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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns and expressions of self-reference

    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
    Parcelize
    -0.49
    pecabe
    -0.49
     pulito
    -0.43
    󠁢
    -0.42
     Infór
    -0.42
     propuesto
    -0.41
     derra
    -0.40
    ientras
    -0.40
    archiwizowane
    -0.40
     tartalomajánló
    -0.40
    POSITIVE LOGITS
    IVEREF
    0.50
    الحياه
    0.45
     parapet
    0.42
     <<<<<<<<<<<<<<
    0.40
     zich
    0.39
    complexContent
    0.39
    kijken
    0.39
    webElement
    0.39
    Zeneca
    0.38
    Aura
    0.38
    Act Density 0.022%

    No Known Activations