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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and personal reflections

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

    after "then"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.72
     autorytatywna
    -0.57
     '\\;'
    -0.54
    ernoo
    -0.50
     jScrollPane
    -0.48
    出版年
    -0.48
    tagHelperRunner
    -0.46
    
    -0.46
    Derbyniad
    -0.44
     __
    -0.44
    POSITIVE LOGITS
     Then
    0.63
    Then
    0.57
     then
    0.56
     THEN
    0.55
    then
    0.54
     entonces
    0.51
     sitten
    0.49
     dann
    0.49
     puis
    0.40
     sonra
    0.40
    Act Density 0.129%

    No Known Activations