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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance of 'the'

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

    Follows "the"

    np_acts-logits-general · gemini-2.0-flash

    the superlative or defining noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monarchs
    -0.52
     igjen
    -0.51
    ต่างๆ
    -0.47
    눠
    -0.46
     Ruhm
    -0.45
    mousemove
    -0.45
     ſaid
    -0.45
    kenal
    -0.44
    Recent
    -0.44
     hlavy
    -0.44
    POSITIVE LOGITS
     same
    0.86
     مشين
    0.80
    enumi
    0.79
     result
    0.77
    DoubleQuotes
    0.76
     easiest
    0.75
     quickest
    0.73
     fastest
    0.73
     perfect
    0.72
     exact
    0.72
    Act Density 0.281%

    No Known Activations