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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets or configuration settings

    oai_token-act-pair · gpt-3.5-turbo

    syntax or formatting related to programming or database entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -1.27
     oun
    -1.14
     pione
    -1.10
    oreAnd
    -1.01
    DeliveryDate
    -1.01
    ą
    -0.99
    À
    -0.99
    ě
    -0.99
    đ
    -0.99
    ö
    -0.99
    POSITIVE LOGITS
    both
    0.95
    img
    0.94
    src
    0.90
    embed
    0.88
    //
    0.88
    }{
    0.87
    input
    0.86
    submit
    0.86
    attribute
    0.86
    {{
    0.85
    Act Density 0.094%

    No Known Activations