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

    Neuronpedia

    INDEX
    Explanations

    interactions involving requests or expressions of gratitude and acknowledgment

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

    Terms of endearment

    np_acts-logits-general · gemini-2.0-flash

    terms of endearment or address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     którzy
    -0.55
     mukana
    -0.55
    [];
    -0.52
     noastră
    -0.51
    خصة
    -0.50
     culturali
    -0.49
     herself
    -0.48
    MLLoader
    -0.48
     keluarganya
    -0.48
    TagHelpers
    -0.47
    POSITIVE LOGITS
     sweetie
    1.00
     dear
    0.96
     buddy
    0.90
     sweetheart
    0.90
     darling
    0.85
    weetie
    0.85
     sir
    0.79
     baby
    0.76
     dearest
    0.76
     lad
    0.76
    Act Density 0.131%

    No Known Activations