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

    Neuronpedia

    INDEX
    Explanations

    references to the word "Cedar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¼
    -0.17
    adf
    -0.15
    alse
    -0.15
    orama
    -0.15
    iaux
    -0.14
    ytt
    -0.14
    enes
    -0.14
    ysters
    -0.14
    mise
    -0.14
     Orc
    -0.14
    POSITIVE LOGITS
     Rapids
    0.25
     rap
    0.20
     Sinai
    0.16
    hurst
    0.16
     Shake
    0.15
    quires
    0.14
    atum
    0.14
    RAP
    0.14
    amm
    0.14
    rieg
    0.14
    Act Density 0.007%

    No Known Activations