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

    Neuronpedia

    INDEX
    Explanations

    references to bugs and issues in software or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    easy
    -0.45
     easy
    -0.44
     str
    -0.42
     nên
    -0.41
    str
    -0.40
     Therefore
    -0.38
    onski
    -0.37
    Easy
    -0.36
     ведь
    -0.36
     reste
    -0.36
    POSITIVE LOGITS
     bug
    1.36
    bug
    1.08
    Bug
    1.07
     bugs
    1.05
     Bug
    1.04
     BUG
    0.99
    BUG
    0.95
    bugs
    0.89
    bugging
    0.87
     StatefulWidget
    0.86
    Act Density 1.548%

    No Known Activations