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

    Neuronpedia

    INDEX
    Explanations

    news headlines with a call to action to read more

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Read more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascal
    -0.77
    xon
    -0.77
    اÙĦ
    -0.68
    pload
    -0.66
    -"
    -0.65
    ugal
    -0.65
    alm
    -0.64
    unity
    -0.62
    VC
    -0.61
    IDS
    -0.61
    POSITIVE LOGITS
     aloud
    1.11
     Read
    0.99
    Write
    0.97
    ahead
    0.82
    Read
    0.81
     Reading
    0.79
    just
    0.79
    sworth
    0.78
    iness
    0.77
    gon
    0.77
    Act Density 0.017%

    No Known Activations