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

    Neuronpedia

    INDEX
    Explanations

    references to the speaker or those they are addressing in a conversation

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

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McNally
    -0.44
    InteropServices
    -0.43
     McF
    -0.41
     Victory
    -0.40
     Gare
    -0.38
    ValueGeneration
    -0.38
     benefitted
    -0.37
    美味しかったです
    -0.37
     benefited
    -0.36
     reputable
    -0.35
    POSITIVE LOGITS
     fragen
    0.57
    Asking
    0.56
     question
    0.56
    uxley
    0.56
     ask
    0.55
     Asking
    0.54
     asked
    0.53
     pytania
    0.53
     NSCoder
    0.52
     řek
    0.52
    Act Density 0.008%

    No Known Activations