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

    Neuronpedia

    INDEX
    Explanations

    the name "Serafini" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffix "af."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.62
    boats
    -0.62
    keyes
    -0.60
    mouth
    -0.59
    driver
    -0.58
     Hurricanes
    -0.57
     nipple
    -0.57
    itiveness
    -0.57
     riots
    -0.57
     roses
    -0.56
    POSITIVE LOGITS
    otal
    0.92
    inyl
    0.87
    ãĤ¨ãĥ«
    0.86
    aru
    0.85
    icz
    0.79
    ofer
    0.79
    isse
    0.79
    ahn
    0.78
    anche
    0.78
    ird
    0.78
    Act Density 0.232%

    No Known Activations