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

    Neuronpedia

    INDEX
    Explanations

    references to specific news articles and their publication details

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     dedic
    -0.47
    ButterKnife
    -0.47
    oa̍t
    -0.45
    pointments
    -0.44
    abba
    -0.44
     richten
    -0.44
     dedicate
    -0.43
     dedicated
    -0.43
     yaklaş
    -0.43
     directed
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.77
    存于互联网档案馆
    0.71
     pinulongan
    0.71
    BoxShadow
    0.65
     EconPapers
    0.65
    abestanden
    0.63
    WireFormatLite
    0.60
    EDEFAULT
    0.59
    قایناقلار
    0.57
     cherchés
    0.56
    Act Density 0.510%

    No Known Activations