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

    Neuronpedia

    INDEX
    Explanations

    terms related to confidentiality or classified information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulin
    -0.15
    رÙĪد
    -0.15
    annis
    -0.14
    errupted
    -0.14
    erner
    -0.14
    ابÙĤÙĩ
    -0.14
    bery
    -0.14
    lings
    -0.14
    pg
    -0.14
    ucher
    -0.14
    POSITIVE LOGITS
     conf
    0.21
    /conf
    0.20
     Conf
    0.18
    SSION
    0.18
    used
    0.17
    licts
    0.17
    urb
    0.16
    ément
    0.16
    lict
    0.16
    озд
    0.16
    Act Density 0.025%

    No Known Activations