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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or manuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.80
     Kardash
    -0.80
    Kind
    -0.76
     poles
    -0.75
     saline
    -0.75
    Latin
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.73
    Quantity
    -0.72
     caucuses
    -0.71
    hift
    -0.71
    POSITIVE LOGITS
    /?
    1.35
     âĢº
    1.05
    /.
    1.00
    gmail
    0.94
    /_
    0.93
    /#
    0.91
    biz
    0.91
    /-
    0.89
    MpServer
    0.87
    /,
    0.87
    Act Density 0.183%

    No Known Activations