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

    Neuronpedia

    INDEX
    Explanations

    assertions of contradiction or opposition in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words/tokens following "the" or "exact" indicating an opposite

    np_acts-logits-general · gemini-2.0-flash

    exact opposite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.60
     >=",
    -0.59
     perdon
    -0.49
     Protobuf
    -0.48
    acakt
    -0.46
     ErrIntOverflow
    -0.45
    utilisons
    -0.45
    JspWriter
    -0.45
    Rohy
    -0.44
    atisfactory
    -0.43
    POSITIVE LOGITS
     reverse
    3.00
     opposite
    2.54
     Reverse
    2.52
    reverse
    2.50
     reversed
    2.47
    Reverse
    2.38
     inverse
    2.36
    opposite
    2.25
     reverses
    2.22
     reversing
    2.13
    Act Density 0.589%

    No Known Activations