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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns referring to the self

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

    reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.55
     Normdatei
    -0.54
     дописавши
    -0.52
    actéristi
    -0.50
     pleaſure
    -0.48
    glLoad
    -0.48
     صفحۀ
    -0.48
    ########.
    -0.47
     ſta
    -0.47
    Pozri
    -0.47
    POSITIVE LOGITS
     themselves
    0.73
    themselves
    0.68
     yourself
    0.65
     herself
    0.65
     ourselves
    0.57
    itself
    0.57
     Yourself
    0.57
     oneself
    0.56
    herself
    0.56
     Itself
    0.54
    Act Density 0.014%

    No Known Activations