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

    Neuronpedia

    INDEX
    Explanations

    phrases that express past actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egin
    -0.16
    _ARB
    -0.16
    ably
    -0.16
     mát
    -0.15
    llib
    -0.15
    ylvania
    -0.15
    ILD
    -0.15
    naires
    -0.14
    taire
    -0.14
     ê·¸ëŁ°
    -0.13
    POSITIVE LOGITS
    ascal
    0.16
     Await
    0.15
    ri
    0.15
     been
    0.15
    wig
    0.14
    ãĥ«ãĥķ
    0.14
    err
    0.14
    zung
    0.14
    abol
    0.13
    unce
    0.13
    Act Density 0.018%

    No Known Activations