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

    Neuronpedia

    INDEX
    Explanations

    numerical values denoting locations or quantities

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values related to time and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.94
    alid
    -0.93
    gotten
    -0.86
    bara
    -0.84
    stood
    -0.84
    bid
    -0.82
    olic
    -0.82
    eki
    -0.81
    unal
    -0.79
    ouri
    -0.79
    POSITIVE LOGITS
    mAh
    1.20
     MHz
    1.05
    MHz
    0.93
     rpm
    0.84
     Hz
    0.83
     msec
    0.81
    é¾įåĸļ士
    0.81
     kcal
    0.81
     watts
    0.80
     NOTICE
    0.77
    Act Density 0.037%

    No Known Activations