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

    Neuronpedia

    INDEX
    Explanations

    statements expressing possibility or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scoped
    -0.16
    etag
    -0.15
    InnerText
    -0.15
    uhe
    -0.14
    eren
    -0.14
    idia
    -0.14
    .bc
    -0.14
    ffi
    -0.14
    %%%%%%%%%%%%%%%%
    -0.14
    UIAlertAction
    -0.14
    POSITIVE LOGITS
    ors
    0.17
    les
    0.16
    ily
    0.15
    央
    0.14
    nam
    0.14
    pls
    0.14
    weather
    0.14
    anges
    0.14
    hem
    0.14
    ayout
    0.14
    Act Density 0.096%

    No Known Activations