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

    Neuronpedia

    INDEX
    Explanations

    numeric or time-related elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åŀ
    -0.16
    arus
    -0.15
    æݧ
    -0.15
    eller
    -0.15
    à¸Ħว
    -0.14
    uard
    -0.14
    usk
    -0.14
    ocket
    -0.14
    lake
    -0.14
    طة
    -0.14
    POSITIVE LOGITS
    radu
    0.16
    duk
    0.15
    untu
    0.15
    mans
    0.15
    ulle
    0.15
     slee
    0.15
    asant
    0.14
    ạt
    0.14
    _xs
    0.14
     bul
    0.14
    Act Density 0.002%

    No Known Activations