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

    Neuronpedia

    INDEX
    Explanations

    references to tables in written documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.17
    elas
    -0.16
    im
    -0.16
    seller
    -0.16
    rix
    -0.15
    elan
    -0.15
    ri
    -0.15
    rians
    -0.15
    fall
    -0.15
    ening
    -0.14
    POSITIVE LOGITS
    cloth
    0.28
    aus
    0.25
    aux
    0.24
    cth
    0.22
    au
    0.21
    clo
    0.20
    LayoutPanel
    0.19
    asic
    0.19
    oenix
    0.18
    ten
    0.18
    Act Density 0.028%

    No Known Activations