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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal observations or predictions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ints
    -0.85
    inventoryQuantity
    -0.80
    eworks
    -0.80
    abilities
    -0.78
     Cosponsors
    -0.73
    姫
    -0.73
    sites
    -0.72
     Packs
    -0.72
     Shots
    -0.69
    sts
    -0.69
    POSITIVE LOGITS
     wherein
    1.03
     devoid
    0.95
     governed
    0.93
     where
    0.92
     dominated
    0.89
     rife
    0.89
     littered
    0.85
     filled
    0.85
     consisting
    0.85
     bere
    0.79
    Act Density 0.201%

    No Known Activations