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

    Neuronpedia

    INDEX
    Explanations

    formatting elements and structural components in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    {}/
    -0.51
     Or
    -0.50
    Or
    -0.49
    janja
    -0.46
     commerciali
    -0.46
     product
    -0.45
     you
    -0.45
     private
    -0.45
     =
    -0.45
     turn
    -0.44
    POSITIVE LOGITS
     الحره
    0.98
     Италијани
    0.95
    IsContent
    0.92
    OGND
    0.90
    StoryboardSegue
    0.86
     CURIAM
    0.86
    LookAnd
    0.84
    <bos>
    0.83
    bewerken
    0.81
    Personensuche
    0.80
    Act Density 0.104%

    No Known Activations