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

    Neuronpedia

    INDEX
    Explanations

    references to legal terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yorsunuz
    -0.58
    +#+#
    -0.55
     onCancelled
    -0.54
     snippetHide
    -0.52
    RectangleBorder
    -0.51
     very
    -0.49
     متعلقه
    -0.48
    …」
    -0.47
    rungsseite
    -0.46
    !")
    -0.46
    POSITIVE LOGITS
     ¶
    0.67
    Slip
    0.64
     (“
    0.64
     slip
    0.64
     ("
    0.62
     Compl
    0.59
     Slip
    0.59
    slip
    0.58
    ("[
    0.57
     ๆ
    0.55
    Act Density 2.739%

    No Known Activations