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

    Neuronpedia

    INDEX
    Explanations

    references to outdoor activities and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hotels
    -0.55
     égard
    -0.55
     pyramid
    -0.47
    ég
    -0.47
    ristiana
    -0.46
    arily
    -0.46
    Код
    -0.45
    ule
    -0.45
    ing
    -0.44
     Hermione
    -0.44
    POSITIVE LOGITS
     draußen
    0.98
     ngoài
    0.95
     afield
    0.91
     outdoors
    0.86
    MessageTagHelper
    0.85
     outside
    0.82
    外面
    0.81
    extAlignment
    0.80
     externes
    0.80
    RectangleBorder
    0.80
    Act Density 0.176%

    No Known Activations