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

    Neuronpedia

    INDEX
    Explanations

    references to the term "word" and its definitions or mentions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.51
     alugar
    -0.51
     florales
    -0.48
     affich
    -0.46
     pitié
    -0.45
     reír
    -0.45
     tiet
    -0.45
     femininas
    -0.45
     reconoci
    -0.44
     innehå
    -0.44
    POSITIVE LOGITS
     ‘
    1.01
     '
    0.94
     “
    0.87
     "
    0.83
    ==="
    0.73
     ‘’
    0.72
    loroethane
    0.71
     словом
    0.71
    |}{$
    0.71
    WireFormatLite
    0.69
    Act Density 0.284%

    No Known Activations