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

    Neuronpedia

    INDEX
    Explanations

    references to face masks and their usage in the context of health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledik
    -0.17
    ifton
    -0.17
    rieve
    -0.15
    νά
    -0.15
    assage
    -0.15
    ãģĭãĤı
    -0.14
    vak
    -0.14
    atto
    -0.13
    abox
    -0.13
     stabil
    -0.13
    POSITIVE LOGITS
     mask
    0.37
     masks
    0.35
     Masks
    0.33
    -mask
    0.30
    .mask
    0.28
     face
    0.28
     Mask
    0.27
    Mask
    0.27
    (mask
    0.26
    -face
    0.26
    Act Density 0.043%

    No Known Activations