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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "do" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rv
    -0.16
    atorio
    -0.15
    eldon
    -0.15
    doch
    -0.14
    ustil
    -0.14
    rett
    -0.14
    ni
    -0.14
    AndPassword
    -0.14
    ror
    -0.14
    redd
    -0.14
    POSITIVE LOGITS
    cket
    0.28
     justice
    0.21
    ctest
    0.20
     away
    0.19
    ork
    0.19
    ctors
    0.19
    ác
    0.18
    ctr
    0.18
     tricks
    0.18
    justice
    0.18
    Act Density 0.177%

    No Known Activations