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

    Neuronpedia

    INDEX
    Explanations

    patterns of habitual actions or routines

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

    usual and routine events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Offisielt
    -0.56
     universelle
    -0.52
     proprement
    -0.48
     ſche
    -0.47
     industrielle
    -0.46
    InputTagHelper
    -0.46
     ujednoznacz
    -0.46
     שוליים
    -0.45
     pédagogique
    -0.43
    reness
    -0.43
    POSITIVE LOGITS
     habitual
    0.53
     usual
    0.46
     routine
    0.44
     habitually
    0.43
    いつもの
    0.41
    usual
    0.41
     regular
    0.40
     rotina
    0.39
    平常
    0.38
     привы
    0.38
    Act Density 0.029%

    No Known Activations