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

    Neuronpedia

    INDEX
    Explanations

    specific locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    geopolitical references related to countries and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tones
    -0.78
    vous
    -0.76
    soDeliveryDate
    -0.75
    pring
    -0.70
    ãģĻ
    -0.68
    ãģĨ
    -0.68
     RTX
    -0.65
     cryptic
    -0.65
     Emin
    -0.65
    Reilly
    -0.64
    POSITIVE LOGITS
     spends
    1.32
     lacks
    1.31
     suffers
    1.26
     possesses
    1.20
     relies
    1.13
     owes
    1.11
     boasts
    1.10
     produces
    1.09
     excel
    1.07
     has
    1.07
    Act Density 0.249%

    No Known Activations