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

    Neuronpedia

    INDEX
    Explanations

    the word "word"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "word."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.77
    psey
    -0.71
    cffff
    -0.68
     Skydragon
    -0.68
    asio
    -0.67
    kens
    -0.67
    abama
    -0.67
    panic
    -0.65
     Flavoring
    -0.64
    angan
    -0.64
    POSITIVE LOGITS
    press
    1.15
    sworth
    0.91
     word
    0.85
     processor
    0.80
    naire
    0.77
    ially
    0.75
    mith
    0.72
     uttered
    0.71
     Word
    0.71
    word
    0.71
    Act Density 0.020%

    No Known Activations