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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of product features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advantages and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Negro
    -0.78
    fell
    -0.71
    ogi
    -0.69
     Freddie
    -0.68
    worn
    -0.67
    Episode
    -0.67
     Tot
    -0.67
     Words
    -0.66
    gian
    -0.66
     occupations
    -0.65
    POSITIVE LOGITS
     versatility
    1.17
     efficient
    1.09
     durability
    1.08
     inexpensive
    1.07
     versatile
    1.06
    efficiency
    1.00
     simplicity
    0.99
     scalable
    0.98
     environmentally
    0.98
    efficient
    0.97
    Act Density 0.682%

    No Known Activations