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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of the word "one"

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

    the word "one"

    np_acts-logits-general · gemini-2.0-flash

    the word one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tably
    -0.70
    ly
    -0.70
     Isidro
    -0.68
     ſch
    -0.67
    dır
    -0.64
    ably
    -0.64
    fully
    -0.61
     București
    -0.61
     ―――――
    -0.58
     Græ
    -0.58
    POSITIVE LOGITS
     Ones
    1.05
     One
    0.98
     hundred
    0.96
     ONE
    0.93
    iric
    0.93
    Ones
    0.92
     estimés
    0.90
    One
    0.88
    -------------</
    0.87
    בודה
    0.86
    Act Density 0.173%

    No Known Activations