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

    Neuronpedia

    INDEX
    Explanations

    narratives involving knocking or door-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flucht
    -0.54
    kels
    -0.47
    cine
    -0.46
    ais
    -0.44
    Vedi
    -0.44
    tenham
    -0.44
    ceans
    -0.43
    dzi
    -0.43
    ENABLED
    -0.43
    fiddle
    -0.42
    POSITIVE LOGITS
     knocking
    1.35
     knocks
    1.26
     knock
    1.25
    Knock
    1.18
     doorbell
    1.14
    knock
    1.11
     knocked
    1.08
     Knock
    1.07
     door
    1.00
     Kno
    0.95
    Act Density 0.187%

    No Known Activations