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

    Neuronpedia

    INDEX
    Explanations

    words related to achieving a high status or rank

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with social commentary and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANE
    -0.81
    7601
    -0.75
     AFB
    -0.72
     Rhodes
    -0.72
    $.
    -0.71
    uary
    -0.69
    kefeller
    -0.68
    $,
    -0.68
    Mike
    -0.67
     Pegasus
    -0.66
    POSITIVE LOGITS
     âĢ
    2.68
    âĢ
    1.82
     â
    1.45
     **
    1.42
     âĸº
    1.39
    ãĢ
    1.38
     âĶ
    1.37
    âĢł
    1.32
     Å
    1.32
     ¶
    1.29
    Act Density 3.393%

    No Known Activations