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

    Neuronpedia

    INDEX
    Explanations

    specific phrases mixed with folklore terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -1.43
     purpoſe
    -1.41
     Audiodateien
    -1.39
     kasarigan
    -1.35
     ویکی‌پدیا
    -1.31
     myſelf
    -1.29
     themſelves
    -1.29
    Geplaatst
    -1.29
    alakip
    -1.28
    StoryboardSegue
    -1.28
    POSITIVE LOGITS
    k
    0.91
    m
    0.91
    v
    0.90
    l
    0.90
    A
    0.89
    h
    0.89
    d
    0.89
    c
    0.86
    n
    0.86
    M
    0.85
    Act Density 0.242%

    No Known Activations