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

    Neuronpedia

    INDEX
    Explanations

    words related to news organizations or news content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "News"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.71
    uras
    -0.69
    vernment
    -0.67
    uates
    -0.61
     downs
    -0.61
    uations
    -0.61
    uve
    -0.61
     hump
    -0.61
     lumber
    -0.61
     stagger
    -0.60
    POSITIVE LOGITS
    letters
    1.37
    room
    1.29
    Hour
    1.13
    peak
    1.09
    radio
    1.09
    groups
    1.05
    night
    1.04
    Radio
    0.99
    reader
    0.98
    letter
    0.98
    Act Density 0.033%

    No Known Activations