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

    Neuronpedia

    INDEX
    Explanations

    pronouns and words related to personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.68
    ValueStyle
    -0.62
    DockStyle
    -0.60
     interesados
    -0.60
     נוסף
    -0.58
     kautta
    -0.58
    MergeFrom
    -0.56
     aikaa
    -0.56
     doccia
    -0.55
     sveta
    -0.52
    POSITIVE LOGITS
     own
    1.46
    Their
    1.02
    Votre
    1.01
     their
    1.00
     ihrem
    0.99
     seu
    0.98
     swoje
    0.98
     your
    0.96
     ihrer
    0.96
    自己的
    0.96
    Act Density 0.052%

    No Known Activations