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

    Neuronpedia

    INDEX
    Explanations

    commands and references related to cleaning and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gt
    -0.17
    amus
    -0.17
    ti
    -0.16
    uml
    -0.15
    ted
    -0.15
    hl
    -0.15
    -employed
    -0.15
    ÑĢеÑĪ
    -0.15
    alth
    -0.15
    unts
    -0.14
    POSITIVE LOGITS
    liness
    0.29
    -clean
    0.23
     slate
    0.22
    (clean
    0.20
    .clean
    0.20
    est
    0.19
     thoroughly
    0.18
     Clean
    0.17
    -cut
    0.17
     clean
    0.17
    Act Density 0.037%

    No Known Activations