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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to various topics such as geography, politics, and popular culture

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.97
     constitu
    -0.92
    piece
    -0.91
    PDATE
    -0.88
     Scrolls
    -0.87
     referen
    -0.86
    kov
    -0.83
     vide
    -0.80
    JECT
    -0.80
    FontSize
    -0.79
    POSITIVE LOGITS
    puff
    0.91
    forth
    0.91
    enment
    0.90
     Fors
    0.85
    oling
    0.84
    loe
    0.84
    raft
    0.81
    rays
    0.81
    arre
    0.80
    furt
    0.80
    Act Density 2.537%

    No Known Activations