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

    Neuronpedia

    INDEX
    Explanations

    phrases related to press releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.73
    AppData
    -0.69
     pract
    -0.68
     brightest
    -0.67
    vag
    -0.66
    otin
    -0.62
    skill
    -0.61
     apprentice
    -0.61
     impro
    -0.61
     seam
    -0.58
    POSITIVE LOGITS
     announcing
    1.19
     issued
    1.07
     touting
    0.89
     detailing
    0.88
    velop
    0.85
     titled
    0.83
    press
    0.80
     headlined
    0.79
     emailed
    0.78
     released
    0.76
    Act Density 0.038%

    No Known Activations