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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diplomatic assignments and interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public affairs and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brakes
    -0.65
    quickShipAvailable
    -0.57
    apego
    -0.55
     Flavoring
    -0.54
    ÃįÃį
    -0.54
     Yorkers
    -0.52
    maxwell
    -0.52
    hran
    -0.52
    Afee
    -0.52
    ifact
    -0.51
    POSITIVE LOGITS
     guise
    0.84
     vicinity
    0.77
     manner
    0.70
     nutshell
    0.68
     contexts
    0.66
     mode
    0.66
     territory
    0.64
     neighb
    0.62
     precincts
    0.62
    vironments
    0.61
    Act Density 1.513%

    No Known Activations