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

    Neuronpedia

    INDEX
    Explanations

    references to winning or victory

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to victories and wins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intestine
    -0.71
     encyclopedia
    -0.70
     bowel
    -0.70
    erity
    -0.68
     Uz
    -0.68
     incorpor
    -0.65
     notor
    -0.65
     trave
    -0.65
     pronouns
    -0.62
    umn
    -0.62
    POSITIVE LOGITS
    nings
    1.22
    now
    0.95
    iem
    0.95
    ners
    0.85
    athon
    0.82
    throp
    0.80
    iors
    0.79
    ces
    0.78
    hardt
    0.78
    win
    0.77
    Act Density 0.023%

    No Known Activations