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

    Neuronpedia

    INDEX
    Explanations

    formal expressions and transitional phrases in a text

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

    the word "In"

    np_acts-logits-general · gemini-2.0-flash

    in certain contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.97
    addCriterion
    -0.96
    脚注の使い方
    -0.91
     itſelf
    -0.87
    expandindo
    -0.87
     protoimpl
    -0.86
    parsedMessage
    -0.81
     Jefus
    -0.81
     themſelves
    -0.80
    OGND
    -0.79
    POSITIVE LOGITS
     larger
    1.01
     smaller
    1.00
     most
    0.90
     older
    0.87
     large
    0.81
    larger
    0.80
     newer
    0.79
     rare
    0.77
     certain
    0.77
    smaller
    0.77
    Act Density 0.694%

    No Known Activations