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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and their associations within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     https
    -0.15
     Tik
    -0.14
    tik
    -0.14
     Wyatt
    -0.13
    =https
    -0.13
    uddy
    -0.13
    isor
    -0.13
    asics
    -0.13
     Covid
    -0.13
    Reviewed
    -0.13
    POSITIVE LOGITS
     Studio
    0.32
    Studio
    0.28
     NYC
    0.22
     Studios
    0.22
     studio
    0.21
    studio
    0.21
     Dinner
    0.20
     AOL
    0.20
     Gmail
    0.19
    NY
    0.19
    Act Density 0.003%

    No Known Activations