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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new section or idea in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bois
    -0.46
     seines
    -0.46
    arde
    -0.43
     compacto
    -0.42
    mente
    -0.42
    мир
    -0.41
     &(
    -0.40
    gnet
    -0.40
     totalt
    -0.40
     Unterhaltung
    -0.40
    POSITIVE LOGITS
    <bos>
    2.51
    DockStyle
    1.11
    uxxxx
    1.07
     Paglinawan
    1.04
     Савезне
    1.03
     Италијани
    0.98
    '
    0.94
    expandindo
    0.94
     estekak
    0.94
    ///</
    0.93
    Act Density 0.010%

    No Known Activations