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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations such as towns and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    specific place names and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BILITY
    -0.50
     freshman
    -0.48
     FANTASY
    -0.48
    Michigan
    -0.46
     timelines
    -0.46
     warranties
    -0.46
    WARE
    -0.46
    ATIONAL
    -0.46
     bullies
    -0.46
     Michigan
    -0.46
    POSITIVE LOGITS
    iani
    0.77
    én
    0.76
    aban
    0.72
    ÃŃn
    0.71
    endi
    0.71
    chu
    0.68
    acha
    0.68
    adan
    0.67
    ici
    0.67
    enh
    0.66
    Act Density 0.478%

    No Known Activations