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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the approval and authorization process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ums
    -0.15
    -browser
    -0.15
    ette
    -0.14
    одо
    -0.14
    ettes
    -0.14
    .Rad
    -0.14
    /do
    -0.13
    are
    -0.13
    odo
    -0.13
    race
    -0.13
    POSITIVE LOGITS
    ably
    0.21
    ance
    0.16
    able
    0.15
    rias
    0.15
    ANCE
    0.15
    VERTISEMENT
    0.15
    447
    0.15
     Ansi
    0.14
    ptal
    0.14
     Zub
    0.14
    Act Density 0.033%

    No Known Activations