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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policies, regulations, and legal terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.77
    terday
    -0.70
     IPM
    -0.68
     TAMADRA
    -0.65
     Archdemon
    -0.64
     Townsend
    -0.62
     Keller
    -0.61
     Beir
    -0.61
     Abrams
    -0.61
     Shutterstock
    -0.61
    POSITIVE LOGITS
     varieties
    0.80
    related
    0.79
     variants
    0.77
     types
    0.77
     categories
    0.75
     titles
    0.75
     configurations
    0.74
     implementations
    0.74
     endorsements
    0.73
     activ
    0.72
    Act Density 23.374%

    No Known Activations