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

    Neuronpedia

    INDEX
    Explanations

    terms related to bandwidth and throughput

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleasure
    -1.73
     git
    -1.59
    ureus
    -1.58
     blessing
    -1.43
    cca
    -1.43
     Calendar
    -1.41
     help
    -1.40
    usepackage
    -1.40
     whom
    -1.39
    woke
    -1.39
    POSITIVE LOGITS
    worth
    1.97
    gap
    1.70
    wise
    1.70
    ontal
    1.60
    block
    1.55
    neutral
    1.55
     spectrum
    1.53
    "}](#
    1.48
    furt
    1.45
    worthy
    1.43
    Act Density 0.021%

    No Known Activations