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

    Neuronpedia

    INDEX
    Explanations

    locations or geographic entities

    oai_token-act-pair · gpt-3.5-turbo

    words that consist of short, potentially phonetic-sounding syllables or parts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     capsules
    -0.63
     chains
    -0.62
     priceless
    -0.62
     legacy
    -0.61
     tremend
    -0.61
    FORMATION
    -0.60
     symbolism
    -0.59
     hardcore
    -0.59
    BILITY
    -0.58
     mantle
    -0.58
    POSITIVE LOGITS
    wana
    0.99
    anu
    0.95
    ak
    0.91
    ima
    0.90
    ara
    0.89
    aj
    0.88
    agh
    0.87
    aman
    0.87
    jen
    0.87
    eman
    0.87
    Act Density 0.221%

    No Known Activations