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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to confirmations or affirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Singer
    -0.15
    zet
    -0.14
    try
    -0.14
    aps
    -0.14
     paramName
    -0.14
     Santana
    -0.14
    koa
    -0.14
     Magick
    -0.14
    _warnings
    -0.14
    ær
    -0.14
    POSITIVE LOGITS
    atory
    0.18
    atively
    0.17
     existence
    0.17
    ainty
    0.16
     rằng
    0.15
    amen
    0.15
    ably
    0.15
     fact
    0.14
    bindValue
    0.14
    atorio
    0.14
    Act Density 0.068%

    No Known Activations