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

    Neuronpedia

    INDEX
    Explanations

    elements related to structure and functioning of complex systems or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]='\
    -0.59
    RegressionTest
    -0.54
    örd
    -0.54
    ooker
    -0.52
    oneof
    -0.52
    🏻‍♀️
    -0.51
    ,:),
    -0.51
    extAlignment
    -0.51
    Atsauces
    -0.51
    ();)
    -0.50
    POSITIVE LOGITS
     shouldn
    1.00
     wouldn
    0.94
     didn
    0.91
     needn
    0.91
     may
    0.90
     hadn
    0.87
     couldn
    0.83
     might
    0.82
     wasn
    0.81
     should
    0.80
    Act Density 1.705%

    No Known Activations