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

    Neuronpedia

    INDEX
    Explanations

    phrases related to photo credits or image sources

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     conduc
    -0.72
     recite
    -0.66
     revolves
    -0.64
    priority
    -0.64
     downfall
    -0.63
     defences
    -0.63
     conson
    -0.63
     apart
    -0.62
    igue
    -0.62
     tending
    -0.62
    POSITIVE LOGITS
     Shutterstock
    0.83
     Wikimedia
    0.82
     Freed
    0.77
     Applied
    0.74
     Wizards
    0.74
     Photographer
    0.74
     STATS
    0.74
     Geo
    0.72
     Photography
    0.72
     Photos
    0.69
    Act Density 0.027%

    No Known Activations