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

    Neuronpedia

    INDEX
    Explanations

    articles related to research breakthroughs and news developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pport
    -0.64
     trunc
    -0.61
     constraints
    -0.61
    Decre
    -0.60
     roundup
    -0.60
    ocations
    -0.60
     progress
    -0.60
    process
    -0.59
    ysc
    -0.59
     format
    -0.58
    POSITIVE LOGITS
     Jr
    1.59
     Sr
    1.36
    Jr
    1.13
     PhD
    1.09
     aka
    1.06
     founder
    0.97
     who
    0.97
    who
    0.97
     QC
    0.96
     grandson
    0.94
    Act Density 1.715%

    No Known Activations