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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to the name "Win."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the product "Windows" and its various versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶģ
    -0.73
    ¿½
    -0.68
     condu
    -0.67
     trave
    -0.67
    ADRA
    -0.66
    gdala
    -0.64
     unaff
    -0.64
    umn
    -0.64
     gravity
    -0.63
    abad
    -0.63
    POSITIVE LOGITS
    ners
    1.14
    frey
    1.10
    nings
    1.09
    throp
    0.99
    fred
    0.94
    hardt
    0.92
    now
    0.88
    win
    0.85
    NER
    0.84
    ning
    0.83
    Act Density 0.020%

    No Known Activations