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

    Neuronpedia

    INDEX
    Explanations

    comparative or superlative adjectives and their associated contexts

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

    further values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.52
    verwijspagina
    -0.50
     Photocase
    -0.47
    HideFlags
    -0.45
     themſelves
    -0.44
    prepareStatement
    -0.43
    toBeTruthy
    -0.42
     BytesLike
    -0.42
     nahilalakip
    -0.42
    :+:
    -0.42
    POSITIVE LOGITS
     ännu
    0.50
     even
    0.48
    更是
    0.48
    Even
    0.45
     further
    0.45
    fromnode
    0.45
     ještě
    0.43
     Even
    0.43
    それも
    0.42
    余計
    0.42
    Act Density 0.201%

    No Known Activations