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

    Neuronpedia

    INDEX
    Explanations

    the word "this" followed by additional content

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or concepts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.84
    alties
    -0.83
    aneers
    -0.83
    acers
    -0.83
    Methods
    -0.82
    tones
    -0.82
    ends
    -0.81
    ãĥĺ
    -0.80
    Products
    -0.79
    masters
    -0.78
    POSITIVE LOGITS
     nifty
    1.12
     lovely
    1.02
     adorable
    1.01
     amazing
    1.00
     delightful
    0.97
     handy
    0.95
     week
    0.95
     gorgeous
    0.95
     awesome
    0.94
     incredible
    0.94
    Act Density 0.159%

    No Known Activations