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

    geographical locations and specific place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.80
     retard
    -0.74
     charact
    -0.71
    berman
    -0.70
    acters
    -0.68
     conduc
    -0.67
    agonists
    -0.67
    ULAR
    -0.66
    dyl
    -0.65
    chieve
    -0.65
    POSITIVE LOGITS
     Township
    1.34
     Valley
    1.28
     County
    1.27
     Hills
    1.27
    stown
    1.25
     Junction
    1.24
     Heights
    1.24
     Falls
    1.23
     Village
    1.22
     Farms
    1.22
    Act Density 0.301%

    No Known Activations