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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating physical movement or actions in various contexts

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

    movement verbs preceding directional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.47
    AddHtmlAttribute
    -0.44
    oneofs
    -0.43
     endblock
    -0.42
    findpost
    -0.41
    Архівовано
    -0.41
    aarrggbb
    -0.41
    wnętr
    -0.41
    muerzo
    -0.41
     óptica
    -0.40
    POSITIVE LOGITS
     Fahrt
    0.45
     trek
    0.44
     travelling
    0.43
     ride
    0.42
     đi
    0.42
    trip
    0.42
     chạy
    0.42
     walk
    0.41
     trip
    0.41
     رفت
    0.41
    Act Density 0.238%

    No Known Activations