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

    Neuronpedia

    INDEX
    Explanations

    concepts related to performance metrics and evaluation criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OND
    -0.15
     Hlav
    -0.14
     Sug
    -0.14
    ô
    -0.14
    prit
    -0.14
    Ìĥ
    -0.13
    ney
    -0.13
     ‘
    -0.13
    tones
    -0.13
     buck
    -0.13
    POSITIVE LOGITS
     referred
    0.19
     subsection
    0.18
     prescribed
    0.16
     Her
    0.15
     Crown
    0.15
     subparagraph
    0.14
     GOODS
    0.14
    íĥģ
    0.14
    jets
    0.14
    롱
    0.14
    Act Density 0.001%

    No Known Activations