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

    Neuronpedia

    INDEX
    Explanations

    references to specific structures and components within texts, particularly focusing on lines, passages, and chapters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fab
    -0.15
    .instances
    -0.15
    567
    -0.14
    707
    -0.14
    uw
    -0.14
    èī²
    -0.13
    ì¶Ķì²ľ
    -0.13
    crast
    -0.13
    abb
    -0.13
    557
    -0.13
    POSITIVE LOGITS
    olet
    0.18
    omi
    0.16
    zv
    0.15
    agh
    0.15
    rema
    0.15
    _requires
    0.15
    ÙĦÙħاÙĨ
    0.15
    -long
    0.14
    riage
    0.14
     of
    0.14
    Act Density 0.192%

    No Known Activations