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

    Neuronpedia

    INDEX
    Explanations

    words related to names and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BibitemShut
    -0.97
     Theſe
    -0.93
     ―――――
    -0.92
     iſt
    -0.92
    ſelves
    -0.91
     Beſ
    -0.89
     Anſ
    -0.88
     myſelf
    -0.87
     ſeveral
    -0.86
     leaſt
    -0.85
    POSITIVE LOGITS
     nationaux
    0.86
     kasarigan
    0.86
    Przypisy
    0.85
     AssemblyCulture
    0.85
    !*\
    0.79
     sebenar
    0.76
    DoS
    0.74
    E
    0.73
     Erl
    0.73
    ьаж
    0.73
    Act Density 0.569%

    No Known Activations