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

    Neuronpedia

    INDEX
    Explanations

    words related to downward or out-of-control movement or deterioration

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "spiral."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     relics
    -0.68
     presence
    -0.64
     Corpus
    -0.64
     Mayweather
    -0.64
    Hispanic
    -0.63
    aires
    -0.62
     Commissioners
    -0.58
     plaque
    -0.58
     fact
    -0.58
     reserve
    -0.58
    POSITIVE LOGITS
    aling
    1.42
    alling
    1.41
    aled
    1.27
    alled
    1.17
    als
    1.13
    atory
    0.97
    acles
    0.96
    ationally
    0.92
    ited
    0.92
    ging
    0.91
    Act Density 0.057%

    No Known Activations