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

    Neuronpedia

    INDEX
    Explanations

    topic-related keywords or actions related to announcements and declarations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "announced."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avery
    -0.77
    otin
    -0.70
    angs
    -0.69
    imeo
    -0.68
    phe
    -0.67
    isma
    -0.67
    osph
    -0.67
    vag
    -0.67
    iking
    -0.67
    Pg
    -0.66
    POSITIVE LOGITS
     announces
    0.82
     partnerships
    0.78
    doms
    0.77
     announcements
    0.77
     goodbye
    0.75
     beforehand
    0.71
    details
    0.70
     announcing
    0.69
     anew
    0.69
     layoffs
    0.68
    Act Density 0.044%

    No Known Activations