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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data and financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     looph
    -0.66
    ãĥĥãĤ¯
    -0.62
    ortment
    -0.60
    abet
    -0.56
    ãĥı
    -0.54
    ibur
    -0.52
     welf
    -0.50
    \">
    -0.49
    WithNo
    -0.48
    icut
    -0.48
    POSITIVE LOGITS
    ?,
    1.03
    ,...
    0.94
     requires
    0.90
    !,
    0.88
     becomes
    0.84
     seems
    0.84
     entails
    0.82
     resides
    0.81
     ensures
    0.81
     reveals
    0.80
    Act Density 0.722%

    No Known Activations