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

    Neuronpedia

    INDEX
    Explanations

    common punctuation and structure elements that indicate questions or transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Promise
    -0.15
    ersh
    -0.14
     lam
    -0.14
     spoiler
    -0.14
    /pdf
    -0.13
    رÛĮب
    -0.13
    ãĥ©ãĤ¤ãĥ³
    -0.13
     ç¤
    -0.13
     scram
    -0.13
     Kund
    -0.13
    POSITIVE LOGITS
    itsu
    0.15
    olds
    0.15
    urons
    0.14
    malink
    0.14
    anim
    0.14
    lichkeit
    0.13
    HK
    0.13
    gw
    0.13
    onym
    0.13
    _IMPL
    0.13
    Act Density 0.004%

    No Known Activations