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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the"

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

    increasing impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getJSONArray
    -0.45
    ────────
    -0.43
     Pickett
    -0.41
     Told
    -0.40
     front
    -0.39
     StringTokenizer
    -0.39
     Blatt
    -0.39
    localVar
    -0.39
     town
    -0.38
     Namely
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.73
     leſs
    0.69
     raiſ
    0.65
     fometimes
    0.62
     uſed
    0.61
     juſ
    0.60
     itſelf
    0.60
     whoſe
    0.60
    VYMaps
    0.59
     ſever
    0.58
    Act Density 0.075%

    No Known Activations