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

    Neuronpedia

    INDEX
    Explanations

    references to metrics and measurements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ryo
    -0.17
    ä¹ĭä¸Ģ
    -0.16
    ijkl
    -0.14
    :async
    -0.14
    enco
    -0.14
    ouv
    -0.13
    idor
    -0.13
    him
    -0.13
     himself
    -0.13
    awy
    -0.13
    POSITIVE LOGITS
     folks
    0.45
     gentlemen
    0.42
     guys
    0.38
     ladies
    0.37
     boys
    0.37
     friends
    0.36
     buddy
    0.35
     sir
    0.34
     Fol
    0.34
     mate
    0.33
    Act Density 0.836%

    No Known Activations