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

    Neuronpedia

    INDEX
    Explanations

    mentions of masks

    oai_token-act-pair · gpt-3.5-turbo

    references to masks and their various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Yards
    -0.78
    course
    -0.76
    scill
    -0.72
    hower
    -0.70
    ally
    -0.69
    athan
    -0.67
    UNCH
    -0.66
    izabeth
    -0.65
    ynes
    -0.64
     Citation
    -0.64
    POSITIVE LOGITS
    resses
    0.97
     masks
    0.93
     wearer
    0.85
    ullah
    0.84
     mask
    0.82
     Mask
    0.80
    ilated
    0.79
    Mask
    0.73
    daq
    0.71
    lain
    0.71
    Act Density 0.038%

    No Known Activations