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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks used in dialogue or attributed speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -1.05
     rul
    -1.02
    ¥ŀ
    -1.00
     confir
    -1.00
    Þ
    -1.00
     oun
    -0.96
     exting
    -0.94
     earthqu
    -0.93
     occas
    -0.93
     satell
    -0.92
    POSITIVE LOGITS
    They
    1.92
    And
    1.87
    But
    1.87
    We
    1.83
    It
    1.82
    That
    1.81
    Especially
    1.81
    Everybody
    1.81
    Nobody
    1.79
    Otherwise
    1.79
    Act Density 0.129%

    No Known Activations