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

    Neuronpedia

    INDEX
    Explanations

    terms associated with victory or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.65
     Infór
    -0.62
    enterOuterAlt
    -0.61
     Lingkungan
    -0.59
     faſt
    -0.59
    tagHelperRunner
    -0.59
    ſelves
    -0.58
     secundario
    -0.57
     mío
    -0.57
     suyo
    -0.57
    POSITIVE LOGITS
     WIN
    0.94
     win
    0.91
     winning
    0.81
     Win
    0.80
    WIN
    0.79
     wins
    0.77
     Winning
    0.75
     Wins
    0.71
    win
    0.68
    winning
    0.64
    Act Density 0.174%

    No Known Activations