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

    Neuronpedia

    INDEX
    Explanations

    negations and terms indicating contraindications or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alone
    -1.02
    alone
    -1.02
     sole
    -1.00
    Alone
    -0.99
     ALONE
    -0.99
     solely
    -0.95
    ONLY
    -0.93
    Sole
    -0.88
    sole
    -0.87
     exclusively
    -0.86
    POSITIVE LOGITS
     oly
    0.54
     тока
    0.50
    zczy
    0.43
    醐
    0.42
     ol
    0.41
     nevera
    0.40
    ")));
    0.40
    簧
    0.40
    ('');
    0.40
     Kunt
    0.40
    Act Density 0.167%

    No Known Activations