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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and quantitative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.75
    ngth
    -0.70
    dimension
    -0.70
    letters
    -0.68
    irie
    -0.68
    lished
    -0.68
    ournal
    -0.66
    ousands
    -0.65
    onge
    -0.64
    uesday
    -0.64
    POSITIVE LOGITS
     considering
    1.13
     huh
    0.86
     nonetheless
    0.81
     compared
    0.80
     anyway
    0.77
     eh
    0.73
     understatement
    0.71
     given
    0.71
    ADS
    0.69
    Sensor
    0.68
    Act Density 0.437%

    No Known Activations