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

    Neuronpedia

    INDEX
    Explanations

    names and references to prominent individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.10
     Beſ
    -1.10
     Eſ
    -1.06
     Efq
    -1.05
     Theſe
    -1.03
     pleaſure
    -1.02
     myſelf
    -1.01
     themſelves
    -1.00
     Monfieur
    -0.99
     whoſe
    -0.99
    POSITIVE LOGITS
     von
    0.63
    regon
    0.62
    guten
    0.61
    fikasi
    0.59
    blockList
    0.59
    OrBuilder
    0.56
     Von
    0.56
    Im
    0.56
    alter
    0.55
    asteroide
    0.55
    Act Density 0.885%

    No Known Activations