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

    Neuronpedia

    INDEX
    Explanations

    the word "Dig" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "dig" and its variations, indicating a focus on digging or related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VALUE
    -0.79
     ACTIONS
    -0.75
    OHN
    -0.66
    BuyableInstoreAndOnline
    -0.64
     CLA
    -0.63
     CHO
    -0.63
     Karin
    -0.63
     Peninsula
    -0.62
    Reloaded
    -0.62
     Eliot
    -0.62
    POSITIVE LOGITS
    imon
    1.26
    Dig
    1.20
    itized
    1.14
    gers
    1.05
    itial
    1.00
    dig
    0.99
    itive
    0.97
    ging
    0.96
    ibility
    0.96
    alog
    0.95
    Act Density 0.007%

    No Known Activations