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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and software

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and places, along with certain significant words related to entities or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.81
    ĨĴ
    -0.74
     carbohyd
    -0.74
     oun
    -0.73
    ITNESS
    -0.73
    ĸļ
    -0.70
     skelet
    -0.69
    ++++
    -0.67
    SpaceEngineers
    -0.67
    BOOK
    -0.67
    POSITIVE LOGITS
    beck
    0.81
    ette
    0.68
    arian
    0.67
    uk
    0.67
    ny
    0.66
    tein
    0.64
    belt
    0.64
    igi
    0.63
    uous
    0.63
    iger
    0.62
    Act Density 0.405%

    No Known Activations