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

    Neuronpedia

    INDEX
    Explanations

    length measurements in meters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurement and dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.78
     Ragnarok
    -0.75
    apego
    -0.71
    Pir
    -0.71
     Metatron
    -0.68
     Religion
    -0.66
     Pirates
    -0.64
    udeb
    -0.64
    theme
    -0.63
     Wein
    -0.63
    POSITIVE LOGITS
     increments
    0.99
     apiece
    0.91
     diameter
    0.85
    ught
    0.80
     squared
    0.75
     onwards
    0.74
    illion
    0.73
     GDDR
    0.70
    plus
    0.69
    dn
    0.69
    Act Density 0.066%

    No Known Activations