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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific locations within a building or structure

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases indicating location or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.82
    amount
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    ÃŁ
    -0.71
    arella
    -0.70
    >(
    -0.70
    REF
    -0.68
    merga
    -0.68
     amount
    -0.66
    phabet
    -0.64
    POSITIVE LOGITS
     Ideal
    0.70
     Stamford
    0.70
     Parliament
    0.67
     unsuspecting
    0.67
     Genius
    0.67
     courthouse
    0.66
     Mt
    0.66
     Notre
    0.64
     Sty
    0.64
     Café
    0.64
    Act Density 0.191%

    No Known Activations