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

    Neuronpedia

    INDEX
    Explanations

    lists or recommendations related to various topics/tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to tips and suggestions for various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yards
    -0.69
    lihood
    -0.66
    ufact
    -0.66
    aughter
    -0.66
    plet
    -0.64
    yss
    -0.63
    ONT
    -0.62
    oubted
    -0.62
    eals
    -0.61
    rama
    -0.61
    POSITIVE LOGITS
     tips
    1.04
    tips
    0.97
    Tips
    0.96
     Tips
    0.93
    Tip
    0.90
    tip
    0.88
    heet
    0.87
     guide
    0.82
     glean
    0.80
     tip
    0.79
    Act Density 0.042%

    No Known Activations