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

    Neuronpedia

    INDEX
    Explanations

    references to lists and instructional formats in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.77
    ibu
    -0.71
     Reincarnated
    -0.69
    xit
    -0.62
    ahu
    -0.62
     [+
    -0.61
     Demand
    -0.61
    netflix
    -0.61
    advertising
    -0.59
    YP
    -0.59
    POSITIVE LOGITS
     summarize
    0.94
     caveats
    0.94
     spoilers
    0.90
     caveat
    0.90
     spoiler
    0.87
     ital
    0.87
    endix
    0.85
     summar
    0.85
     suffice
    0.85
     disclaimer
    0.84
    Act Density 0.355%

    No Known Activations