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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters and regulations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or phrases ending with a comma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.72
    ²¾
    -0.71
    ingu
    -0.67
     helicop
    -0.65
     brill
    -0.64
     consec
    -0.64
    cend
    -0.63
     favourites
    -0.63
    ¬¼
    -0.63
    eb
    -0.61
    POSITIVE LOGITS
     reads
    1.09
     according
    0.92
     writes
    0.85
     wrote
    0.85
     says
    0.83
    said
    0.81
     said
    0.80
    according
    0.78
     recalls
    0.76
     observes
    0.72
    Act Density 0.085%

    No Known Activations