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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "Inf" followed by a number, such as "Inf8" or "Inf9"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific internet domain or website

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.84
    \\\\\\\\
    -0.83
    ãģ®éŃĶ
    -0.76
    manship
    -0.74
    âķIJâķIJ
    -0.71
    UAL
    -0.70
    soDeliveryDate
    -0.68
    OPLE
    -0.67
     Athletic
    -0.66
     Dare
    -0.65
    POSITIVE LOGITS
    rared
    1.19
    inite
    1.13
    ertility
    1.13
    lamm
    1.12
    rastructure
    1.11
    luence
    1.11
    ractions
    1.08
    amous
    1.06
    iltration
    1.04
    inity
    1.04
    Act Density 0.013%

    No Known Activations