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

    Neuronpedia

    INDEX
    Explanations

    references to citation formats or academic contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.08
     myſelf
    -0.98
     Anſ
    -0.93
     Theſe
    -0.84
     iſt
    -0.82
     Monfieur
    -0.81
     Jefus
    -0.80
     iconFacebook
    -0.78
     ſta
    -0.78
     Eſ
    -0.77
    POSITIVE LOGITS
     aldus
    0.69
    .
    0.62
    Последние
    0.50
     ifølge
    0.49
    RegressionTest
    0.49
     enligt
    0.48
     noted
    0.47
     said
    0.46
    があると
    0.46
     olej
    0.46
    Act Density 0.402%

    No Known Activations