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

    Neuronpedia

    INDEX
    Explanations

    references to different types of shirts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InvalidProtocol
    -0.76
     تضيفلها
    -0.75
    "])
    -0.71
    </tfoot>
    -0.69
    __))
    -0.69
    期刊论文
    -0.63
    ).]
    -0.63
    gouv
    -0.61
    Aval
    -0.60
     estimés
    -0.60
    POSITIVE LOGITS
     shirt
    3.23
     shirts
    2.94
     Shirt
    2.90
    shirt
    2.81
    Shirt
    2.75
     Shirts
    2.62
    shirts
    2.46
    Shirts
    2.19
    hirt
    2.03
     camisa
    1.78
    Act Density 0.049%

    No Known Activations