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

    Neuronpedia

    INDEX
    Explanations

    words related to physical flexibility or actions involving exertion

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "flex" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reincarn
    -0.80
    keepers
    -0.71
     Ragnarok
    -0.70
     Columb
    -0.70
     âĸº
    -0.66
    ģĸ
    -0.66
     Munich
    -0.65
    keeping
    -0.64
    keeper
    -0.61
     Nare
    -0.61
    POSITIVE LOGITS
    ibilities
    1.06
    itime
    1.06
    ibly
    1.04
    arious
    0.98
    iants
    0.91
    ressive
    0.91
     flex
    0.90
    inished
    0.86
    esville
    0.85
    ional
    0.84
    Act Density 0.026%

    No Known Activations