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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pairs or grouped items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Holtz
    -0.79
    antism
    -0.77
     ['./
    -0.74
    Ong
    -0.68
    Anhalt
    -0.66
     Ong
    -0.66
    enic
    -0.65
    وظ
    -0.63
    [@"
    -0.62
     المكتبه
    -0.62
    POSITIVE LOGITS
     pair
    2.71
     pairs
    2.57
     Pair
    2.56
     PAIR
    2.49
    pair
    2.42
    Pair
    2.32
     Pairs
    2.31
     paire
    2.27
    PAIR
    2.16
    pairs
    2.15
    Act Density 0.041%

    No Known Activations