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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "dig" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adow
    -0.18
    ç·Ĵ
    -0.17
    adows
    -0.16
    deen
    -0.16
    edly
    -0.15
    holder
    -0.15
     PartialView
    -0.15
    ijo
    -0.15
     ritual
    -0.15
    彦
    -0.15
    POSITIVE LOGITS
     dig
    0.34
    dig
    0.31
     Dig
    0.30
    ression
    0.30
    Dig
    0.28
    ested
    0.27
     digs
    0.26
    ress
    0.24
     digging
    0.24
    ITAL
    0.23
    Act Density 0.010%

    No Known Activations