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

    Neuronpedia

    INDEX
    Explanations

    significant words that indicate presence or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umont
    -0.15
     queer
    -0.15
    iever
    -0.14
    mlink
    -0.14
    omanip
    -0.14
     neighbouring
    -0.13
     demi
    -0.13
    αι
    -0.13
    iators
    -0.13
    UnderTest
    -0.13
    POSITIVE LOGITS
    atrice
    0.16
     Atlas
    0.15
    íĴį
    0.15
    ogne
    0.15
     zel
    0.15
     paren
    0.15
     Fle
    0.14
    /latest
    0.14
    nuts
    0.14
    ç´
    0.14
    Act Density 0.000%

    No Known Activations