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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific news outlets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the HuffPost and related media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.68
    izations
    -0.67
    ces
    -0.65
    BuyableInstoreAndOnline
    -0.65
     realization
    -0.61
    ========
    -0.61
    immers
    -0.60
     magnitude
    -0.60
    isations
    -0.59
    nings
    -0.58
    POSITIVE LOGITS
     HuffPost
    1.11
    edIn
    0.91
    shire
    0.91
    entimes
    0.83
    odox
    0.76
     Feedback
    0.70
    aires
    0.70
    aukee
    0.68
    arella
    0.67
    rary
    0.67
    Act Density 0.008%

    No Known Activations