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

    Neuronpedia

    INDEX
    Explanations

    addresses or locations expressed in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    place names and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.76
     doub
    -0.62
     caution
    -0.57
     Leilan
    -0.56
    adobe
    -0.56
    proof
    -0.56
    brush
    -0.56
    WIND
    -0.55
     accounting
    -0.55
    fold
    -0.54
    POSITIVE LOGITS
    .,
    1.99
    .;
    1.57
    .:
    1.52
    .?
    1.51
    .,"
    1.46
    ./
    1.40
    .),
    1.32
    .—
    1.21
    .):
    1.16
    .-
    1.14
    Act Density 0.217%

    No Known Activations