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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical calculations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.44
     her
    -0.42
     voulez
    -0.42
     den
    -0.42
    ariConfig
    -0.41
     die
    -0.41
    уна
    -0.39
     Völ
    -0.39
     alle
    -0.38
     az
    -0.38
    POSITIVE LOGITS
     estekak
    0.99
    saraba
    0.97
    expandindo
    0.96
    yntaxException
    0.93
     يتيمه
    0.92
    ########.
    0.91
     Efq
    0.88
     Reſ
    0.87
     Houſe
    0.87
     Majefty
    0.85
    Act Density 0.551%

    No Known Activations