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

    Neuronpedia

    INDEX
    Explanations

    helmet-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to helmets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atoes
    -0.76
    quart
    -0.76
    icult
    -0.71
    agent
    -0.70
    angu
    -0.69
    hower
    -0.69
     Restaur
    -0.67
    inity
    -0.67
    intelligence
    -0.66
    course
    -0.65
    POSITIVE LOGITS
     worn
    1.09
     goggles
    1.05
     wearer
    1.03
     helmets
    1.00
     helmet
    0.96
     headset
    0.85
     equipped
    0.83
     straps
    0.83
     headsets
    0.79
     sunglasses
    0.78
    Act Density 0.054%

    No Known Activations