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

    Neuronpedia

    INDEX
    Explanations

    words related to terms or phrases used in certain contexts, potentially with a focus on specific groups, sectors, or issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lua
    -0.77
    ople
    -0.74
     IPM
    -0.73
    hua
    -0.71
    CVE
    -0.70
    ructose
    -0.70
     Clause
    -0.67
    inventoryQuantity
    -0.67
    itiveness
    -0.67
    steamapps
    -0.66
    POSITIVE LOGITS
     besides
    1.30
    worldly
    1.14
     than
    0.99
     unrelated
    0.83
    than
    0.81
    iations
    0.81
     includ
    0.76
     factors
    0.76
    isms
    0.75
    illary
    0.75
    Act Density 2.394%

    No Known Activations