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

    Neuronpedia

    INDEX
    Explanations

    technical details related to programming and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.90
     nahilalakip
    -0.86
     مشارکت‌کنندگان
    -0.82
    )";
    -0.78
    లాలు
    -0.77
     Shakspeare
    -0.76
     Conſ
    -0.74
     Diſ
    -0.74
     Perſ
    -0.74
     Anſ
    -0.73
    POSITIVE LOGITS
    ´
    0.73
    Nr
    0.65
     «
    0.62
     (...)
    0.60
     underlines
    0.59
     „
    0.59
     underline
    0.58
    igth
    0.58
     adresses
    0.57
     ressources
    0.57
    Act Density 2.104%

    No Known Activations