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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Roman" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ken
    -0.16
    supply
    -0.16
    upply
    -0.16
    som
    -0.15
     rocky
    -0.15
    805
    -0.15
    vv
    -0.14
     Grimm
    -0.14
    rogen
    -0.14
    y
    -0.14
    POSITIVE LOGITS
    esco
    0.18
     numer
    0.17
    aised
    0.17
    ivec
    0.16
    utow
    0.16
    nesc
    0.16
    meler
    0.15
    ised
    0.15
     numeral
    0.15
    elli
    0.15
    Act Density 0.026%

    No Known Activations