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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "statement."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongan
    -0.17
    usu
    -0.17
    -scalable
    -0.16
     nhau
    -0.16
    ìĦł
    -0.16
    sey
    -0.15
    ram
    -0.14
    ongyang
    -0.14
    erman
    -0.14
    readcr
    -0.14
    POSITIVE LOGITS
    edly
    0.19
    naires
    0.18
    xic
    0.17
    naire
    0.17
    fact
    0.16
    rophe
    0.16
    .Statement
    0.15
    making
    0.15
    idebar
    0.15
    ourcem
    0.14
    Act Density 0.034%

    No Known Activations