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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to technology companies and products

    oai_token-act-pair · gpt-3.5-turbo

    brands and influential figures in the film and technology industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAFT
    -0.77
    в
    -0.72
    ãģ¦
    -0.70
     Surgery
    -0.70
     Tayyip
    -0.70
     NETWORK
    -0.68
    л
    -0.67
    ãĤī
    -0.67
    sburgh
    -0.67
     Bakr
    -0.67
    POSITIVE LOGITS
     Lum
    1.14
    osity
    1.05
    inary
    0.99
    ifer
    0.84
    atts
    0.81
     Lumin
    0.79
    iven
    0.79
    cipled
    0.79
    istries
    0.78
     gobl
    0.78
    Act Density 0.014%

    No Known Activations