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

    Neuronpedia

    INDEX
    Explanations

    references to illegal activities or items

    oai_token-act-pair · gpt-3.5-turbo

    terms and themes related to illegal activities and trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pread
    -0.85
    efully
    -0.77
    oleon
    -0.76
    ivities
    -0.74
    Ħ¢
    -0.73
    igating
    -0.73
    enger
    -0.73
    bourg
    -0.72
    ritis
    -0.71
    issance
    -0.70
    POSITIVE LOGITS
     trafficking
    0.96
     illegal
    0.90
     substances
    0.88
     immigrant
    0.88
     immigrants
    0.83
     aliens
    0.81
     alien
    0.80
     drugs
    0.80
    ities
    0.80
     downloading
    0.80
    Act Density 0.037%

    No Known Activations