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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "nor" and its variations in context of negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ्ट
    -0.69
    Apoll
    -0.66
    fwd
    -0.66
    SAX
    -0.65
    pezi
    -0.65
    migrationBuilder
    -0.65
     عظ
    -0.64
    tacles
    -0.63
     Woodruff
    -0.63
    UpdateTime
    -0.62
    POSITIVE LOGITS
    neither
    1.43
     neither
    1.37
    Neither
    1.26
     nor
    1.22
    Nor
    1.21
     Neither
    1.20
    nor
    1.15
     NOR
    1.13
     Nor
    1.10
     Norris
    1.06
    Act Density 0.117%

    No Known Activations