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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conflict or disagreement in a legal or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -1.00
     utafitiHapana
    -0.85
    NUMX
    -0.80
     }</
    -0.78
    yship
    -0.76
    etheless
    -0.76
     désolés
    -0.75
    UATION
    -0.75
    ⎓
    -0.75
    expandindo
    -0.74
    POSITIVE LOGITS
    ,
    0.54
    *
    0.52
     ModelExpression
    0.50
    .
    0.50
    invokeLater
    0.47
    LookAnd
    0.46
    -
    0.46
    ↵↵
    0.45
    /
    0.45
    \
    0.45
    Act Density 2.438%

    No Known Activations