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

    Neuronpedia

    INDEX
    Explanations

    dates and times mentioned in a document

    oai_token-act-pair · gpt-3.5-turbo

    the end of an input sequence or document termination markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynt
    -0.67
    $$$$
    -0.65
    ????????
    -0.65
    ãĥ¼ãĥĨ
    -0.63
    ptin
    -0.62
    RL
    -0.62
    200000
    -0.62
    Daddy
    -0.61
    anan
    -0.60
    Versions
    -0.60
    POSITIVE LOGITS
     behalf
    1.00
    etime
    0.81
    sight
    0.76
    shore
    0.73
     Haunted
    0.71
    eness
    0.70
     Tradable
    0.70
    coming
    0.69
     Flickr
    0.68
     Aging
    0.68
    Act Density 0.045%

    No Known Activations