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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "up" and its variations

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

    "up" preceding "to"

    np_acts-logits-general · gemini-2.0-flash

    up to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.88
    jsonwebtoken
    -0.83
     متعلقه
    -0.82
     Efq
    -0.81
     itſelf
    -0.80
     pleaſure
    -0.79
     faſt
    -0.77
     themſelves
    -0.74
    neſs
    -0.72
     ſtill
    -0.72
    POSITIVE LOGITS
     down
    0.78
    down
    0.68
     Down
    0.67
    Down
    0.63
     DOWN
    0.58
     up
    0.55
     Up
    0.51
    Up
    0.50
     downs
    0.48
    up
    0.47
    Act Density 0.060%

    No Known Activations