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

    Neuronpedia

    INDEX
    Explanations

    specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warranties
    -0.62
    MON
    -0.62
     plates
    -0.62
     specials
    -0.61
     macros
    -0.61
     portfolios
    -0.60
     Doors
    -0.59
     pickups
    -0.59
     personalities
    -0.58
     positives
    -0.58
    POSITIVE LOGITS
    cture
    0.89
    isphere
    0.83
    hei
    0.74
    ranch
    0.73
    sha
    0.70
    gha
    0.70
    ylon
    0.68
    ebin
    0.68
    ichick
    0.66
    ios
    0.65
    Act Density 0.180%

    No Known Activations