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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes and experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal perspectives or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogens
    -0.78
    anism
    -0.64
    btn
    -0.63
     trem
    -0.63
     harming
    -0.62
     Haram
    -0.61
     ç¥ŀ
    -0.61
     Kare
    -0.61
     Narendra
    -0.61
     destiny
    -0.59
    POSITIVE LOGITS
     anecd
    1.15
     confir
    1.05
     sources
    1.01
     obser
    0.97
     recollection
    0.94
    reports
    0.93
     glean
    0.84
     consulted
    0.83
     sugg
    0.83
     experien
    0.83
    Act Density 0.154%

    No Known Activations