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

    Neuronpedia

    INDEX
    Explanations

    instances of the abbreviation "ac" and variations of the word "account."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ntax
    -0.16
    ilers
    -0.15
    ths
    -0.15
    ego
    -0.15
    lio
    -0.14
    iless
    -0.14
    uling
    -0.14
    igh
    -0.14
    cation
    -0.14
    unes
    -0.14
    POSITIVE LOGITS
    oust
    0.28
    quis
    0.27
     ac
    0.25
    acia
    0.25
    acias
    0.24
    rob
    0.24
    uity
    0.23
    adian
    0.23
    climate
    0.22
    ording
    0.22
    Act Density 0.012%

    No Known Activations