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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endra
    -0.15
    yny
    -0.14
    arrant
    -0.14
     Laden
    -0.14
    optera
    -0.14
    staking
    -0.14
    ertz
    -0.14
    estate
    -0.14
    earing
    -0.14
    Ir
    -0.13
    POSITIVE LOGITS
    s
    0.20
    shaw
    0.16
    uck
    0.15
    illo
    0.15
    loe
    0.14
    immel
    0.14
    izz
    0.14
    nel
    0.14
    nyder
    0.14
    ont
    0.14
    Act Density 0.033%

    No Known Activations