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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate product descriptions or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Filmografia
    -0.53
    ScopeManager
    -0.50
     resourceCulture
    -0.50
    windowFixed
    -0.49
     ब्रेकडाउन
    -0.49
     bandits
    -0.49
     समीक्षाओं
    -0.48
     bandit
    -0.48
     Infór
    -0.47
     Meksi
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.56
    0.49
     Features
    0.42
     features
    0.40
     [*]
    0.35
     disfruta
    0.35
    Features
    0.35
     featuring
    0.34
    AsUp
    0.34
     dessutom
    0.34
    Act Density 0.179%

    No Known Activations