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

    Neuronpedia

    INDEX
    Explanations

    punctuations and formatting related to academic journal articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     counters
    -0.15
    -0.14
    564
    -0.14
    lando
    -0.14
    563
    -0.14
     Et
    -0.14
     bac
    -0.14
    ini
    -0.14
    Ï
    -0.13
    IJ
    -0.13
    POSITIVE LOGITS
    ignet
    0.17
    jos
    0.16
    intage
    0.16
     RedirectTo
    0.15
    _Lean
    0.14
    ODEV
    0.14
    alnız
    0.14
    ajas
    0.14
     sẵn
    0.14
    á»ĥn
    0.14
    Act Density 0.002%

    No Known Activations