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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies or finance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tracks
    -0.75
    checks
    -0.71
    lines
    -0.70
    adobe
    -0.68
    versions
    -0.67
    naires
    -0.67
    raising
    -0.66
    paralle
    -0.64
    packages
    -0.64
     UM
    -0.64
    POSITIVE LOGITS
     mention
    1.33
    asted
    0.86
     compensate
    0.82
     appease
    0.80
     worry
    0.79
    asters
    0.79
     capitalize
    0.79
     emphasize
    0.76
    adies
    0.76
     exceed
    0.75
    Act Density 0.031%

    No Known Activations