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

    Neuronpedia

    INDEX
    Explanations

    references to individuals or entities involved in reporting or academia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apus
    -0.16
    argent
    -0.16
    yna
    -0.15
    ãĥ©ãĤ¹
    -0.15
    avaÅŁ
    -0.15
    arius
    -0.15
     buá»ķi
    -0.14
    ÙĨاء
    -0.14
    .volley
    -0.14
    æ¸Ī
    -0.14
    POSITIVE LOGITS
     Democracy
    0.18
    utt
    0.17
    orts
    0.15
    AMY
    0.15
    avn
    0.14
     democracy
    0.14
    won
    0.14
    .openg
    0.14
    BarItem
    0.14
    347
    0.14
    Act Density 0.003%

    No Known Activations