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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mirrors
    -0.16
     दर
    -0.15
    еж
    -0.15
    321
    -0.15
     Bracket
    -0.14
     комÑĥ
    -0.14
    ids
    -0.14
     consensus
    -0.14
    á»ĵi
    -0.14
    Ñĸж
    -0.14
    POSITIVE LOGITS
    interpreter
    0.17
    aldo
    0.15
    ÑĢоÑģÑĤ
    0.15
     strstr
    0.14
     BORDER
    0.14
     Breed
    0.14
    DP
    0.13
    ë°ĶìĿ´
    0.13
    DATED
    0.13
    rieb
    0.13
    Act Density 0.008%

    No Known Activations