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

    Neuronpedia

    INDEX
    Explanations

    economic and policy-related terms and numbers

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases related to potential outcomes or implications of policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reporting
    -0.66
     confessed
    -0.65
    itu
    -0.63
     reperto
    -0.63
    Favorite
    -0.61
     guesses
    -0.61
     confession
    -0.61
     knows
    -0.60
     recounts
    -0.60
    noticed
    -0.58
    POSITIVE LOGITS
     exacerbate
    1.26
     worsen
    1.26
     reduce
    1.24
     adversely
    1.21
     stimulate
    1.19
     negatively
    1.19
     affect
    1.14
     boost
    1.13
     discourage
    1.11
     spur
    1.08
    Act Density 0.178%

    No Known Activations