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

    Neuronpedia

    INDEX
    Explanations

    country names and related entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcs
    -0.76
    ufact
    -0.75
    afety
    -0.71
    rss
    -0.70
    osaurus
    -0.70
    elist
    -0.70
    xon
    -0.69
    zsche
    -0.68
    oslav
    -0.68
    gow
    -0.67
    POSITIVE LOGITS
     riches
    0.68
     fortune
    0.59
    ãĥ¼ãĥĨ
    0.55
    iggs
    0.51
     Maxwell
    0.51
     fortunes
    0.50
     Divine
    0.50
     Fortune
    0.49
    ÃĤ
    0.48
    ±
    0.48
    Act Density 2.179%

    No Known Activations