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

    Neuronpedia

    INDEX
    Explanations

    references to software bugs being fixed

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.93
    rained
    -0.81
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
    worth
    -0.72
    mop
    -0.71
    zos
    -0.69
    whatever
    -0.68
    arious
    -0.67
    âĪĴ
    -0.67
    Pros
    -0.66
    POSITIVE LOGITS
     typo
    1.03
     bug
    0.95
     Fixes
    0.87
     erroneous
    0.81
     shader
    0.77
     localization
    0.74
     tooltip
    0.74
     UI
    0.74
     errone
    0.73
     exploit
    0.72
    Act Density 0.089%

    No Known Activations