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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inquiry or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing inquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.53
    -0.40
     Благодаря
    -0.37
     fhort
    -0.37
     Diſ
    -0.35
    jmniej
    -0.35
    MessageTagHelper
    -0.34
    jbl
    -0.34
     CreateTagHelper
    -0.33
     drap
    -0.33
    POSITIVE LOGITS
     question
    0.77
     wondering
    0.73
     wondered
    0.72
     questions
    0.72
     QUESTIONS
    0.69
    Questions
    0.69
    疑問
    0.69
     wonder
    0.67
     Questions
    0.67
     pregunto
    0.66
    Act Density 0.167%

    No Known Activations