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

    Neuronpedia

    INDEX
    Explanations

    content that involves complex numeric or scientific data and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '
    -0.26
     --
    -0.22
     '[
    -0.21
    --
    -0.19
     ...
    -0.18
    ...'
    -0.18
     ('
    -0.18
    -'
    -0.18
    ---
    -0.18
     '--
    -0.17
    POSITIVE LOGITS
     dinosaur
    0.22
     pal
    0.19
    din
    0.19
     “
    0.18
     fossil
    0.17
     dinosaurs
    0.17
     Pal
    0.17
     fossils
    0.17
    Perm
    0.16
     scientific
    0.15
    Act Density 0.002%

    No Known Activations