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

    Neuronpedia

    INDEX
    Explanations

    the syllable "at"

    oai_token-act-pair · gpt-4-turbo

    words related to the concept of 'ateness'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "at"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tsukuyomi
    -0.72
     tremend
    -0.68
    SPONSORED
    -0.68
    gravity
    -0.66
    Winged
    -0.66
    pmwiki
    -0.64
    士
    -0.64
    IDER
    -0.63
    ¥ŀ
    -0.62
     resil
    -0.62
    POSITIVE LOGITS
    mosp
    1.13
    abase
    1.02
    oday
    0.96
    hens
    0.94
    roph
    0.92
     least
    0.91
    rix
    0.90
    rium
    0.90
    arian
    0.89
    ainment
    0.89
    Act Density 0.030%

    No Known Activations