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

    Neuronpedia

    INDEX
    Explanations

    incidents of greetings and their variations

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

    greeting others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [*]
    -0.49
     Malone
    -0.47
    File
    -0.44
     File
    -0.43
     parts
    -0.40
     Piper
    -0.40
     file
    -0.38
    OutputPath
    -0.38
     files
    -0.38
     Parsons
    -0.38
    POSITIVE LOGITS
     greet
    1.22
    greet
    1.16
     greeting
    1.15
     Greet
    1.14
     greets
    1.13
     Greeting
    1.11
    Greeting
    1.08
    greeting
    1.06
     greetings
    1.04
    Greet
    1.02
    Act Density 0.003%

    No Known Activations