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

    Neuronpedia

    INDEX
    Explanations

    body parts

    oai_token-act-pair · gpt-3.5-turbo

    elements related to action and consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    of
    -0.71
     of
    -0.58
    Of
    -0.56
    oÄŁ
    -0.56
    ozy
    -0.55
    oft
    -0.53
    hetically
    -0.51
    comed
    -0.50
    zsche
    -0.50
    etter
    -0.50
    POSITIVE LOGITS
     Units
    0.49
     provinces
    0.47
     GDP
    0.46
     cubic
    0.46
    steamapps
    0.45
    ().
    0.45
     railways
    0.45
     Yards
    0.44
     999
    0.44
     hectares
    0.44
    Act Density 0.980%

    No Known Activations