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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "dig" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.17
    adow
    -0.17
    adows
    -0.17
    ç·Ĵ
    -0.16
    ucus
    -0.16
     PartialView
    -0.15
    holder
    -0.15
    olan
    -0.15
    enant
    -0.15
     Ritual
    -0.15
    POSITIVE LOGITS
     dig
    0.33
    dig
    0.31
     Dig
    0.31
    ression
    0.30
    Dig
    0.29
    ested
    0.27
    ress
    0.26
    ITAL
    0.25
     digs
    0.25
    ãĤ¿ãĥ«
    0.24
    Act Density 0.012%

    No Known Activations