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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly semicolons and periods in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Z
    -0.52
    -
    -0.44
     is
    -0.44
     response
    -0.44
     sub
    -0.43
    (
    -0.43
     same
    -0.42
     part
    -0.42
     “
    -0.42
     hành
    -0.42
    POSITIVE LOGITS
    PerformLayout
    0.97
     متعلقه
    0.95
    InjectAttribute
    0.88
     purpoſe
    0.85
     raiſ
    0.83
     pleaſure
    0.83
     poffible
    0.82
    ])));
    0.82
     myſelf
    0.82
    ]));
    0.81
    Act Density 0.005%

    No Known Activations