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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize surpassing limits or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.45
     Artículos
    -0.45
    IBOutlet
    -0.42
    GOTREF
    -0.39
     thiệu
    -0.37
    ImageContext
    -0.35
    dataclass
    -0.34
     déposer
    -0.34
    Clik
    -0.33
    /*
    -0.32
    POSITIVE LOGITS
     beyond
    2.02
    beyond
    1.99
     Beyond
    1.94
     BEYOND
    1.87
    Beyond
    1.84
    YOND
    1.51
    delà
    1.16
    超越
    0.97
    oltre
    0.91
    超出
    0.91
    Act Density 0.204%

    No Known Activations