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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something that stands out or is distinguished from something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to uniqueness and distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.77
    pmwiki
    -0.65
    upon
    -0.62
     retweet
    -0.62
    aucuses
    -0.60
     hashing
    -0.57
    )--
    -0.56
     chants
    -0.56
    à¼
    -0.55
    utterstock
    -0.54
    POSITIVE LOGITS
     Albion
    0.69
     Mik
    0.69
     Henderson
    0.68
     Nelson
    0.68
     Greene
    0.67
     Barton
    0.67
     Garrett
    0.65
     Kem
    0.65
     Hawkins
    0.65
     Van
    0.65
    Act Density 1.301%

    No Known Activations