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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority and power control

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to control and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.72
    lehem
    -0.67
    vious
    -0.66
    onic
    -0.64
    Acknowled
    -0.64
     Statement
    -0.63
    mers
    -0.61
    ullah
    -0.61
     Friend
    -0.61
    reet
    -0.61
    POSITIVE LOGITS
     destiny
    1.27
     levers
    1.23
     reins
    1.04
     affairs
    1.00
     finances
    1.00
     airspace
    0.96
     purse
    0.94
     faculties
    0.78
    access
    0.75
     dest
    0.74
    Act Density 0.164%

    No Known Activations