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

    Neuronpedia

    INDEX
    Explanations

    references to silence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "silent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sych
    -0.79
    lete
    -0.72
    akeru
    -0.72
    MAL
    -0.71
    GAN
    -0.71
    Lago
    -0.70
    mia
    -0.68
    HY
    -0.68
    artney
    -0.67
    hews
    -0.67
    POSITIVE LOGITS
     aperture
    0.79
     bystand
    0.74
     silent
    0.72
     autom
    0.72
    encing
    0.72
     fry
    0.71
     eyel
    0.69
     silhou
    0.67
     breathing
    0.67
     vigil
    0.67
    Act Density 0.014%

    No Known Activations