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

    Neuronpedia

    INDEX
    Explanations

    references to nationalities or countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     watered
    -0.73
     slept
    -0.72
     Marketable
    -0.70
    dayName
    -0.68
     clipped
    -0.66
    EStreamFrame
    -0.65
     existed
    -0.64
     unheard
    -0.64
     handled
    -0.63
     didnt
    -0.63
    POSITIVE LOGITS
     authorities
    1.04
     officials
    1.00
     prosecutors
    0.97
     investigators
    0.97
     lawmakers
    0.92
     legislators
    0.89
     Attorney
    0.88
     Deputy
    0.86
     politicians
    0.85
     scientists
    0.84
    Act Density 0.142%

    No Known Activations