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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and expressions of gratitude

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

    greetings and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorin
    -0.67
    ElementException
    -0.51
     Persönlichkeit
    -0.50
     Finanzierung
    -0.50
     suaminya
    -0.49
     hendes
    -0.49
     Nachhaltigkeit
    -0.49
     bancaire
    -0.47
     Geburt
    -0.47
     Wahrnehmung
    -0.47
    POSITIVE LOGITS
     guys
    0.60
     Guys
    0.58
     Dear
    0.52
     Taktlose
    0.51
     thank
    0.51
     dear
    0.51
    Gentlemen
    0.51
     PJ
    0.50
     gentlemen
    0.50
     Hi
    0.50
    Act Density 0.030%

    No Known Activations