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

    Neuronpedia

    INDEX
    Explanations

    concepts and elements related to guidance and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĢ¦↵
    -0.15
    âĢ¦↵
    -0.15
    (
    -0.15
    bers
    -0.14
    oto
    -0.14
    _
    -0.14
    oul
    -0.14
    ochen
    -0.14
    Z
    -0.13
    ↵
    -0.13
    POSITIVE LOGITS
    'gc
    0.17
    LAR
    0.15
    TokenType
    0.14
    aylight
    0.14
     EXEMPLARY
    0.14
    æ®
    0.14
    /testify
    0.13
    лиÑĪком
    0.13
    ernaut
    0.13
    .Loader
    0.13
    Act Density 0.031%

    No Known Activations