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

    Neuronpedia

    INDEX
    Explanations

    mentions of government or law enforcement entities

    oai_token-act-pair · gpt-3.5-turbo

    references to authorities or governing bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thal
    -0.74
     Sleeping
    -0.71
    ces
    -0.68
     Generations
    -0.66
    rities
    -0.65
     Spect
    -0.62
    esta
    -0.62
    antam
    -0.62
     Leaf
    -0.62
    olan
    -0.62
    POSITIVE LOGITS
     authorities
    1.01
     agencies
    1.00
     officials
    0.89
     investigating
    0.85
     Authorities
    0.85
     overseeing
    0.81
     tasked
    0.81
     decree
    0.80
     crackdown
    0.79
     confir
    0.78
    Act Density 0.030%

    No Known Activations