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
    mauer
    -0.59
    Play
    -0.57
    mR
    -0.56
    window
    -0.53
    se
    -0.52
     window
    -0.52
    R
    -0.51
     Mier
    -0.51
     Dray
    -0.50
    िख
    -0.50
    POSITIVE LOGITS
    theless
    1.06
    bably
    0.94
    BufferException
    0.94
     defaultstate
    0.90
    BibitemShut
    0.89
    ificantly
    0.88
    UALLY
    0.88
    ctically
    0.87
     Probably
    0.87
     probably
    0.87
    Act Density 0.173%

    No Known Activations