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

    Neuronpedia

    INDEX
    Explanations

    web-related terms and website functionalities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.71
    t
    -0.69
    tons
    -0.67
    cards
    -0.66
    wise
    -0.66
    scale
    -0.65
    points
    -0.65
    Ö¼
    -0.65
     WATCHED
    -0.64
    TY
    -0.64
    POSITIVE LOGITS
    uthor
    1.34
    ñ
    1.31
    vel
    1.23
    BILITY
    1.22
    pling
    1.16
    qua
    1.14
    plin
    1.12
    ï
    1.12
    ption
    1.10
    ples
    1.06
    Act Density 1.727%

    No Known Activations