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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EventArgs
    -0.75
    lename
    -0.71
     kasarigan
    -0.70
    TKey
    -0.70
    XtraGrid
    -0.69
    存于互联网档案馆
    -0.68
     setLoading
    -0.68
     respiration
    -0.66
    MessageTagHelper
    -0.66
     vapors
    -0.64
    POSITIVE LOGITS
     without
    1.51
     Without
    1.28
    without
    1.25
    Without
    1.23
     WITHOUT
    1.10
    WITHOUT
    1.00
     despite
    0.98
     above
    0.87
     regardless
    0.87
     tanpa
    0.85
    Act Density 0.136%

    No Known Activations