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

    Neuronpedia

    INDEX
    Explanations

    names of individuals often in a list format

    oai_token-act-pair · gpt-3.5-turbo

    proper names of individuals, particularly those in the entertainment industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.62
    Reviewer
    -0.58
    above
    -0.57
    BOOK
    -0.56
     Responsibility
    -0.56
     ascend
    -0.54
    =>
    -0.54
    TIME
    -0.53
    Priv
    -0.53
    Tokens
    -0.52
    POSITIVE LOGITS
     Cummings
    0.87
     Hayes
    0.85
     Amos
    0.82
     McK
    0.81
     Mann
    0.80
     Wagner
    0.80
     Rebell
    0.79
     Marino
    0.77
     Hann
    0.77
     Yar
    0.77
    Act Density 0.256%

    No Known Activations