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

    Neuronpedia

    INDEX
    Explanations

    sequences of alphanumeric characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and letters that may represent device identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.90
    Ü
    -0.82
     mathemat
    -0.66
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.64
     urgently
    -0.63
     tractor
    -0.62
    itialized
    -0.62
     bisc
    -0.62
     weekday
    -0.62
     billionaires
    -0.61
    POSITIVE LOGITS
    fy
    0.87
     attRot
    0.85
    )))
    0.73
    }\
    0.71
    phrine
    0.70
    etc
    0.70
     etc
    0.68
    \">
    0.68
    eson
    0.66
    dd
    0.66
    Act Density 0.053%

    No Known Activations