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

    Neuronpedia

    INDEX
    Explanations

    mentions of "int" in any form, particularly as a prefix in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azzi
    -0.15
    uds
    -0.15
    ulg
    -0.14
     Kramer
    -0.14
    EDITOR
    -0.14
    ãĥį
    -0.14
    rpc
    -0.14
    ultz
    -0.14
     Norm
    -0.14
    OrCreate
    -0.14
    POSITIVE LOGITS
    roducing
    0.20
    repid
    0.19
    umes
    0.19
    RODUCTION
    0.19
    angible
    0.18
    rodu
    0.18
    emann
    0.17
    ention
    0.17
    oler
    0.17
    roduced
    0.17
    Act Density 0.027%

    No Known Activations