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

    Neuronpedia

    INDEX
    Explanations

    phrases related to illegal activities, specifically trafficking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human and illegal trafficking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thus
    -0.71
    eely
    -0.69
    ¯¯
    -0.69
     Fitness
    -0.68
    semble
    -0.67
    ++++++++++++++++
    -0.66
     Metatron
    -0.66
     Pyr
    -0.66
     Einstein
    -0.65
    tes
    -0.65
    POSITIVE LOGITS
     trafficking
    1.49
     Traff
    1.15
     traffickers
    0.99
     traff
    0.94
     proble
    0.84
    wana
    0.82
     offenders
    0.82
     offenses
    0.82
     exploited
    0.80
     smuggling
    0.79
    Act Density 0.009%

    No Known Activations