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

    Neuronpedia

    INDEX
    Explanations

    various forms of statistical analysis and comparative measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    897
    -0.16
     पà¤ķ
    -0.15
    allon
    -0.14
    andas
    -0.14
    ik
    -0.13
    266
    -0.13
     Merk
    -0.13
     Bits
    -0.13
    uffle
    -0.13
     Mentor
    -0.13
    POSITIVE LOGITS
    forc
    0.15
    RESS
    0.15
    æĨ
    0.15
    territ
    0.15
    DMI
    0.15
     forc
    0.15
    Wunused
    0.14
    IFI
    0.14
     springfox
    0.14
    -Token
    0.14
    Act Density 0.111%

    No Known Activations