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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.72
    SPONSORED
    -0.72
    Reply
    -0.68
    sci
    -0.65
    اÙĦ
    -0.62
    ecycle
    -0.61
    ufact
    -0.60
    ancock
    -0.60
    artney
    -0.59
     agre
    -0.59
    POSITIVE LOGITS
     huh
    1.13
     awaits
    1.06
     equals
    0.99
     notwithstanding
    0.95
     ensued
    0.92
     eh
    0.92
     looms
    0.91
    ?!
    0.90
     aside
    0.90
     ain
    0.87
    Act Density 3.597%

    No Known Activations