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

    Neuronpedia

    INDEX
    Explanations

    references to pairs of objects or data entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Holtz
    -0.92
     ['./
    -0.86
    })));
    -0.85
    ABASES
    -0.79
    /**/*.
    -0.77
     للمعارف
    -0.77
    ,:);
    -0.75
     Wul
    -0.75
    ])));
    -0.74
    antism
    -0.73
    POSITIVE LOGITS
     PAIR
    1.69
     pairs
    1.66
     Pair
    1.63
     pair
    1.63
     paire
    1.53
     Pairs
    1.53
    pair
    1.43
    Pair
    1.41
    PAIR
    1.36
    pairs
    1.35
    Act Density 0.085%

    No Known Activations