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

    Neuronpedia

    INDEX
    Explanations

    references to narcissistic behavior and its impact in various contexts

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

    Sentences starting with coordinating conjunctions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and sentence starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -1.42
    OGND
    -1.25
    adaptiveStyles
    -1.13
     AssemblyVersion
    -1.12
    StoryboardSegue
    -1.10
     lenker
    -1.08
    TagMode
    -1.07
    AddTagHelper
    -1.06
     EconPapers
    -1.06
     disambiguazione
    -1.06
    POSITIVE LOGITS
     It
    0.93
     it
    0.92
     But
    0.74
     That
    0.73
     I
    0.70
     They
    0.69
     However
    0.67
     especially
    0.67
     they
    0.67
     he
    0.66
    Act Density 0.254%

    No Known Activations