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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "both."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Both
    -0.92
    Both
    -0.85
     Ambos
    -0.84
     Beide
    -0.77
     ambos
    -0.77
    Ambos
    -0.75
    both
    -0.69
     BOTH
    -0.65
    BOTH
    -0.65
     beide
    -0.62
    POSITIVE LOGITS
    tagHelperRunner
    0.44
     bek
    0.43
    ...");
    0.42
    0.40
     Walkover
    0.39
    ...");
    0.39
    ...');
    0.39
    Serv
    0.39
    ')));
    0.38
    engen
    0.38
    Act Density 0.007%

    No Known Activations