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

    Neuronpedia

    INDEX
    Explanations

    words related to programming and technology

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" and the presence of nouns following it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ['
    -0.83
    EMA
    -0.82
    Versions
    -0.79
    ocity
    -0.78
    uploads
    -0.78
     Izan
    -0.71
    iments
    -0.70
    Shape
    -0.70
    Īè
    -0.70
    Alien
    -0.70
    POSITIVE LOGITS
     versatile
    0.98
     powerful
    0.95
     unique
    0.94
     recurring
    0.91
     rare
    0.91
     fictional
    0.90
     small
    0.90
     combination
    0.89
     fascinating
    0.87
     standalone
    0.87
    Act Density 0.143%

    No Known Activations