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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or the state of being unsure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.67
    +#+#
    -0.55
     engraçadas
    -0.54
     demais
    -0.52
     alberi
    -0.51
     blessés
    -0.50
     EconPapers
    -0.50
     importanza
    -0.50
     ordini
    -0.46
     suivants
    -0.46
    POSITIVE LOGITS
    "):
    0.80
     referenties
    0.75
    --)
    0.73
    jedis
    0.71
    '):
    0.71
    "){
    0.70
    ]){
    0.70
    tubers
    0.70
     StatefulWidget
    0.69
    "),
    0.67
    Act Density 0.101%

    No Known Activations