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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and experiences

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

    personal or reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.69
     betweenstory
    -0.52
    NameInMap
    -0.50
     ourselves
    -0.49
     själva
    -0.47
     lives
    -0.45
    السكان
    -0.44
     our
    -0.43
     nostre
    -0.43
     intptr
    -0.41
    POSITIVE LOGITS
     myself
    0.69
    himself
    0.59
    myself
    0.59
     himself
    0.58
    MLLoader
    0.56
    UserScript
    0.56
     sám
    0.55
     Myself
    0.52
     personalmente
    0.49
    Myself
    0.48
    Act Density 0.234%

    No Known Activations