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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating origin or source

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     from
    -0.76
     From
    -0.66
    CompleteListener
    -0.66
     FROM
    -0.66
     来自
    -0.65
    bidden
    -0.64
     Meksiku
    -0.63
    жели
    -0.63
     helt
    -0.63
    getFrom
    -0.59
    POSITIVE LOGITS
    存于互联网档案馆
    0.73
     للاسماء
    0.68
     geslacht
    0.61
     Rasp
    0.51
     eſ
    0.51
     martens
    0.51
     quæ
    0.50
     Boles
    0.50
     alps
    0.50
     Garuda
    0.50
    Act Density 0.034%

    No Known Activations