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

    Neuronpedia

    INDEX
    Explanations

    references to functional and practical aspects of products and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appar
    -0.17
    ross
    -0.17
    headline
    -0.15
    icle
    -0.15
     Network
    -0.15
     reasonable
    -0.15
    rosse
    -0.14
    maal
    -0.14
    prim
    -0.14
     bounding
    -0.14
    POSITIVE LOGITS
     komunik
    0.15
    éħ
    0.15
    alink
    0.14
    _tensors
    0.14
    AF
    0.14
    AMS
    0.14
     Triangle
    0.14
    ebek
    0.14
    undry
    0.13
    pes
    0.13
    Act Density 0.076%

    No Known Activations