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

    Neuronpedia

    INDEX
    Explanations

    references to economic sectors, particularly illegal or prohibited activities within them

    oai_token-act-pair · gpt-3.5-turbo

    references to specific economic sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.64
    xes
    -0.61
    ":"","
    -0.60
     Maps
    -0.60
    grand
    -0.57
    con
    -0.56
    wolves
    -0.56
    ggles
    -0.55
    shows
    -0.55
    oat
    -0.55
    POSITIVE LOGITS
    sector
    1.41
     sector
    1.37
     sectors
    1.32
     Sector
    1.11
    enaries
    0.72
    lesi
    0.71
    unic
    0.70
    arse
    0.70
    coe
    0.70
     entreprene
    0.69
    Act Density 0.008%

    No Known Activations