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

    Neuronpedia

    INDEX
    Explanations

    names, particularly those of people and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drawSprites
    -0.99
    Vidite
    -0.97
     Shira
    -0.91
    <%=
    -0.89
     Siena
    -0.89
     Lufthansa
    -0.88
     Sparta
    -0.87
     Nae
    -0.87
     Kanna
    -0.86
    SequentialGroup
    -0.85
    POSITIVE LOGITS
     Oliver
    0.72
     Corm
    0.68
     Daw
    0.67
     lleg
    0.67
    Ori
    0.63
    Oliver
    0.63
    i
    0.60
     Windsor
    0.60
    oplayer
    0.60
     Tür
    0.60
    Act Density 0.051%

    No Known Activations