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

    Neuronpedia

    INDEX
    Explanations

    terms related to encryption methods and ciphers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vla
    -0.17
    uguay
    -0.17
    aday
    -0.15
    AYER
    -0.15
    ÑĤии
    -0.15
    inded
    -0.15
    tier
    -0.15
    tains
    -0.15
    lar
    -0.15
    rawtypes
    -0.15
    POSITIVE LOGITS
    longleftrightarrow
    0.18
     Pemb
    0.17
    etu
    0.16
    optera
    0.15
    ainty
    0.15
    æ£ļ
    0.14
    enced
    0.14
    Brandon
    0.14
    ic
    0.14
    _AMD
    0.13
    Act Density 0.003%

    No Known Activations