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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people's actions and interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     territo
    -0.78
     kasa
    -0.75
     kase
    -0.70
     kamb
    -0.69
     vettoriale
    -0.67
     kuku
    -0.66
     mimi
    -0.66
     koz
    -0.65
     naer
    -0.65
     lele
    -0.65
    POSITIVE LOGITS
     people
    0.57
     kteří
    0.53
    "}")
    0.53
    Viitteet
    0.51
     bParam
    0.51
    people
    0.51
    HideFlags
    0.49
    िल्म
    0.48
     Paglinawan
    0.48
    <bos>
    0.48
    Act Density 0.356%

    No Known Activations