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

    Neuronpedia

    INDEX
    Explanations

    references to locations and events in a community setting

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     escaping
    -0.71
     flock
    -0.60
     landing
    -0.59
     creeping
    -0.59
     stagn
    -0.59
     joints
    -0.58
     infiltration
    -0.58
     undet
    -0.58
     elev
    -0.57
     offended
    -0.56
    POSITIVE LOGITS
    pictured
    1.11
    Reuters
    1.05
    ANI
    1.00
    CBC
    0.99
    Reporting
    0.93
    ABC
    0.93
    AFP
    0.91
    sic
    0.90
    READ
    0.88
    PHOTOS
    0.87
    Act Density 8.689%

    No Known Activations