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

    Neuronpedia

    INDEX
    Explanations

    words related to pride and self-esteem

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

    prides itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.55
    MMP
    -0.54
     FileWriter
    -0.52
    USSR
    -0.51
     שוליים
    -0.51
     MMP
    -0.50
     Jann
    -0.49
    ViewInit
    -0.49
    帖最后由
    -0.49
    cerpt
    -0.48
    POSITIVE LOGITS
     prides
    1.09
     pride
    1.04
    pride
    0.70
     orgullo
    0.69
     Pride
    0.59
    Pride
    0.57
     proudly
    0.54
     unggul
    0.52
     proudest
    0.52
     orgull
    0.51
    Act Density 0.001%

    No Known Activations