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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to various forms of media or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raman
    -0.15
     rational
    -0.15
    наÑĤ
    -0.15
    997
    -0.14
     Rational
    -0.14
    iris
    -0.14
    eral
    -0.14
    ̣
    -0.13
    æģµ
    -0.13
    纪
    -0.13
    POSITIVE LOGITS
    tru
    0.15
    격
    0.15
    tr
    0.14
    utenberg
    0.14
    urum
    0.13
    ungi
    0.13
     flaw
    0.13
    terior
    0.13
    еÑĢб
    0.13
    Incre
    0.13
    Act Density 0.025%

    No Known Activations