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

    Neuronpedia

    INDEX
    Explanations

    instances where some kind of formal permission or approval is granted to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with giving permission or official approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tes
    -0.77
    psc
    -0.71
    enegger
    -0.70
     Sins
    -0.69
    ateg
    -0.66
    ategy
    -0.66
    sis
    -0.66
    ron
    -0.66
     Hungry
    -0.65
    ashington
    -0.64
    POSITIVE LOGITS
     amnesty
    1.04
     granted
    0.88
     immunity
    0.87
     acceptance
    0.75
    ees
    0.75
     renewal
    0.74
    uthor
    0.74
     grant
    0.74
     Pwr
    0.74
     aid
    0.73
    Act Density 0.034%

    No Known Activations