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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe methods or approaches

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

    "way"

    np_acts-logits-general · gemini-2.0-flash

    way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -1.06
    Datuak
    -0.95
    VersionUID
    -0.93
    хьтан
    -0.92
     nakalista
    -0.91
     Mahmud
    -0.89
    TestingModule
    -0.88
     transférez
    -0.88
    XMLSchema
    -0.87
    вгений
    -0.86
    POSITIVE LOGITS
     Way
    1.48
     WAY
    1.45
    Way
    1.35
     way
    1.33
    way
    1.27
     ways
    1.20
    WAY
    1.19
     Ways
    1.17
     WAYS
    1.09
    Ways
    1.06
    Act Density 0.089%

    No Known Activations