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

    Neuronpedia

    INDEX
    Explanations

    expressions or phrases related to communication or conveying messages

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

    message or messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     listing
    -0.39
     computing
    -0.38
     computer
    -0.38
     compute
    -0.36
     listings
    -0.35
     routines
    -0.34
     databases
    -0.33
     liquidation
    -0.32
     komputer
    -0.32
    Автор
    -0.32
    POSITIVE LOGITS
     message
    1.18
    message
    1.09
     mensagem
    1.04
     messaggio
    1.03
     mensaje
    1.02
     Message
    1.01
     MESSAGE
    1.00
     messages
    0.94
    MESSAGE
    0.94
     Messages
    0.92
    Act Density 0.007%

    No Known Activations