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

    Neuronpedia

    INDEX
    Explanations

    mentions of helmets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "helmet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VD
    -0.71
     ABE
    -0.67
    tery
    -0.66
    ween
    -0.66
    hower
    -0.66
     Huntington
    -0.64
    atoes
    -0.64
     Bulletin
    -0.64
     Radical
    -0.64
     Roosevelt
    -0.64
    POSITIVE LOGITS
     worn
    1.03
     helmets
    1.03
     helmet
    0.97
     wearer
    0.86
     Helmet
    0.86
     goggles
    0.83
     equipped
    0.77
    lain
    0.76
     adorned
    0.73
    wash
    0.72
    Act Density 0.019%

    No Known Activations