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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of a repeated action or event happening again

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "reboot" or related forms indicating re-establishment or recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.96
    âĢ¢âĢ¢
    -0.85
     Dome
    -0.68
    íķ
    -0.66
     Faculty
    -0.65
     Corpus
    -0.64
    66666666
    -0.63
    anto
    -0.62
     Supplementary
    -0.62
    ãģ®ç
    -0.62
    POSITIVE LOGITS
     reb
    1.22
    anche
    0.98
    ounding
    0.91
    uffed
    0.88
    interstitial
    0.88
     challeng
    0.87
    uked
    0.87
     barg
    0.81
    uls
    0.80
     tremend
    0.78
    Act Density 0.005%

    No Known Activations