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

    Neuronpedia

    INDEX
    Explanations

    references to masks or the act of wearing masks

    oai_token-act-pair · gpt-3.5-turbo

    references to masks or mask-wearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yards
    -0.76
    course
    -0.73
    scill
    -0.69
    ynes
    -0.68
    ndra
    -0.67
     Dynamics
    -0.66
    atican
    -0.66
    nie
    -0.64
    GGGGGGGG
    -0.62
    Ĵ
    -0.61
    POSITIVE LOGITS
    resses
    1.09
     masks
    0.94
     mask
    0.92
    ullah
    0.84
     wearer
    0.81
    mask
    0.80
     Mask
    0.79
    ilated
    0.79
     disgu
    0.79
    lets
    0.75
    Act Density 0.078%

    No Known Activations