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

    Neuronpedia

    INDEX
    Explanations

    numerical ratings or scores in a standardized format

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behavi
    -0.80
     sustainability
    -0.77
     arson
    -0.74
     proactive
    -0.72
    etheless
    -0.71
     architectural
    -0.71
     salty
    -0.70
    ogether
    -0.70
     antidepress
    -0.70
     handwriting
    -0.69
    POSITIVE LOGITS
    99
    1.13
    00
    1.07
    jpg
    1.06
    jar
    1.04
    htm
    1.03
    5
    1.03
    75
    1.01
    html
    0.99
    0
    0.98
    05
    0.97
    Act Density 0.102%

    No Known Activations