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

    Neuronpedia

    INDEX
    Explanations

    references to historical empires and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.86
    yrics
    -0.80
    paces
    -0.76
    electric
    -0.74
    onto
    -0.74
    etooth
    -0.72
    ociate
    -0.71
    eness
    -0.71
    matter
    -0.70
    CAST
    -0.69
    POSITIVE LOGITS
     Strikes
    0.96
     Claud
    0.92
    perors
    0.90
     Augustus
    0.86
     Nero
    0.84
     empire
    0.83
     empires
    0.79
    perial
    0.78
     Napoleon
    0.78
     Builder
    0.78
    Act Density 0.038%

    No Known Activations