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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and helpfulness

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

    hope this helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.73
    postsleuth
    -0.67
    scribers
    -0.65
     OFDb
    -0.65
    styleType
    -0.64
    MLLoader
    -0.61
    RTEE
    -0.61
    səhifə
    -0.61
     wireType
    -0.60
     betweenstory
    -0.60
    POSITIVE LOGITS
     information
    0.42
     info
    0.39
     helpful
    0.38
     insight
    0.37
    info
    0.34
    information
    0.34
     clue
    0.34
    Cordialement
    0.33
     :-)
    0.33
    INFO
    0.32
    Act Density 0.010%

    No Known Activations