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

    Neuronpedia

    INDEX
    Explanations

    phrases related to surveillance and potentially violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    mentions of eavesdropping and fatal incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsky
    -0.85
    naires
    -0.77
    lli
    -0.75
    anan
    -0.70
     sights
    -0.70
    icals
    -0.64
     Gram
    -0.64
    yon
    -0.63
    ogether
    -0.63
    hift
    -0.62
    POSITIVE LOGITS
    cens
    0.80
    psc
    0.76
    odied
    0.75
    enegger
    0.75
     disarm
    0.73
    izophren
    0.73
    ufact
    0.71
     disband
    0.70
     indebted
    0.68
     prof
    0.68
    Act Density 0.018%

    No Known Activations