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

    Neuronpedia

    INDEX
    Explanations

    keywords indicating performance and function within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uhe
    -0.15
    lescope
    -0.14
    Specifier
    -0.13
    uye
    -0.13
    apon
    -0.13
    culate
    -0.13
    iliki
    -0.13
    minate
    -0.13
    lla
    -0.13
     fluid
    -0.13
    POSITIVE LOGITS
    serter
    0.14
    /stretch
    0.13
     dün
    0.13
    rij
    0.13
    äºĭæĥħ
    0.13
     ëĵ£
    0.13
    neath
    0.13
     ngh
    0.13
    -transitional
    0.12
    idden
    0.12
    Act Density 0.009%

    No Known Activations