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

    Neuronpedia

    INDEX
    Explanations

    reports on news or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reports" indicating news or journalism activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istical
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    agues
    -0.59
    respective
    -0.58
     gauge
    -0.57
    folk
    -0.56
    lor
    -0.56
    thumbnails
    -0.55
     Ples
    -0.55
    lling
    -0.54
    POSITIVE LOGITS
     below
    0.68
     BELOW
    0.67
    :[
    0.66
    :
    0.65
    :(
    0.64
    :"
    0.64
    :'
    0.62
    olate
    0.62
    :#
    0.60
     NAD
    0.60
    Act Density 0.103%

    No Known Activations