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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Now" indicating a shift in time or sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to current events or news stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vati
    -0.74
    CONCLUS
    -0.71
    Newsletter
    -0.70
    Conclusion
    -0.69
    venge
    -0.65
    forth
    -0.62
    Roaming
    -0.61
    ionage
    -0.59
    ITNESS
    -0.59
    Lastly
    -0.59
    POSITIVE LOGITS
    eaturing
    0.71
    ategories
    0.59
    utterstock
    0.59
     Transcript
    0.58
     infographic
    0.58
     bombshell
    0.57
    uesday
    0.56
     frontman
    0.56
     Printed
    0.56
    actionDate
    0.55
    Act Density 0.958%

    No Known Activations