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

    Neuronpedia

    INDEX
    Explanations

    variables and their attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ‍
    -0.43
    íncipe
    -0.42
     quien
    -0.41
     Don
    -0.41
     et
    -0.41
     
    -0.40
    c
    -0.39
    readAs
    -0.39
    -
    -0.39
     wurden
    -0.39
    POSITIVE LOGITS
     pleaſure
    0.96
     kasarigan
    0.88
     raiſ
    0.88
    #
    0.88
     المعيارى
    0.85
     purpoſe
    0.85
    Sucesor
    0.84
    WebVitals
    0.82
    IsInitialized
    0.82
     itſelf
    0.81
    Act Density 0.210%

    No Known Activations