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

    Neuronpedia

    INDEX
    Explanations

    academic references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.18
     Jefus
    -1.16
     Beſ
    -1.15
     houſe
    -1.14
     Efq
    -1.11
     myſelf
    -1.10
     Monfieur
    -1.08
     Eſ
    -1.08
     themſelves
    -1.07
     reaſon
    -1.03
    POSITIVE LOGITS
     Normdatei
    0.79
    fikasi
    0.65
    thansa
    0.62
     von
    0.62
     Haas
    0.59
     Von
    0.59
    valdi
    0.58
    Rudy
    0.57
     Rudy
    0.56
    stalt
    0.55
    Act Density 1.042%

    No Known Activations