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

    Neuronpedia

    INDEX
    Explanations

    locations and actions related to movement, especially walking and driving

    oai_token-act-pair · gpt-3.5-turbo

    actions or activities related to movement or engagement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phies
    -0.72
    ema
    -0.65
    lands
    -0.62
    cknowled
    -0.61
    pora
    -0.59
    rust
    -0.59
    aryn
    -0.58
    ulnerability
    -0.58
    ogene
    -0.57
    rely
    -0.57
    POSITIVE LOGITS
    itored
    0.77
    heses
    0.70
    tips
    0.68
    seless
    0.67
    Pand
    0.66
    Sov
    0.65
    Constructed
    0.65
     exha
    0.62
    RAG
    0.62
     Classes
    0.61
    Act Density 0.190%

    No Known Activations