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

    Neuronpedia

    INDEX
    Explanations

    references to windows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    window and related context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.45
     Lef
    -0.43
     Celtic
    -0.42
    ]=$
    -0.40
    liest
    -0.39
     Mel
    -0.39
    ']='
    -0.38
    tis
    -0.38
     Bost
    -0.38
    elif
    -0.37
    POSITIVE LOGITS
     window
    1.88
     Window
    1.84
    Window
    1.69
    window
    1.66
     WINDOW
    1.59
     fenêtre
    1.42
    WINDOW
    1.41
     ventana
    1.30
     windows
    1.27
     Fenster
    1.23
    Act Density 0.005%

    No Known Activations