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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing high praise or strong recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     africain
    -0.73
     sauvages
    -0.70
     aveug
    -0.66
     Hauser
    -0.66
     abandonné
    -0.65
     étr
    -0.64
     exemplaire
    -0.64
     Hager
    -0.64
     étranger
    -0.64
     sauvage
    -0.63
    POSITIVE LOGITS
    HtmlAttribute
    0.76
     مرئيه
    0.67
    Obrázky
    0.63
    })*/
    0.63
     للمعارف
    0.61
     dataSnapshot
    0.61
    SourceChecksum
    0.61
    AutoScale
    0.60
    ]++;
    0.59
    >",
    0.59
    Act Density 0.109%

    No Known Activations