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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical levels or boundaries, especially in terms of "upper" or "lower" limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Réponses
    -0.96
     DiCaprio
    -0.79
     Jovi
    -0.75
    ismet
    -0.71
     Params
    -0.70
     Bruges
    -0.70
    feats
    -0.68
    Filmographie
    -0.67
    ➟
    -0.67
    ログ
    -0.66
    POSITIVE LOGITS
     Upper
    1.19
     UPPER
    1.13
    Upper
    1.12
    UPPER
    1.10
     upper
    1.04
    upper
    0.96
    Lower
    0.88
     Lower
    0.81
    LOWER
    0.81
     LOWER
    0.80
    Act Density 0.076%

    No Known Activations