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

    Neuronpedia

    INDEX
    Explanations

    references to specific issues or problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sponges
    -0.84
     Rebekah
    -0.76
     Guay
    -0.74
     Meli
    -0.74
    mew
    -0.73
     otomatig
    -0.73
     sogni
    -0.72
    politan
    -0.72
     Hert
    -0.72
    BST
    -0.72
    POSITIVE LOGITS
     issues
    1.58
     Issues
    1.52
    Issues
    1.51
    issues
    1.49
     ISSUES
    1.43
     issue
    1.42
     ISSUE
    1.30
    ISSUES
    1.30
    issue
    1.30
    Issue
    1.27
    Act Density 0.078%

    No Known Activations