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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate greetings or conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    СТВА
    -0.79
    НОЙ
    -0.77
    СТВО
    -0.76
    НОСТИ
    -0.73
    НОЕ
    -0.67
     viewDidLoad
    -0.63
    stücke
    -0.62
    ЦИЯ
    -0.62
    НЫ
    -0.61
    ЩИ
    -0.60
    POSITIVE LOGITS
     С
    1.04
    С
    1.01
    В
    0.95
    А
    0.94
    У
    0.91
    О
    0.91
     В
    0.89
    И
    0.89
     О
    0.88
     А
    0.88
    Act Density 0.029%

    No Known Activations