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

    Neuronpedia

    INDEX
    Explanations

    references to messages or message-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     húmedo
    -0.43
     inoxidable
    -0.43
     autonomía
    -0.40
     mejorado
    -0.40
     dettaglio
    -0.40
     estudar
    -0.40
    AndEndTag
    -0.40
     especializado
    -0.38
     excelencia
    -0.38
     Melhor
    -0.38
    POSITIVE LOGITS
     message
    1.71
     Message
    1.65
     messages
    1.61
     Messages
    1.55
    message
    1.49
    Message
    1.42
     MESSAGE
    1.41
    Messages
    1.38
     mensagem
    1.37
     msg
    1.33
    Act Density 0.048%

    No Known Activations