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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nodd
    -0.92
     enumer
    -0.80
     stadiums
    -0.79
     broadly
    -0.78
     dracon
    -0.78
     awarding
    -0.77
     implementations
    -0.75
     affili
    -0.74
     assass
    -0.73
    yip
    -0.73
    POSITIVE LOGITS
     Unable
    1.38
     Luckily
    1.35
     Eventually
    1.29
     Thankfully
    1.25
     His
    1.22
     She
    1.22
     Afterwards
    1.22
     Suddenly
    1.21
     Initially
    1.20
     Fortunately
    1.20
    Act Density 0.362%

    No Known Activations