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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns related to ownership and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     talking
    -0.52
     CIT
    -0.47
     والن
    -0.46
     cevap
    -0.45
    monta
    -0.45
    iega
    -0.45
    Пита
    -0.44
    IDLE
    -0.43
    SetTitle
    -0.43
    fraid
    -0.43
    POSITIVE LOGITS
    EDEFAULT
    0.84
    AddTagHelper
    0.80
    Искәрмәләр
    0.79
    expandindo
    0.78
    HasBeenSet
    0.74
    تقاوى
    0.70
    COUVER
    0.70
    DeleteBehavior
    0.70
    WithIOException
    0.70
     onCreateView
    0.70
    Act Density 0.180%

    No Known Activations