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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and variations indicating obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ever
    -0.58
    슷
    -0.57
     deines
    -0.54
    iesto
    -0.53
     long
    -0.53
     solution
    -0.53
    DataTo
    -0.51
    TimeTo
    -0.51
    EndOf
    -0.51
     local
    -0.50
    POSITIVE LOGITS
     kann
    1.24
     können
    1.18
     wird
    1.12
     haben
    1.08
     müssen
    0.97
     werden
    0.96
     hatte
    0.91
     gibt
    0.91
     wurde
    0.89
     heeft
    0.86
    Act Density 0.015%

    No Known Activations