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

    Neuronpedia

    INDEX
    Explanations

    keywords related to physical exercise and weight training

    oai_token-act-pair · gpt-3.5-turbo

    references to weight and weight-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BLE
    -0.86
    ICLE
    -0.80
     Gutenberg
    -0.75
     Noir
    -0.74
     Suc
    -0.70
    xon
    -0.68
    oral
    -0.68
     VIS
    -0.68
    ï
    -0.67
     Mb
    -0.67
    POSITIVE LOGITS
    lifting
    1.08
     weights
    0.96
    weight
    0.96
    lessness
    0.94
    weights
    0.93
     heaviest
    0.89
    lif
    0.88
     weight
    0.86
    loss
    0.85
    iless
    0.83
    Act Density 0.023%

    No Known Activations