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

    Neuronpedia

    INDEX
    Explanations

    organization and person names in a news article

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fetus
    -0.77
     uter
    -0.76
     GOODMAN
    -0.75
    Fax
    -0.74
     protester
    -0.70
     pierced
    -0.70
     ov
    -0.69
     Shutterstock
    -0.68
    bits
    -0.68
    amazon
    -0.68
    POSITIVE LOGITS
     coaching
    1.51
     coached
    1.41
     coaches
    1.20
     coach
    1.15
    Coach
    1.09
     rebuilding
    1.06
     Coach
    1.06
     sacked
    1.05
     appointing
    1.03
     hiring
    1.03
    Act Density 0.477%

    No Known Activations