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

    Neuronpedia

    INDEX
    Explanations

    words expressing negation or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.74
     Exacts
    -0.73
    setVerticalGroup
    -0.72
    PhysRev
    -0.71
    webElement
    -0.68
    PreferredItem
    -0.67
    NameInMap
    -0.67
    دانشنامهٔ
    -0.67
    Spoljašnje
    -0.66
     otomatig
    -0.64
    POSITIVE LOGITS
     useContext
    0.54
    你能
    0.50
    geslacht
    0.47
    SizeF
    0.46
     becauſe
    0.46
    ttemberg
    0.46
    Filmografie
    0.45
     lenker
    0.45
    zugehen
    0.45
    你有
    0.43
    Act Density 1.133%

    No Known Activations