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

    Neuronpedia

    INDEX
    Explanations

    nouns and identifiers related to ownership and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrant
    -0.15
    estli
    -0.14
    à¸Ļà¸ģ
    -0.14
    ewan
    -0.14
    .oracle
    -0.13
    esco
    -0.13
    еÑĩение
    -0.13
    avigator
    -0.13
    éĻµ
    -0.13
     Hao
    -0.13
    POSITIVE LOGITS
    zel
    0.17
    ijn
    0.16
    wig
    0.15
    atern
    0.15
    irq
    0.14
     Bubble
    0.14
    icensed
    0.14
    atars
    0.14
    chains
    0.13
    kowski
    0.13
    Act Density 0.046%

    No Known Activations