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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations within a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.72
     long
    -0.53
    ...
    -0.52
     much
    -0.51
     bu
    -0.51
    ↵↵
    -0.48
     //
    -0.48
    :
    -0.47
     |
    -0.46
     free
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.94
     فريبيس
    0.93
    RegressionTest
    0.90
     rhestr
    0.87
     تانيه
    0.87
     Theſe
    0.85
     الرياضيه
    0.84
    UserScript
    0.81
    帖最后由
    0.80
     &___
    0.79
    Act Density 2.097%

    No Known Activations