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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases that express observation or perception, particularly "It seems" or similar constructions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus
    New Auto-Interp
    Negative Logits
     Cáceres
    -0.72
    vertx
    -0.72
    Переваги
    -0.72
     Kaufman
    -0.70
    katy
    -0.67
     scolaires
    -0.67
    yı
    -0.67
    toarele
    -0.67
     lunghi
    -0.66
    holi
    -0.66
    POSITIVE LOGITS
     seem
    1.02
     Seem
    1.01
    seem
    1.00
    seems
    0.98
     seemed
    0.95
     seems
    0.94
    Seems
    0.94
     Seems
    0.87
    seemed
    0.85
    pearing
    0.81
    Act Density 0.096%

    No Known Activations