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

    Neuronpedia

    INDEX
    Explanations

    words related to law enforcement, investigations, and judicial processes

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Regist
    -0.67
    è¦ļéĨĴ
    -0.66
    ACP
    -0.65
     Belgian
    -0.64
     Gaw
    -0.64
     Buff
    -0.62
     ATK
    -0.61
     rgb
    -0.60
     Alban
    -0.59
    ashtra
    -0.59
    POSITIVE LOGITS
    itivity
    1.06
    uries
    1.02
    itely
    1.00
    ptions
    1.00
    ciation
    0.90
    itiveness
    0.86
    itors
    0.86
    itive
    0.85
    ystem
    0.85
    cence
    0.83
    Act Density 0.093%

    No Known Activations