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

    Neuronpedia

    INDEX
    Explanations

    references to financial figures and statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     radios
    -0.52
    ban
    -0.48
    hid
    -0.48
    lio
    -0.48
     censorship
    -0.47
    THING
    -0.46
    Hide
    -0.46
    ODY
    -0.46
     learns
    -0.46
     misunderstand
    -0.45
    POSITIVE LOGITS
    ngth
    0.69
     average
    0.66
     multiplied
    0.65
     averages
    0.64
    total
    0.63
     equivalent
    0.63
     compared
    0.62
     averaged
    0.62
    Total
    0.62
     TOTAL
    0.62
    Act Density 1.631%

    No Known Activations