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

    Neuronpedia

    INDEX
    Explanations

    segments of code related to expected values in tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     téléphonique
    -0.52
     kond
    -0.46
    endphp
    -0.46
    trise
    -0.46
    istra
    -0.45
    ̀nh
    -0.45
    Alla
    -0.44
    ransition
    -0.44
     valent
    -0.44
     setuptools
    -0.44
    POSITIVE LOGITS
                
    0.78
    省市镇
    0.64
                 
    0.62
    IsMutable
    0.61
     ویکی‌پدیای
    0.57
    inston
    0.56
     Enix
    0.56
    0.54
     ninth
    0.54
    tagHelperRunner
    0.54
    Act Density 0.103%

    No Known Activations