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

    Neuronpedia

    INDEX
    Explanations

    person names in the format Firstname<tab>Lastname

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (?,
    -0.55
    ãĢİ
    -0.53
     Reincarn
    -0.50
    cerning
    -0.49
    âĵĺ
    -0.49
     deciding
    -0.48
    FTWARE
    -0.47
     stubborn
    -0.47
     unexpectedly
    -0.47
     boosters
    -0.46
    POSITIVE LOGITS
    utterstock
    0.88
    photos
    0.87
    ulton
    0.84
    reenshot
    0.77
    )/
    0.75
     /
    0.72
     Photography
    0.71
     Shutterstock
    0.71
    /)
    0.68
     IMAGES
    0.68
    Act Density 0.151%

    No Known Activations