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

    Neuronpedia

    INDEX
    Explanations

    sentences with a mixture of conjunctions, pronouns, and punctuation indicating conversation structure or narrative flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĮÏĦη
    -0.17
    ahir
    -0.17
     totiž
    -0.16
    ignon
    -0.15
    nam
    -0.14
    æģIJ
    -0.14
    raf
    -0.14
    ome
    -0.14
     protagonists
    -0.14
    unn
    -0.14
    POSITIVE LOGITS
     thus
    0.23
     each
    0.22
     then
    0.21
    è¿Ļæł·
    0.20
    each
    0.19
    Each
    0.19
     thereby
    0.19
    iken
    0.19
     Each
    0.18
     Таким
    0.17
    Act Density 0.274%

    No Known Activations