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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "independent" or related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mers
    -0.96
    itual
    -0.96
    frey
    -0.82
    amac
    -0.77
     Nieto
    -0.75
    older
    -0.74
    days
    -0.74
    ttp
    -0.73
    risome
    -0.73
    mes
    -0.72
    POSITIVE LOGITS
     contractor
    1.16
     minded
    1.05
     contractors
    1.02
     thinker
    0.94
     counsel
    0.86
     judiciary
    0.84
     expenditure
    0.84
     verification
    0.80
     observer
    0.79
     thinkers
    0.77
    Act Density 0.021%

    No Known Activations