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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()")
    -0.79
    )";
    -0.74
    )++;
    -0.73
     "];
    -0.70
    PARTIC
    -0.67
    ApplicationTests
    -0.66
    "}")
    -0.65
    )['
    -0.65
     referenties
    -0.64
    )*/
    -0.64
    POSITIVE LOGITS
     spend
    0.90
     spent
    0.81
    mit
    0.77
    escape
    0.76
     Spent
    0.75
    Spent
    0.74
    Spend
    0.74
    Escape
    0.70
    spent
    0.70
     spends
    0.69
    Act Density 0.116%

    No Known Activations