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

    Neuronpedia

    INDEX
    Explanations

    blocks of code handling exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.59
    .
    -0.49
     {
    -0.48
    …
    -0.44
    <eos>
    -0.44
     <
    -0.41
     cuales
    -0.40
    ↵↵
    -0.40
    )
    -0.40
    (
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    1.27
     يتيمه
    1.27
    RectangleBorder
    1.22
    VersionUID
    1.18
     utafitiHapana
    1.18
    ViewFeatures
    1.18
    GraphicsUnit
    1.16
     متعلقه
    1.13
    BeginContext
    1.12
    ValueStyle
    1.12
    Act Density 0.059%

    No Known Activations