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

    Neuronpedia

    INDEX
    Explanations

    passages indicating the act of writing or referencing contributions in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itel
    -0.18
    rita
    -0.16
    .fhir
    -0.16
    yre
    -0.15
    ToFront
    -0.15
    enton
    -0.14
    xn
    -0.14
    embed
    -0.14
    eldo
    -0.14
    issen
    -0.13
    POSITIVE LOGITS
     Friedman
    0.14
    ocab
    0.14
    /settings
    0.14
    keley
    0.14
    conference
    0.14
    eatures
    0.14
    е
    0.14
    unge
    0.14
    _consts
    0.14
    \a
    0.14
    Act Density 0.027%

    No Known Activations