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

    Neuronpedia

    INDEX
    Explanations

    references to packages being picked up, delivered, or dealing with software or insurance packages

    oai_token-act-pair · gpt-3.5-turbo

    references to packages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Democr
    -0.74
    SOURCE
    -0.72
    BN
    -0.71
    Commission
    -0.70
    Ba
    -0.69
     Democrat
    -0.69
    Hz
    -0.68
    BF
    -0.68
     Greens
    -0.68
     Democratic
    -0.67
    POSITIVE LOGITS
     packages
    1.34
    uggest
    1.22
    ometimes
    1.04
    mith
    1.03
    poons
    1.03
    avorite
    1.01
    hops
    1.01
    htaking
    1.00
    packages
    0.98
    etting
    0.97
    Act Density 0.011%

    No Known Activations