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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal rules and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çļĦ人
    -0.18
    erval
    -0.16
    ãģ®äºº
    -0.16
    iego
    -0.15
    ibt
    -0.15
    appa
    -0.15
    Ñĩий
    -0.15
    edla
    -0.14
    iedo
    -0.14
    ÙħاÙħ
    -0.14
    POSITIVE LOGITS
     them
    0.18
    stroy
    0.15
    æľīçļĦ
    0.15
     they
    0.14
    631
    0.14
     Ñģами
    0.14
    634
    0.14
    703
    0.14
    ienen
    0.14
     Affero
    0.14
    Act Density 0.289%

    No Known Activations