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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    had to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creen
    -0.36
     group
    -0.30
     caen
    -0.29
     zone
    -0.28
    之
    -0.27
    ParallelGroup
    -0.26
     оз
    -0.26
     auss
    -0.25
     toros
    -0.25
     program
    -0.25
    POSITIVE LOGITS
     fallu
    0.80
     terpaksa
    0.79
     пришлось
    0.79
     dovuto
    0.79
     musste
    0.73
     musia
    0.71
    лтемелер
    0.70
     Forced
    0.69
    Must
    0.69
    Forced
    0.68
    Act Density 0.061%

    No Known Activations