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

    Neuronpedia

    INDEX
    Explanations

    references to puzzles or puzzle-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALER
    -0.15
    üzel
    -0.15
    andles
    -0.15
    icine
    -0.15
     hers
    -0.15
    lung
    -0.14
    ingle
    -0.14
     sert
    -0.14
    iska
    -0.14
    linger
    -0.14
    POSITIVE LOGITS
    bum
    0.14
    TU
    0.14
    osity
    0.14
     inherit
    0.14
    AYOUT
    0.13
    .outer
    0.13
    HS
    0.13
    aro
    0.13
    arium
    0.13
     swings
    0.13
    Act Density 0.004%

    No Known Activations