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

    Neuronpedia

    INDEX
    Explanations

    references to contributions or acknowledgments in academic or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOCTYPE
    -0.61
     kteří
    -0.56
     Rosalie
    -0.56
    abestanden
    -0.56
     iNdEx
    -0.55
    ScopeManager
    -0.55
    taciones
    -0.53
    ingway
    -0.53
    ientôt
    -0.53
     חיצוניים
    -0.52
    POSITIVE LOGITS
     by
    0.81
     Dr
    0.76
     author
    0.76
     автор
    0.72
     oleh
    0.71
    Author
    0.70
    by
    0.69
    Dr
    0.69
     kasarigan
    0.67
     Author
    0.67
    Act Density 0.436%

    No Known Activations