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

    Neuronpedia

    INDEX
    Explanations

    the word "pomegranate."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ome"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iversal
    -0.83
    icter
    -0.77
    lished
    -0.74
    Ó
    -0.73
    pring
    -0.72
    neapolis
    -0.70
    olicy
    -0.69
    rontal
    -0.67
    ulence
    -0.67
    istas
    -0.67
    POSITIVE LOGITS
    gran
    0.92
    ome
    0.90
    lette
    0.84
    chan
    0.76
     prolifer
    0.75
    lla
    0.74
    gger
    0.74
    ppa
    0.71
    anism
    0.71
    ña
    0.71
    Act Density 0.019%

    No Known Activations