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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "winning" and its variations

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

    winning achievement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oh
    -0.46
    kreises
    -0.46
     squats
    -0.46
     հղումներ
    -0.44
    Peers
    -0.43
     affitto
    -0.43
    rachtet
    -0.43
     portas
    -0.43
     GROUPS
    -0.42
     vecka
    -0.42
    POSITIVE LOGITS
     winning
    1.82
     Winning
    1.70
    Winning
    1.70
    winning
    1.69
     winner
    0.93
     winners
    0.93
     losing
    0.92
    losing
    0.90
    winner
    0.85
     winnings
    0.84
    Act Density 0.004%

    No Known Activations