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

    Neuronpedia

    INDEX
    Explanations

    terms related to variability or change, particularly in physical or quantitative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    castle
    -0.19
    play
    -0.18
    elson
    -0.17
    ÃŃf
    -0.15
    lington
    -0.15
    pel
    -0.15
    alth
    -0.15
    etta
    -0.14
    acho
    -0.14
    EDITOR
    -0.14
    POSITIVE LOGITS
    chart
    0.20
    onium
    0.18
    uating
    0.16
    uation
    0.16
    ugh
    0.16
    íĻľ
    0.16
    arez
    0.16
    ange
    0.15
    orian
    0.15
    oxetine
    0.15
    Act Density 0.048%

    No Known Activations