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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to speaking and communication

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

    or phrases being said

    np_acts-logits-general · gemini-2.0-flash

    saying hello or goodbye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Frage
    -0.50
    DebuggerNonUser
    -0.49
    mities
    -0.45
     ural
    -0.45
    商品説明
    -0.45
     mismatch
    -0.45
    Millisecond
    -0.44
     FontFamily
    -0.44
    ēj
    -0.44
    EUROPA
    -0.42
    POSITIVE LOGITS
     goodbye
    1.40
     hello
    1.08
     yes
    0.88
     farewell
    0.88
    goodbye
    0.85
     thank
    0.84
     something
    0.83
     adiós
    0.83
     nothing
    0.83
     aloud
    0.78
    Act Density 0.093%

    No Known Activations