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

    Neuronpedia

    INDEX
    Explanations

    keywords related to brands and product names

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.75
    ArgsConstructor
    -0.62
    pola
    -0.59
    djangoproject
    -0.56
    ]._
    -0.56
    AdapterFactory
    -0.54
    </s>
    -0.52
    $_
    -0.52
      
    -0.51
    Ө
    -0.51
    POSITIVE LOGITS
    IVEREF
    0.64
    postsleuth
    0.55
     rêves
    0.54
     viewType
    0.53
    şekkür
    0.51
     fédé
    0.49
     tiszt
    0.49
    <tfoot>
    0.49
    CloseOperation
    0.49
     jár
    0.49
    Act Density 0.194%

    No Known Activations