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

    Neuronpedia

    INDEX
    Explanations

    references to the action of digging or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç·Ĵ
    -0.18
    enberg
    -0.17
    ulen
    -0.16
    adow
    -0.16
    deen
    -0.16
    arger
    -0.15
    uur
    -0.15
    彦
    -0.15
    adows
    -0.15
    ucus
    -0.15
    POSITIVE LOGITS
     dig
    0.34
    dig
    0.32
     Dig
    0.30
    ression
    0.29
    Dig
    0.28
    ested
    0.26
     digs
    0.25
    ress
    0.25
     digging
    0.24
    ãĤ¿ãĥ«
    0.23
    Act Density 0.013%

    No Known Activations