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

    Neuronpedia

    INDEX
    Explanations

    numbers related to human casualties or population movements

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to casualties and displacements in conflict situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.75
    hetics
    -0.73
     srfAttach
    -0.72
    quickShipAvailable
    -0.70
     superiors
    -0.70
     Excellence
    -0.66
    OLOG
    -0.64
     manag
    -0.64
     nicely
    -0.63
    ãĤ¦ãĤ¹
    -0.63
    POSITIVE LOGITS
     perished
    1.35
     died
    1.06
     starve
    1.05
     die
    1.01
     perish
    1.00
     starved
    0.96
     illegally
    0.95
     suffer
    0.95
     murdered
    0.92
     enrolled
    0.90
    Act Density 0.331%

    No Known Activations