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

    Neuronpedia

    INDEX
    Explanations

    references to licensing and usage terms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     noastre
    -0.83
     Efq
    -0.83
     deschis
    -0.69
     nostru
    -0.64
     InputDecoration
    -0.60
     Monfieur
    -0.59
     tfsi
    -0.59
     myſelf
    -0.58
     dignité
    -0.57
     zelve
    -0.56
    POSITIVE LOGITS
     mergeFrom
    0.67
    Hozzáférés
    0.56
    données
    0.55
    رفة
    0.53
     regime
    0.52
    ამ
    0.52
     فريبيس
    0.51
    UGHS
    0.51
    '])->
    0.50
    |$.
    0.50
    Act Density 0.003%

    No Known Activations