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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical activities or movements

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement and activities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ema
    -0.69
    cknowled
    -0.66
    nea
    -0.64
    pora
    -0.62
    ulnerability
    -0.62
     imprint
    -0.60
     kicker
    -0.60
     rider
    -0.59
    kie
    -0.58
     homepage
    -0.58
    POSITIVE LOGITS
     exha
    0.73
    Sov
    0.70
    sth
    0.69
     frantically
    0.67
    redients
    0.66
    RAG
    0.66
    flix
    0.65
    Pand
    0.65
    Constructed
    0.64
     CP
    0.63
    Act Density 0.236%

    No Known Activations