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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack or insufficiency

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of sufficiency or lack thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inarily
    -0.84
    amon
    -0.81
    ista
    -0.74
    eson
    -0.73
    occ
    -0.72
    folk
    -0.68
    azar
    -0.68
    eer
    -0.67
    mast
    -0.67
    eston
    -0.66
    POSITIVE LOGITS
     anymore
    0.86
     convincing
    0.69
     nor
    0.68
     calories
    0.68
     Asians
    0.67
     Thieves
    0.66
     academ
    0.66
     Centauri
    0.64
     yen
    0.64
     bedrooms
    0.63
    Act Density 0.019%

    No Known Activations