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

    Neuronpedia

    INDEX
    Explanations

    titles of books, movies, and television shows

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poke
    -0.76
    />
    -0.76
    gpu
    -0.75
     undergo
    -0.74
    imposed
    -0.70
    âĶĢ
    -0.70
     patiently
    -0.70
    serving
    -0.68
     according
    -0.68
     stationed
    -0.68
    POSITIVE LOGITS
    atre
    1.12
     Simpsons
    1.12
     Greatest
    1.12
     Stranger
    1.08
     Lost
    1.06
    oret
    1.06
    odor
    1.05
     Legend
    1.05
     Alchemist
    1.03
     Martian
    1.03
    Act Density 0.081%

    No Known Activations