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

    Neuronpedia

    INDEX
    Explanations

    locations with the word "Falls" in their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical features related to waterfalls and falls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mble
    -0.79
    ech
    -0.67
     Luther
    -0.67
    anyahu
    -0.66
    rons
    -0.65
     habitable
    -0.64
    rious
    -0.64
    other
    -0.64
    pai
    -0.63
    micro
    -0.61
    POSITIVE LOGITS
     Falls
    1.28
    dale
    0.92
     Meadows
    0.80
    ashtra
    0.77
    falls
    0.76
    burgh
    0.75
     Rite
    0.74
    head
    0.74
    bows
    0.73
     Creek
    0.72
    Act Density 0.008%

    No Known Activations