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

    Neuronpedia

    INDEX
    Explanations

    references to concerns or issues regarding societal topics and discussions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    abre
    -0.57
     lini
    -0.57
    ણ
    -0.56
     original
    -0.56
     réussi
    -0.55
     full
    -0.54
     sede
    -0.54
    Original
    -0.54
     reçu
    -0.53
     placé
    -0.52
    POSITIVE LOGITS
     about
    1.22
     متعلقه
    1.16
     abt
    1.16
     matters
    1.13
     Tentang
    1.13
     Acerca
    1.13
    about
    1.09
     About
    1.07
     ABOUT
    1.07
    ABOUT
    1.05
    Act Density 1.884%

    No Known Activations