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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conspiracy theories and illegal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to conspiracy-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TPS
    -0.74
     Abyss
    -0.73
    âĵĺ
    -0.71
     Millennium
    -0.69
     Welsh
    -0.69
    asma
    -0.68
    profits
    -0.67
    Scope
    -0.66
    neath
    -0.64
    profit
    -0.63
    POSITIVE LOGITS
    oled
    0.98
    orting
    0.94
    pired
    0.90
    oling
    0.89
    ented
    0.85
    igned
    0.85
    edi
    0.81
    orted
    0.80
    orts
    0.80
    eering
    0.79
    Act Density 0.051%

    No Known Activations