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

    Neuronpedia

    INDEX
    Explanations

    mentions of publicity

    oai_token-act-pair · gpt-3.5-turbo

    references to publicity and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.85
    artment
    -0.75
    tre
    -0.72
    osite
    -0.68
    ¯¯¯¯
    -0.67
    stead
    -0.64
    anical
    -0.62
    WER
    -0.61
    aghetti
    -0.61
    arre
    -0.60
    POSITIVE LOGITS
    quickShipAvailable
    0.94
    seeking
    0.93
     endorsements
    0.91
    seekers
    0.90
     fades
    0.89
     bestowed
    0.85
     seekers
    0.84
     afforded
    0.84
     seeker
    0.80
     Murdoch
    0.80
    Act Density 0.152%

    No Known Activations