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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing quality and comparisons, especially regarding excellence and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTERS
    -0.64
    ử
    -0.62
    HtmlAttribute
    -0.61
    CloseOperation
    -0.60
    __))
    -0.57
    COUVER
    -0.57
    ędzynarod
    -0.55
    hnte
    -0.55
    zygous
    -0.55
    sern
    -0.53
    POSITIVE LOGITS
     quality
    1.15
    quality
    1.09
    Quality
    0.99
     excellence
    0.97
     Quality
    0.96
     excellent
    0.95
     kval
    0.93
    excellent
    0.92
     good
    0.92
     QUALITY
    0.91
    Act Density 0.254%

    No Known Activations