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

    Neuronpedia

    INDEX
    Explanations

    references to surveys and related methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.45
    bootstrapcdn
    -0.43
    FUL
    -0.42
    middels
    -0.40
     Provinz
    -0.38
    的東西
    -0.38
    ful
    -0.38
    toInt
    -0.37
    æde
    -0.37
    DotNetBar
    -0.37
    POSITIVE LOGITS
    parsedMessage
    0.52
     conducted
    0.52
    الحياه
    0.51
     Conducted
    0.48
    awtextra
    0.47
     Cursed
    0.46
    Jeografia
    0.45
    Hentet
    0.45
    SequentialGroup
    0.45
    SharedDtor
    0.45
    Act Density 0.316%

    No Known Activations