    POSITIVE LOGITS
     punishment
    2.62
     punish
    2.38
     punished
    2.14
     Punishment
    2.08
     punishments
    2.03
    pun
    1.97
     punishing
    1.90
    Pun
    1.79
     pun
    1.73
     Pun
    1.62
    Act Density 0.097%

    No Known Activations