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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and significant identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AKE
    -0.16
    erman
    -0.15
    emen
    -0.15
    efd
    -0.14
    äºĭ
    -0.14
    ermann
    -0.14
    vero
    -0.14
    INDOW
    -0.14
    ermen
    -0.13
    NJ
    -0.13
    POSITIVE LOGITS
    iple
    0.16
     Dann
    0.15
    -fit
    0.15
    imoto
    0.15
    arest
    0.15
    ncoder
    0.14
    ntity
    0.14
    izu
    0.13
    cury
    0.13
     Birch
    0.13
    Act Density 0.003%

    No Known Activations