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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pair" and its variations related to relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antism
    -0.66
    ABASES
    -0.65
    "]).
    -0.64
     Holtz
    -0.64
     ['./
    -0.63
    ุทธ
    -0.62
     prec
    -0.60
     mercen
    -0.58
     Undeclared
    -0.57
    =""/>
    -0.57
    POSITIVE LOGITS
     pair
    4.01
     Pair
    3.74
    pair
    3.56
     pairs
    3.54
     PAIR
    3.38
    Pair
    3.37
     Pairs
    3.21
     paire
    3.00
    pairs
    2.94
    PAIR
    2.92
    Act Density 0.062%

    No Known Activations