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

    Neuronpedia

    INDEX
    Explanations

    terms related to data extraction and analysis methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    referrer
    -0.15
    arget
    -0.15
    apo
    -0.15
     halk
    -0.15
     stos
    -0.14
    ":[{"
    -0.14
    icens
    -0.14
    .dest
    -0.13
    -feedback
    -0.13
    Multiplicity
    -0.13
    POSITIVE LOGITS
     feature
    0.36
     features
    0.33
     Feature
    0.31
    feature
    0.31
     Features
    0.29
    features
    0.28
    Feature
    0.28
    -feature
    0.28
    Features
    0.27
    /features
    0.26
    Act Density 0.023%

    No Known Activations