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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ock
    -0.15
    ancy
    -0.15
    ogn
    -0.15
    iais
    -0.14
    avis
    -0.14
    kos
    -0.14
    avin
    -0.14
    neider
    -0.14
    lop
    -0.14
    ufs
    -0.14
    POSITIVE LOGITS
     justice
    0.19
    ogle
    0.18
     mistakes
    0.18
    ctest
    0.16
    justice
    0.16
     not
    0.15
    æ³ķ
    0.15
    uten
    0.15
    -it
    0.15
     wonders
    0.15
    Act Density 0.068%

    No Known Activations