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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that describe positive outcomes from medical treatments, personal hardships and athletic performance

    oai_token-act-pair · gemini-2.0-flash

    references to specific concepts or identifiers

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     this
    -1.41
    this
    -1.00
     этого
    -0.84
     questa
    -0.78
    這個
    -0.77
     resourceCulture
    -0.75
     THIS
    -0.75
     the
    -0.74
     dieses
    -0.73
     этой
    -0.73
    POSITIVE LOGITS
     These
    0.65
    These
    0.60
    เหล
    0.59
    这些
    0.53
    ándolos
    0.52
    これらの
    0.52
    這些
    0.50
    どれも
    0.48
     Olympedia
    0.47
    ModelSerializer
    0.47
    Act Density 5.827%

    No Known Activations