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

    Neuronpedia

    INDEX
    Explanations

    greetings and conversational openings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.94
     tfsi
    -0.71
     Coolidge
    -0.69
     chảy
    -0.68
     Mayweather
    -0.68
    Открыть
    -0.68
     crossorigin
    -0.68
    saraba
    -0.68
     Itachi
    -0.68
     Kakashi
    -0.67
    POSITIVE LOGITS
     I
    0.56
    Hello
    0.56
    Referencie
    0.56
    SequentialGroup
    0.51
    Hi
    0.51
    hello
    0.51
    Greetings
    0.50
    您好
    0.49
     hello
    0.45
      
    0.45
    Act Density 0.136%

    No Known Activations