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

    Neuronpedia

    INDEX
    Explanations

    locations or landmarks with the word "Falls" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to locations associated with waterfalls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rons
    -0.68
     Luther
    -0.66
     habitable
    -0.64
    anyahu
    -0.63
    oen
    -0.63
    illary
    -0.63
    llular
    -0.62
    ech
    -0.61
     droid
    -0.61
    mble
    -0.60
    POSITIVE LOGITS
     Falls
    1.08
    dale
    0.88
    ujah
    0.80
    head
    0.80
    burg
    0.75
    LEY
    0.75
    ashtra
    0.74
    falls
    0.74
    aby
    0.73
    opian
    0.73
    Act Density 0.049%

    No Known Activations