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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unct
    -0.62
    lear
    -0.62
    anson
    -0.61
    adiq
    -0.60
     redacted
    -0.59
    ilde
    -0.59
     correction
    -0.58
     corrective
    -0.58
     pneum
    -0.56
    orically
    -0.56
    POSITIVE LOGITS
     periphery
    0.89
     occasions
    0.84
     behalf
    0.83
     doorstep
    0.79
    grounds
    0.72
     shelf
    0.71
     overlooking
    0.71
    iatus
    0.71
     sidelines
    0.70
     heels
    0.69
    Act Density 0.455%

    No Known Activations