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

    Neuronpedia

    INDEX
    Explanations

    references to personal ownership or individual experiences

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

    Following the word "own"

    np_acts-logits-general · gemini-2.0-flash

    own followed by personal attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     novità
    -0.65
     istrinya
    -0.60
     partenza
    -0.59
     samlet
    -0.56
     réfugiés
    -0.56
     partea
    -0.54
     sposa
    -0.53
     vaisselle
    -0.53
     deacon
    -0.53
    DockStyle
    -0.53
    POSITIVE LOGITS
     personal
    0.92
     OWN
    0.85
     own
    0.82
     sendiri
    0.79
     unique
    0.78
    ERSHIP
    0.74
     Own
    0.74
    ership
    0.71
    ſelf
    0.69
     particular
    0.68
    Act Density 0.063%

    No Known Activations