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

    Neuronpedia

    INDEX
    Explanations

    occurrences of a specific character or symbol sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '[
    -0.22
     [--
    -0.17
     [&
    -0.16
     '!
    -0.16
     '--
    -0.15
     signalling
    -0.15
     '-
    -0.14
    oreach
    -0.14
    istrovstvÃŃ
    -0.14
     '(
    -0.14
    POSITIVE LOGITS
     “
    0.19
     States
    0.17
    4
    0.15
     extension
    0.15
     https
    0.15
    https
    0.15
    crast
    0.14
     kinds
    0.14
    =>
    0.14
     (“
    0.14
    Act Density 0.004%

    No Known Activations