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

    Neuronpedia

    INDEX
    Explanations

    references to proposed solutions or approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BorderRadius
    -0.97
    WriteAttribute
    -0.85
    zieży
    -0.80
     Efq
    -0.80
     незавершена
    -0.79
    ]-->
    -0.79
     varandra
    -0.76
     craw
    -0.75
     RIPRODUZIONE
    -0.72
    BYTES
    -0.72
    POSITIVE LOGITS
     solutions
    2.13
     solution
    1.97
     Solutions
    1.91
     Solution
    1.86
    Solutions
    1.83
    Solution
    1.75
     SOLUTION
    1.72
    solutions
    1.69
    solution
    1.67
     SOLUTIONS
    1.64
    Act Density 0.084%

    No Known Activations