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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and research publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olut
    -0.16
    upon
    -0.16
    fall
    -0.15
    allen
    -0.15
     suff
    -0.15
     party
    -0.15
    ilk
    -0.15
    uš
    -0.14
     obviously
    -0.14
    err
    -0.14
    POSITIVE LOGITS
    ãĥĥãĥĦ
    0.17
    lite
    0.17
    onne
    0.16
    ettings
    0.16
    .crm
    0.16
    lama
    0.16
     Elm
    0.15
    clip
    0.15
    onas
    0.15
    /document
    0.14
    Act Density 0.020%

    No Known Activations