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

    Neuronpedia

    INDEX
    Explanations

    terms related to the evaluation of test reliability and performance metrics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    öglich
    -0.49
    臆
    -0.46
     интересно
    -0.45
    zzino
    -0.45
    hyp
    -0.44
    Moj
    -0.44
    有意思
    -0.43
     cycle
    -0.41
     parted
    -0.41
     wiser
    -0.41
    POSITIVE LOGITS
     Ensuring
    0.74
    afety
    0.71
    QUALITY
    0.71
     quality
    0.70
     safety
    0.69
     للاسماء
    0.69
    quality
    0.68
     ensuring
    0.68
     QUALITY
    0.68
    Quality
    0.66
    Act Density 0.363%

    No Known Activations