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

    Neuronpedia

    INDEX
    Explanations

    parentheses or references to them in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.18
    $
    -0.17
    &
    -0.17
    *
    -0.16
    ifu
    -0.15
     behalf
    -0.15
    ],
    -0.15
    atin
    -0.14
     Tradable
    -0.14
    %
    -0.14
    POSITIVE LOGITS
    Side
    0.21
    Note
    0.21
     Note
    0.21
    NB
    0.21
    Though
    0.20
    Inc
    0.20
     Side
    0.20
    Although
    0.19
    Iron
    0.19
    NOTE
    0.19
    Act Density 0.029%

    No Known Activations