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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or entities involved in notable historical or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ίοÏĤ
    -0.16
    serie
    -0.15
    971
    -0.15
    961
    -0.15
    uristic
    -0.15
    ocache
    -0.15
     laid
    -0.14
    ead
    -0.14
    exclude
    -0.14
    enha
    -0.14
    POSITIVE LOGITS
    ningen
    0.38
    heten
    0.30
    lingen
    0.28
    ingen
    0.26
    standen
    0.24
    isten
    0.24
    isen
    0.24
    ivet
    0.23
    ansen
    0.23
    ature
    0.23
    Act Density 0.071%

    No Known Activations