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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets and programming terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     disg
    -0.75
     whis
    -0.73
     prosecut
    -0.72
     apologies
    -0.71
    taboola
    -0.71
     jams
    -0.69
     fabrication
    -0.69
     jaws
    -0.68
     acron
    -0.66
     melt
    -0.66
    POSITIVE LOGITS
    ()
    1.37
    ())
    1.28
    ().
    1.24
    ();
    1.22
    ():
    1.12
    Item
    1.12
    (),
    1.12
    Header
    1.10
    Limit
    1.09
    _
    1.08
    Act Density 0.136%

    No Known Activations