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

    Neuronpedia

    INDEX
    Explanations

    phrases that express direct address or engagement with the reader or listener

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

    second person pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     größte
    -0.46
     plegable
    -0.45
     Cientí
    -0.43
     Tatsache
    -0.43
     polecam
    -0.41
     satisfecho
    -0.41
     środków
    -0.39
     sítio
    -0.39
     isolado
    -0.37
    各样的
    -0.36
    POSITIVE LOGITS
    YOU
    0.72
     YOU
    0.68
    you
    0.68
     Numerade
    0.66
    yourself
    0.63
    🫵
    0.62
    rungsseite
    0.61
    webElementXpaths
    0.60
    oredCriteria
    0.60
    You
    0.60
    Act Density 0.038%

    No Known Activations