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

    Neuronpedia

    INDEX
    Explanations

    instances of beginning or introductory phrases in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.10
    LookAnd
    -1.00
     EClass
    -0.94
    expandindo
    -0.92
    BufferException
    -0.90
     ويكيميديا
    -0.87
     beginnetje
    -0.87
     betweenstory
    -0.86
     unknownFields
    -0.85
    parsedMessage
    -0.85
    POSITIVE LOGITS
    http
    0.89
    {
    0.83
     cref
    0.79
    https
    0.77
    mailto
    0.75
    www
    0.72
    href
    0.72
     http
    0.68
     debout
    0.65
     https
    0.64
    Act Density 0.016%

    No Known Activations