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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to source attribution or referencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŃĭ
    -0.18
    ãĥ³ãĥĢ
    -0.16
    _abstract
    -0.14
    uras
    -0.14
    QualifiedName
    -0.13
     dyn
    -0.13
    BSD
    -0.13
    .mix
    -0.13
    é§IJ
    -0.13
    orne
    -0.13
    POSITIVE LOGITS
    ToPoint
    0.15
     mes
    0.15
    elm
    0.15
    ãĤ¿ãĥ³
    0.15
     Fence
    0.15
    ÄĻd
    0.15
    ENCE
    0.14
    æĹıèĩªæ²»
    0.14
    tlement
    0.14
    ìŀ¬
    0.14
    Act Density 0.003%

    No Known Activations