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

    Neuronpedia

    INDEX
    Explanations

    references to a specific place or organization, Fort Detrick

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Detroit."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.87
    nown
    -0.77
    hetti
    -0.75
    manship
    -0.73
    ammy
    -0.70
    drive
    -0.70
    toggle
    -0.67
    inventoryQuantity
    -0.67
     actionGroup
    -0.67
    perm
    -0.66
    POSITIVE LOGITS
    ector
    1.21
    ective
    1.18
    ected
    1.14
    ention
    1.06
    ection
    1.03
    rans
    0.99
    ail
    0.98
    roit
    0.97
    ailed
    0.96
    ainer
    0.96
    Act Density 0.018%

    No Known Activations