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

    Neuronpedia

    INDEX
    Explanations

    elements and features related to pairs and pairing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tridge
    -0.15
    ëı
    -0.14
    arias
    -0.14
    andex
    -0.14
    uito
    -0.13
    oden
    -0.13
    ħn
    -0.13
    tright
    -0.13
    izr
    -0.13
    naments
    -0.13
    POSITIVE LOGITS
     pair
    1.33
     pairs
    1.16
    pair
    1.15
     Pair
    1.13
    Pair
    1.05
    _pair
    0.99
    pairs
    0.99
    Pairs
    0.89
     pairing
    0.89
    PAIR
    0.87
    Act Density 0.510%

    No Known Activations