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

    Neuronpedia

    INDEX
    Explanations

    descriptions of unique characteristics, projects, contributions, or situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bárbara
    -0.51
     extrait
    -0.50
     marchand
    -0.50
    Kjelder
    -0.48
     oreille
    -0.48
     romain
    -0.47
    Тарихы
    -0.47
     effectivement
    -0.47
     joyeux
    -0.46
     écla
    -0.45
    POSITIVE LOGITS
     unique
    1.03
    unique
    0.98
     Unique
    0.97
     UNIQUE
    0.95
    Unique
    0.94
    UNIQUE
    0.85
     uniqueness
    0.83
     uniques
    0.76
    queness
    0.76
     uniquely
    0.75
    Act Density 0.108%

    No Known Activations