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

    Neuronpedia

    INDEX
    Explanations

    the surname "Corwin"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "win" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pinpoint
    -0.73
     sensitive
    -0.69
     reservations
    -0.67
     delinquent
    -0.66
     ubiquitous
    -0.64
    ¥ŀ
    -0.64
     unnamed
    -0.64
    OTOS
    -0.64
     identifying
    -0.63
     unnecess
    -0.63
    POSITIVE LOGITS
    ners
    1.48
    win
    1.27
    ning
    1.00
    nings
    0.99
    ner
    0.94
    vier
    0.93
    throp
    0.91
    athon
    0.89
    iculture
    0.89
    boats
    0.87
    Act Density 0.004%

    No Known Activations