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

    Neuronpedia

    INDEX
    Explanations

    references to environmental initiatives or sustainability concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tk
    -0.19
    lescope
    -0.17
    ts
    -0.17
    gnore
    -0.16
    dust
    -0.16
    cket
    -0.15
    erah
    -0.15
    cz
    -0.15
    cum
    -0.15
    tractive
    -0.15
    POSITIVE LOGITS
    ery
    0.38
    peace
    0.33
    wich
    0.29
    belt
    0.29
    est
    0.28
    houses
    0.27
    wald
    0.27
    washing
    0.27
    backs
    0.26
    field
    0.26
    Act Density 0.028%

    No Known Activations