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

    Neuronpedia

    INDEX
    Explanations

    references to medical terminology or treatment methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -1.00
     المعيارى
    -0.95
     myſelf
    -0.95
     ་་
    -0.93
     Jefus
    -0.91
     pleaſure
    -0.90
    endphp
    -0.89
     doubtnut
    -0.87
     Monfieur
    -0.87
     uſed
    -0.86
    POSITIVE LOGITS
    ,
    0.56
    )
    0.56
    tr
    0.56
    e
    0.55
    ...)
    0.55
    er
    0.55
    os
    0.54
    <bos>
    0.54
    are
    0.53
     (
    0.53
    Act Density 0.438%

    No Known Activations