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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and prominent places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Norn
    -0.79
     Presence
    -0.71
     Sale
    -0.64
     Mush
    -0.63
     Sacrifice
    -0.62
    »Ĵ
    -0.61
    omination
    -0.60
    osis
    -0.59
    rifice
    -0.59
     Assignment
    -0.58
    POSITIVE LOGITS
    iest
    1.03
     favourites
    0.95
     favorites
    0.91
    liest
    0.80
    's
    0.78
    dest
    0.77
    ÃŃs
    0.75
    lez
    0.72
     incarn
    0.72
    esters
    0.71
    Act Density 0.237%

    No Known Activations