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

    Neuronpedia

    INDEX
    Explanations

    elements related to stealth and subtle communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uments
    -0.16
    etat
    -0.15
    xcb
    -0.15
    yat
    -0.15
    chl
    -0.14
    ilton
    -0.14
    ospace
    -0.14
    иÑĢа
    -0.14
    à¹Īà¸Ńส
    -0.13
    esser
    -0.13
    POSITIVE LOGITS
     Stealth
    0.19
    ness
    0.17
    dB
    0.16
     stealth
    0.15
    gram
    0.15
    icious
    0.15
    ercul
    0.14
    iveness
    0.14
    alc
    0.14
     judgment
    0.14
    Act Density 0.102%

    No Known Activations