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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing personal feelings and reactions

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

    to my surprise or detriment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Discipline
    -0.45
    ArgumentParser
    -0.44
    học
    -0.43
    Soviet
    -0.42
     wanna
    -0.42
     gobernador
    -0.41
     Stoff
    -0.41
     russes
    -0.40
    enderror
    -0.40
    hombres
    -0.40
    POSITIVE LOGITS
     الحره
    0.52
    WriteTagHelper
    0.52
    SizeMode
    0.50
     hopefully
    0.49
     oprot
    0.49
     Савезне
    0.48
    TRAILING
    0.48
    HtmlAttribute
    0.47
     greatly
    0.47
    addPreferredGap
    0.47
    Act Density 0.030%

    No Known Activations