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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "we" and variations of "there" and "one" in various contexts

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

    Sentences starting with "We"

    np_acts-logits-general · gemini-2.0-flash

    we present/propose/proceed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.71
     Roskov
    -0.56
     bezeichneter
    -0.52
    principalTable
    -0.47
     Winaray
    -0.42
    WebElementEntity
    -0.41
    Geplaatst
    -0.41
     незавершена
    -0.39
     Мексичка
    -0.38
     дописавши
    -0.38
    POSITIVE LOGITS
    Planner
    0.52
    sila
    0.50
    Cos
    0.50
    literature
    0.50
    lists
    0.50
     Cana
    0.49
    Liste
    0.49
    Decl
    0.48
    cosp
    0.48
    уда
    0.48
    Act Density 0.499%

    No Known Activations