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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific names like "Crawley" and "Lamb"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.67
     concess
    -0.66
     shutter
    -0.66
    ÅĤ
    -0.65
    cca
    -0.64
    WAYS
    -0.62
     gir
    -0.61
     entering
    -0.60
     Mehran
    -0.60
     selection
    -0.60
    POSITIVE LOGITS
    herent
    0.97
    dad
    0.97
    bart
    0.95
    emouth
    0.92
    cook
    0.89
    grave
    0.88
    dry
    0.86
    Beat
    0.85
    butt
    0.84
    shaw
    0.81
    Act Density 0.025%

    No Known Activations