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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the purpose or intended use of information or actions

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

    for the purpose of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.61
     Exacts
    -0.54
    AutoScale
    -0.45
    rungsseite
    -0.41
     Exactos
    -0.41
    EndGlobalSection
    -0.40
    Välislingid
    -0.40
    Choisissez
    -0.39
    پیوند
    -0.39
    glLoadIdentity
    -0.38
    POSITIVE LOGITS
     purpose
    1.02
     Purpose
    0.97
     purposes
    0.92
    Purpose
    0.92
     Purposes
    0.90
     PURPOSE
    0.85
    purpose
    0.84
    PURPOSE
    0.81
    purposes
    0.79
    用途
    0.78
    Act Density 0.299%

    No Known Activations