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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to specific entities or topics, possibly related to legal, business, or technical matters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.97
    anwhile
    -0.79
    ierrez
    -0.64
     eleph
    -0.62
    hement
    -0.62
     dummy
    -0.61
    mble
    -0.60
    pherd
    -0.59
     referen
    -0.59
    gomery
    -0.58
    POSITIVE LOGITS
    Coin
    0.90
    Wiki
    0.86
    coin
    0.82
    Game
    0.80
    Fest
    0.79
    Forge
    0.77
    RPG
    0.76
    DB
    0.75
    Py
    0.73
    Hack
    0.73
    Act Density 0.469%

    No Known Activations