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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to the second person, emphasizing engagement with the reader or listener

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

    you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.64
     indígen
    -0.60
    rungsseite
    -0.60
     Redaktion
    -0.56
    protetor
    -0.55
     Monfieur
    -0.55
     deportivas
    -0.54
    IBLIO
    -0.54
     financeira
    -0.54
    Билгалдахарш
    -0.53
    POSITIVE LOGITS
    You
    0.35
     You
    0.34
    epam
    0.34
    Op
    0.32
     Your
    0.32
    copg
    0.32
     you
    0.31
    your
    0.31
     Op
    0.30
    Your
    0.30
    Act Density 0.040%

    No Known Activations