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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey significance or impact

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

    Intensifiers like "more," "much," and "difficult" follow "it"

    np_acts-logits-general · gemini-2.0-flash

    makes it more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.64
     myſelf
    -0.58
    WillAppear
    -0.56
    bių
    -0.55
    Портали
    -0.55
     becauſe
    -0.54
     snippetHide
    -0.54
    chemise
    -0.51
     chofe
    -0.51
     ftate
    -0.50
    POSITIVE LOGITS
     easier
    0.73
     more
    0.60
     shine
    0.58
     even
    0.57
     seem
    0.57
     feel
    0.57
     sweeter
    0.55
     look
    0.55
     doubly
    0.54
     ancor
    0.53
    Act Density 0.126%

    No Known Activations