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

    Neuronpedia

    INDEX
    Explanations

    references to doors and their actions or conditions

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

    door

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.70
    parsedMessage
    -0.62
    исленность
    -0.59
    saraba
    -0.58
    TypedDataSet
    -0.57
    TagMode
    -0.57
    RegressionTest
    -0.57
     Exacts
    -0.56
     становника
    -0.55
    iNdEx
    -0.54
    POSITIVE LOGITS
     door
    1.36
     doors
    1.32
     Door
    1.23
     DOOR
    1.23
    Door
    1.19
    door
    1.17
     Doors
    1.13
    doors
    1.09
    Doors
    1.09
     Türen
    1.00
    Act Density 0.047%

    No Known Activations