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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and affection in dialogues

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

    Terms of endearment

    np_acts-logits-general · gemini-2.0-flash

    terms of endearment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.62
     متعلقه
    -0.59
     którzy
    -0.56
    发表于
    -0.53
    তথ্যসূত্র
    -0.52
    ={}
    -0.52
    まさに
    -0.50
    ={};
    -0.50
     jsPsych
    -0.49
     BorderRadius
    -0.49
    POSITIVE LOGITS
     darling
    1.14
     sweetheart
    1.09
     sweetie
    1.06
     dear
    0.95
     love
    0.94
     dearest
    0.93
     Darling
    0.89
    Darling
    0.87
     babe
    0.86
     cariño
    0.86
    Act Density 0.132%

    No Known Activations