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

    Neuronpedia

    INDEX
    Explanations

    references to comparisons or duality between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yucatán
    -0.68
    er
    -0.67
     Smoky
    -0.65
    ه‌ای
    -0.64
     residue
    -0.63
     Amelia
    -0.63
     Creole
    -0.62
     Rena
    -0.61
     monica
    -0.60
    ckley
    -0.60
    POSITIVE LOGITS
     both
    2.06
    BOTH
    1.98
    both
    1.94
     Both
    1.86
    Both
    1.84
     BOTH
    1.75
    Ambos
    1.61
     beide
    1.46
     ambos
    1.40
     beider
    1.38
    Act Density 0.096%

    No Known Activations