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

    Neuronpedia

    INDEX
    Explanations

    legal terms and court-related language

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legal cases and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.93
    ?).
    -0.86
    ãĤ´ãĥ³
    -0.83
    !).
    -0.75
    )?
    -0.71
    ?),
    -0.69
    ).
    -0.69
    ãĤ¨ãĥ«
    -0.69
    %).
    -0.67
    ):
    -0.66
    POSITIVE LOGITS
     ..."
    1.62
     âĢ¦"
    1.50
     [...]
    1.31
     ['
    1.13
     [
    1.13
     [-
    1.12
     [âĢ¦]
    1.08
     [/
    1.02
    sic
    1.02
    ..."
    1.02
    Act Density 1.140%

    No Known Activations