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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making updates or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADOS
    -0.17
    unny
    -0.14
    ī
    -0.13
    iyet
    -0.13
     Hund
    -0.13
    .EventArgs
    -0.13
    PLAIN
    -0.13
    ormal
    -0.13
    URN
    -0.13
    andbox
    -0.13
    POSITIVE LOGITS
    (update
    0.21
    /update
    0.21
    (updated
    0.20
     accordingly
    0.20
     status
    0.19
     updated
    0.19
     updating
    0.18
     Updating
    0.17
     update
    0.17
    :update
    0.16
    Act Density 0.068%

    No Known Activations