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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and phrases indicating importance or value

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

    Appears before "than"

    np_acts-logits-general · gemini-2.0-flash

    more ... than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itinéraire
    -0.70
     Catawiki
    -0.69
     esternos
    -0.68
    addContainerGap
    -0.65
    DrawerToggle
    -0.64
     gyhoeddwyd
    -0.63
    ollectionView
    -0.63
     ArrayAdapter
    -0.63
    CodeAnalysis
    -0.60
     AssemblyCulture
    -0.60
    POSITIVE LOGITS
     than
    4.38
     THAN
    2.96
    than
    2.93
    Than
    2.67
     Than
    2.56
     niż
    2.54
     kuin
    2.21
    THAN
    2.17
     než
    2.12
     än
    2.12
    Act Density 0.677%

    No Known Activations