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

    Neuronpedia

    INDEX
    Explanations

    countries and governmental bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries and political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sqor
    -1.01
    interstitial
    -0.83
    foundland
    -0.79
    advertisement
    -0.76
    actionDate
    -0.75
    soDeliveryDate
    -0.72
    anmar
    -0.71
    umph
    -0.69
    insula
    -0.66
    sembly
    -0.66
    POSITIVE LOGITS
     chooses
    1.09
     decides
    1.08
     intends
    1.01
     executes
    1.01
     pays
    0.98
     collects
    0.97
     considers
    0.96
     spends
    0.96
     selects
    0.95
     wants
    0.95
    Act Density 0.260%

    No Known Activations