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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or rankings related to events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1
    -0.17
    2
    -0.15
     ("\
    -0.15
    è¾¾
    -0.15
     (*)
    -0.14
     ^{[
    -0.14
     âĢł
    -0.14
     (),
    -0.14
     (\
    -0.14
     ï¼Ī
    -0.14
    POSITIVE LOGITS
    th
    0.47
     th
    0.38
    thin
    0.33
    TH
    0.31
    Th
    0.31
    't
    0.30
    ht
    0.30
    nth
    0.30
    thed
    0.30
    _th
    0.29
    Act Density 0.059%

    No Known Activations