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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Metropolis."

    oai_token-act-pair · gpt-3.5-turbo

    references to 'Met', likely signifying a specific location or establishment frequently mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.92
    ãģį
    -0.87
    é»Ĵ
    -0.79
     cone
    -0.69
     margins
    -0.69
     Parables
    -0.66
     Borderlands
    -0.66
     Republic
    -0.62
     nomine
    -0.62
     differentiation
    -0.62
    POSITIVE LOGITS
    ropolis
    1.28
    amorph
    1.21
    rics
    1.17
    ropolitan
    1.16
    adata
    1.16
    abol
    1.09
    eor
    1.04
    allic
    1.02
    rod
    1.00
    rix
    0.98
    Act Density 0.015%

    No Known Activations