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

    Neuronpedia

    INDEX
    Explanations

    titles and roles related to leadership and professional positions

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

    preceding a comma

    np_acts-logits-general · gemini-2.0-flash

    lists of people and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    -1.16
    ,
    -1.12
    ،
    -1.08
    ,...
    -1.07
    !,
    -1.02
    ,…
    -0.97
    $,
    -0.94
    ，《
    -0.90
    ?,
    -0.90
     ,
    -0.90
    POSITIVE LOGITS
    ]='\
    0.74
     تانيه
    0.73
    RegressionTest
    0.73
     myſelf
    0.71
    }))
    0.71
     itſelf
    0.71
    ſelf
    0.69
     Efq
    0.68
    =")
    0.68
    )++;
    0.67
    Act Density 1.184%

    No Known Activations