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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating awareness or recognition of situations or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ories
    -0.17
     indeed
    -0.15
    æ¡
    -0.15
    нÑĮ
    -0.14
    ochrome
    -0.14
    lemen
    -0.14
    oksen
    -0.14
    inho
    -0.14
    itemap
    -0.14
    ReadWrite
    -0.14
    POSITIVE LOGITS
     til
    0.15
     Dissertation
    0.15
     likely
    0.15
    ilig
    0.14
    chor
    0.14
    LP
    0.13
    antes
    0.13
    likely
    0.13
    åįļ士
    0.13
    ัà¸Ĺ
    0.13
    Act Density 0.123%

    No Known Activations