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

    Neuronpedia

    INDEX
    Explanations

    terms related to independence, audits, and non-government-affiliated investigations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    mers
    -1.01
    itual
    -0.94
    risome
    -0.90
     Nieto
    -0.86
    amac
    -0.84
    frey
    -0.83
    days
    -0.83
    older
    -0.80
    cific
    -0.78
    ttp
    -0.78
    POSITIVE LOGITS
     contractor
    1.15
     minded
    1.09
     contractors
    1.02
     judiciary
    0.84
     thinker
    0.82
     independent
    0.81
     verification
    0.81
     counsel
    0.80
     corrobor
    0.80
    lect
    0.79
    Act Density 7.291%

    No Known Activations