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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions between features in datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audiovisuel
    -0.43
    akit
    -0.36
    fal
    -0.36
    omock
    -0.35
    ệm
    -0.35
    stdlib
    -0.35
    peritoneal
    -0.35
    tisone
    -0.35
    quila
    -0.34
    potamus
    -0.34
    POSITIVE LOGITS
     feature
    3.81
     Feature
    3.44
     features
    3.42
    feature
    3.34
    Feature
    3.33
     Features
    3.20
    features
    3.06
     FEATURE
    3.05
    Features
    3.02
     FEATURES
    2.94
    Act Density 0.681%

    No Known Activations