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

    Neuronpedia

    INDEX
    Explanations

    words related to disappearance or vanishing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disappearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tennis
    -0.72
    ocations
    -0.61
    oker
    -0.61
     plurality
    -0.59
     Demand
    -0.59
    ios
    -0.59
    Demand
    -0.58
    alist
    -0.57
    tha
    -0.57
    asio
    -0.56
    POSITIVE LOGITS
     mysteriously
    1.13
     altogether
    1.01
     into
    1.00
     peacefully
    0.97
     unnoticed
    0.96
     overnight
    0.91
     abruptly
    0.89
    owship
    0.88
     entirely
    0.86
     forever
    0.85
    Act Density 0.061%

    No Known Activations