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

    Neuronpedia

    INDEX
    Explanations

    URLs and reference identifiers for academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antt
    -0.17
    urette
    -0.15
    bers
    -0.14
     Perez
    -0.14
    ÛĮرÙĩ
    -0.14
    antee
    -0.14
    velle
    -0.13
    anki
    -0.13
    aversal
    -0.13
    VOID
    -0.13
    POSITIVE LOGITS
    зÑĭ
    0.19
    OLA
    0.15
    term
    0.14
    NewItem
    0.14
    dge
    0.14
    swire
    0.14
    Ïĥο
    0.14
    istring
    0.14
    åłĤ
    0.14
    ambil
    0.13
    Act Density 0.011%

    No Known Activations