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

    Neuronpedia

    INDEX
    Explanations

    phrases related to occupation, job roles, and specific expertise

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.76
     yourselves
    -0.64
     ourselves
    -0.64
    olulu
    -0.60
     Helpful
    -0.59
     Ga
    -0.58
    nice
    -0.57
    hin
    -0.56
    common
    -0.56
    ÃŁ
    -0.55
    POSITIVE LOGITS
     consisted
    1.11
     consists
    1.05
     extends
    1.01
     differs
    0.99
     revolves
    0.94
     encompasses
    0.93
     depends
    0.93
     is
    0.90
     spans
    0.90
     depended
    0.90
    Act Density 0.538%

    No Known Activations