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

    Neuronpedia

    INDEX
    Explanations

    references to classification, identification, or the status of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    Ini
    -0.15
    amm
    -0.15
    .SDK
    -0.14
    acht
    -0.14
     männer
    -0.14
    .xhtml
    -0.14
     Dün
    -0.14
    czy
    -0.14
    FixedSize
    -0.13
    POSITIVE LOGITS
     Medium
    0.31
     medium
    0.31
    Medium
    0.30
    medium
    0.29
     Category
    0.28
     moderate
    0.27
     category
    0.27
     Moderate
    0.26
     Moder
    0.25
     borderline
    0.25
    Act Density 0.200%

    No Known Activations