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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.81
    featureID
    -0.72
     transfieras
    -0.69
    EndProject
    -0.69
    complexContent
    -0.69
     esternos
    -0.66
    GrantedAuthority
    -0.63
    Personendaten
    -0.61
     дописавши
    -0.60
    SharedDtor
    -0.60
    POSITIVE LOGITS
     subsequent
    0.54
     nên
    0.51
    iteurs
    0.48
     original
    0.47
    Original
    0.46
    Alas
    0.46
    后来
    0.46
    CurrentPage
    0.46
    ataires
    0.46
    original
    0.45
    Act Density 0.364%

    No Known Activations