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

    Neuronpedia

    INDEX
    Explanations

    instances of high-frequency or significant keywords related to importance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rzy
    -0.18
    IDGE
    -0.17
     Toro
    -0.15
    redient
    -0.15
    richt
    -0.15
    anko
    -0.14
    ismet
    -0.14
    loh
    -0.14
    414
    -0.14
    antor
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĤº
    0.23
    iez
    0.17
    osaur
    0.15
    eni
    0.15
    iag
    0.15
     Aerospace
    0.14
    缴
    0.14
     alt
    0.13
     cooled
    0.13
     straight
    0.13
    Act Density 0.001%

    No Known Activations