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

    Neuronpedia

    INDEX
    Explanations

    words related to conflict and resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.76
    ToProps
    -0.51
     ProtoMessage
    -0.49
     queſto
    -0.49
     surla
    -0.47
     Xs
    -0.46
    gsmål
    -0.45
     čierna
    -0.45
    ロウィン
    -0.45
     sandero
    -0.45
    POSITIVE LOGITS
     P
    0.59
     V
    0.57
     M
    0.57
     G
    0.56
     L
    0.56
     Y
    0.56
     F
    0.55
     K
    0.55
     H
    0.54
     D
    0.54
    Act Density 2.622%

    No Known Activations