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

    Neuronpedia

    INDEX
    Explanations

    terms related to labeling and category identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Linux
    -0.18
    roe
    -0.17
    elves
    -0.17
    UMB
    -0.17
    urement
    -0.16
    falls
    -0.16
    umble
    -0.16
    andel
    -0.15
    croft
    -0.15
    IGHL
    -0.14
    POSITIVE LOGITS
    led
    0.32
    ings
    0.22
    /tag
    0.21
    icious
    0.20
    ValuePair
    0.18
    ging
    0.18
    ted
    0.17
    atories
    0.17
    /un
    0.17
    =label
    0.17
    Act Density 0.012%

    No Known Activations