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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.90
     itſelf
    -0.89
    ########.
    -0.80
     becauſe
    -0.79
     pylint
    -0.77
    basicConfig
    -0.77
     StatefulWidget
    -0.76
     pleaſure
    -0.75
     themſelves
    -0.73
     ―――――
    -0.70
    POSITIVE LOGITS
    (')
    0.56
     EClass
    0.55
    Abitanti
    0.53
     level
    0.53
     Cal
    0.53
     Lindley
    0.52
     Mal
    0.50
    gawai
    0.50
     vs
    0.50
     E
    0.49
    Act Density 0.745%

    No Known Activations