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

    Neuronpedia

    INDEX
    Explanations

    references to error messages

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

    message and get/set variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SaveChangesAsync
    -0.48
    WebControls
    -0.46
     suits
    -0.44
     שוליים
    -0.44
     vocales
    -0.43
    soil
    -0.42
     slang
    -0.41
     صوتيه
    -0.41
     useAuth
    -0.41
     aéro
    -0.41
    POSITIVE LOGITS
    message
    1.98
    Message
    1.16
    MESSAGE
    1.04
    getMessage
    0.87
     message
    0.85
    essage
    0.80
     Message
    0.77
     MESSAGE
    0.73
     getMessage
    0.69
     setMessage
    0.69
    Act Density 0.003%

    No Known Activations