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

    Neuronpedia

    INDEX
    Explanations

    instances of the prefix "Int" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.17
    dre
    -0.15
    instances
    -0.15
    hands
    -0.15
    ICIAL
    -0.15
    uds
    -0.14
    ussian
    -0.14
    OrCreate
    -0.14
    308
    -0.14
    ulg
    -0.14
    POSITIVE LOGITS
    rodu
    0.24
    angible
    0.23
    roducing
    0.23
    ense
    0.22
    ended
    0.22
    ention
    0.22
    roduce
    0.22
    ensive
    0.21
    uit
    0.21
    uitive
    0.20
    Act Density 0.027%

    No Known Activations