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

    Neuronpedia

    INDEX
    Explanations

    references to specific city halls

    oai_token-act-pair · gpt-3.5-turbo

    references to government buildings or official locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -0.67
    CHAT
    -0.66
     Trend
    -0.64
    adapt
    -0.63
    Balt
    -0.62
     toget
    -0.60
    different
    -0.59
     gamers
    -0.59
    ãģĵ
    -0.58
     Called
    -0.57
    POSITIVE LOGITS
     entrance
    1.01
     Plaza
    0.95
    assies
    0.92
     entrances
    0.91
     inauguration
    0.88
     Museum
    0.88
     courtyard
    0.87
    eteria
    0.86
     plaza
    0.83
     gates
    0.82
    Act Density 0.136%

    No Known Activations