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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their significance in a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ↘
    -0.71
    writerow
    -0.59
    akterysty
    -0.57
    NOPQRST
    -0.56
    ContentLoaded
    -0.53
    croll
    -0.52
    WriteTagHelper
    -0.52
    Lives
    -0.51
    korb
    -0.51
     JSTOR
    -0.51
    POSITIVE LOGITS
     TextAppearance
    0.55
     financières
    0.53
     relâche
    0.51
    horabuena
    0.51
    aneous
    0.47
     professionnelle
    0.45
     MaterialApp
    0.45
    Nbr
    0.45
    </caption>
    0.45
     suivants
    0.44
    Act Density 0.001%

    No Known Activations