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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the"

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

    "(the ...)" structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.68
     GenerationType
    -0.60
     AssemblyCulture
    -0.59
    principalColumn
    -0.58
    BeginContext
    -0.56
    ItemBackground
    -0.56
    OGND
    -0.54
     oprot
    -0.52
    transQ
    -0.52
     betweenstory
    -0.52
    POSITIVE LOGITS
    :])
    0.49
     Reprodu
    0.45
     pregi
    0.43
    “
    0.43
     reprodu
    0.42
     vru
    0.42
     Lehmann
    0.41
    reprodu
    0.40
     huom
    0.40
     cuk
    0.40
    Act Density 0.036%

    No Known Activations