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

    Neuronpedia

    INDEX
    Explanations

    references to legal terminology and court-related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     […]
    -0.69
     …
    -0.51
    <bos>
    -0.44
     â
    -0.43
    â
    -0.40
    毫不
    -0.39
    有不
    -0.39
    ERRORS
    -0.37
     tasca
    -0.36
     Вікіпе
    -0.36
    POSITIVE LOGITS
    BufferException
    0.95
     HasFactory
    0.88
     للمعارف
    0.82
    rrggbb
    0.79
    cèse
    0.78
    ecore
    0.78
    Scénario
    0.76
    mobileqq
    0.75
     Савезне
    0.74
    Rüyada
    0.74
    Act Density 0.135%

    No Known Activations