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

    Neuronpedia

    INDEX
    Explanations

    mentions of watching or following events in a news context

    oai_token-act-pair · gpt-3.5-turbo

    the word "JUST" and its variations, indicating a focus on assertions or emphatic statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quo
    -0.67
     intimately
    -0.66
     proletariat
    -0.63
     faithfully
    -0.61
     thereof
    -0.60
     progressively
    -0.60
     fullest
    -0.59
     abundantly
    -0.58
    luster
    -0.58
     invari
    -0.57
    POSITIVE LOGITS
    ices
    1.22
     WATCHED
    1.19
    icia
    0.96
    ifications
    0.91
    ICE
    0.89
    iciary
    0.88
    itia
    0.86
    Giving
    0.86
    ICES
    0.86
    inian
    0.85
    Act Density 0.028%

    No Known Activations