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

    Neuronpedia

    INDEX
    Explanations

    phrases related to bundles or grouping items together

    oai_token-act-pair · gpt-3.5-turbo

    terms related to grouping or packaging items together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Correction
    -0.83
    roe
    -0.74
    manship
    -0.72
     Inqu
    -0.71
    humane
    -0.71
    throp
    -0.70
     Holden
    -0.69
     Northwestern
    -0.68
     Obs
    -0.68
     Lear
    -0.67
    POSITIVE LOGITS
     Bund
    3.44
     bund
    3.26
     bundled
    2.93
     bundles
    2.44
     bundle
    2.31
    undle
    1.98
     Bundle
    1.93
     packaged
    1.44
     packages
    1.07
    Package
    1.05
    Act Density 0.045%

    No Known Activations