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

    Neuronpedia

    INDEX
    Explanations

    references to illegal activities and individuals involved in them, particularly related to prostitution

    oai_token-act-pair · gpt-3.5-turbo

    references to prostitution and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REE
    -0.77
    pine
    -0.72
    reens
    -0.69
    AIR
    -0.68
    Bio
    -0.68
    arios
    -0.67
    eq
    -0.66
     Fir
    -0.65
    ucket
    -0.65
    thur
    -0.64
    POSITIVE LOGITS
     prostitutes
    1.06
     prostitute
    1.01
     prostitution
    0.96
     trafficking
    0.87
     Traff
    0.83
     racket
    0.82
     bribery
    0.75
    iasis
    0.74
     extortion
    0.74
     laundering
    0.70
    Act Density 0.029%

    No Known Activations