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

    Neuronpedia

    INDEX
    Explanations

    interactions and attempts at communication between characters

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

    approaching or speaking to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.49
     Infórmanos
    -0.49
     bezeichneter
    -0.48
     Italijani
    -0.46
     Administrativna
    -0.43
    الحياه
    -0.42
     Мексичка
    -0.41
     nakalista
    -0.41
     habet
    -0.40
     Händen
    -0.39
    POSITIVE LOGITS
     chatted
    1.06
     chatting
    1.02
     approached
    1.02
     chat
    1.00
     conversation
    0.96
     interacted
    0.94
     conversations
    0.92
     approach
    0.91
     interact
    0.89
     interacting
    0.88
    Act Density 0.060%

    No Known Activations