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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating uncertainty or gradation in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    complexContent
    -0.49
     ModelExpression
    -0.47
     مرئيه
    -0.47
    featureID
    -0.45
    PropertyChanging
    -0.45
     الرياضيه
    -0.45
    󠁴
    -0.44
    SourceChecksum
    -0.44
    stdc
    -0.41
    AnchorStyles
    -0.41
    POSITIVE LOGITS
    undefined
    0.54
     Menschheit
    0.50
    ritsar
    0.49
    recently
    0.48
    assertNotNull
    0.47
     चीज़ों
    0.47
    Something
    0.47
     recently
    0.47
    Recently
    0.46
     niečo
    0.46
    Act Density 0.169%

    No Known Activations