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

    Neuronpedia

    INDEX
    Explanations

    strong affirmations or expressions of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ison
    -0.17
    ÑĤеÑħ
    -0.15
    ague
    -0.15
    YD
    -0.14
    iele
    -0.14
    sdale
    -0.14
    icky
    -0.14
    stra
    -0.14
     Leone
    -0.14
     RootState
    -0.14
    POSITIVE LOGITS
    OLUTE
    0.21
    ElementsBy
    0.18
     positively
    0.18
    olutely
    0.18
    utely
    0.17
     absolutely
    0.17
    aire
    0.16
    idia
    0.15
     flat
    0.15
    olut
    0.15
    Act Density 0.016%

    No Known Activations