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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general statements, statistics, or observations

    oai_token-act-pair · gpt-3.5-turbo

    words indicating frequency or generality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.61
     consequential
    -0.61
     Pieces
    -0.60
     Seah
    -0.59
     Gothic
    -0.59
     Byzantine
    -0.59
     Keeper
    -0.59
    Alias
    -0.58
     Krypt
    -0.57
    Asset
    -0.57
    POSITIVE LOGITS
     owe
    1.27
     reside
    1.22
     deserve
    1.19
     seem
    1.17
     aren
    1.16
     belong
    1.15
     rely
    1.15
     have
    1.12
     comprise
    1.12
     prefer
    1.11
    Act Density 0.202%

    No Known Activations