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

    Neuronpedia

    INDEX
    Explanations

    references to "text" and related formatting or categorization in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    readcr
    -0.18
    ën
    -0.17
    thon
    -0.16
    ferences
    -0.16
    ok
    -0.16
    thern
    -0.15
    ugh
    -0.15
    deer
    -0.14
    ject
    -0.14
    hs
    -0.14
    POSITIVE LOGITS
    mia
    0.17
    ually
    0.17
    MeshPro
    0.16
    UPPORTED
    0.16
    sik
    0.16
    .RegularExpressions
    0.16
    imonial
    0.16
    -decoration
    0.16
    /plain
    0.15
    ãģªãĤĭ
    0.15
    Act Density 0.047%

    No Known Activations