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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations and news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phrine
    -0.71
     Pric
    -0.71
    ffen
    -0.67
     grun
    -0.66
     goddamn
    -0.66
     cold
    -0.66
    ught
    -0.65
    ¯¯
    -0.65
    hetti
    -0.65
    qqa
    -0.64
    POSITIVE LOGITS
    letters
    1.13
    letter
    0.95
    room
    0.94
     Tycoon
    0.88
    ource
    0.85
     Coverage
    0.80
    reader
    0.79
    hips
    0.79
    worthy
    0.79
     Releases
    0.79
    Act Density 0.030%

    No Known Activations