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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate acknowledgment or sharing of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yolu
    -0.15
    MODE
    -0.15
    rego
    -0.14
     ÐļÑĢа
    -0.14
    ether
    -0.14
    elsen
    -0.14
    uhe
    -0.14
    AZE
    -0.14
    etto
    -0.13
    mojom
    -0.13
    POSITIVE LOGITS
     note
    0.17
    aca
    0.15
     Stanton
    0.15
     Sab
    0.14
    ores
    0.14
     sab
    0.14
    ystack
    0.14
     оÑĤмеÑĤ
    0.14
     âĨij
    0.14
    ickt
    0.14
    Act Density 0.119%

    No Known Activations