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

    Neuronpedia

    INDEX
    Explanations

    terms related to improvement or enhancement processes

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

    improving or clarifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getChildAt
    -0.54
    bootstrapcdn
    -0.54
    ImageContext
    -0.53
    __((
    -0.52
     Joey
    -0.50
     المعيارى
    -0.49
    stdc
    -0.48
     strto
    -0.48
     mur
    -0.48
    adaptiveStyles
    -0.48
    POSITIVE LOGITS
     refine
    1.71
     refinement
    1.66
     refined
    1.60
    refined
    1.48
    refine
    1.46
     Refined
    1.41
     refining
    1.41
     refinements
    1.40
    Refinement
    1.33
     Refin
    1.14
    Act Density 0.004%

    No Known Activations