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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and relationships in narrative or descriptive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     keinen
    -0.19
    Den
    -0.18
     Ihren
    -0.18
     kleinen
    -0.18
     unseren
    -0.18
     eigenen
    -0.17
     Den
    -0.17
     einen
    -0.17
    ниÑĨÑĥ
    -0.17
     seinen
    -0.16
    POSITIVE LOGITS
     es
    0.43
     die
    0.38
     das
    0.34
     sie
    0.30
    die
    0.28
     diese
    0.28
     dies
    0.24
    das
    0.23
    'es
    0.22
    _die
    0.22
    Act Density 0.026%

    No Known Activations