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

    Neuronpedia

    INDEX
    Explanations

    words related to financial and economic discussions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pecially
    -0.74
    姫
    -0.71
    mi
    -0.71
    sbm
    -0.70
    mes
    -0.69
    adelphia
    -0.69
    byss
    -0.69
     dstg
    -0.69
    bes
    -0.68
    pots
    -0.67
    POSITIVE LOGITS
     doesn
    0.99
     nonetheless
    0.99
     differs
    0.92
     ignores
    0.92
     depends
    0.91
     hasn
    0.91
     nevertheless
    0.90
     doesnt
    0.88
     didn
    0.85
     overlook
    0.85
    Act Density 0.136%

    No Known Activations