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

    Neuronpedia

    INDEX
    Explanations

    places of birth

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     messaging
    -0.71
     ObamaCare
    -0.64
     airports
    -0.63
    etheless
    -0.62
     finalized
    -0.61
     DEFENSE
    -0.61
     censored
    -0.60
     paperback
    -0.60
     editing
    -0.59
     NFL
    -0.59
    POSITIVE LOGITS
     Seym
    0.94
     Piet
    0.80
     Kaf
    0.76
     Nanto
    0.76
     Sai
    0.76
     Gaw
    0.75
    elia
    0.73
     Paw
    0.73
    ynt
    0.72
    mie
    0.70
    Act Density 0.384%

    No Known Activations