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

    Neuronpedia

    INDEX
    Explanations

    emphasis on words that denote moderation or limitation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    анÑģи
    -0.14
    ικÏĮÏĤ
    -0.13
    \<^
    -0.13
    ema
    -0.13
    ÙĨدا
    -0.13
    okud
    -0.13
    eden
    -0.13
    ема
    -0.13
    zeichnet
    -0.13
    vertise
    -0.13
    POSITIVE LOGITS
     a
    0.20
     the
    0.20
    inton
    0.15
     an
    0.15
     those
    0.14
    ehr
    0.14
    uria
    0.14
    zell
    0.14
     one
    0.14
    ither
    0.13
    Act Density 0.227%

    No Known Activations