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

    Neuronpedia

    INDEX
    Explanations

    words related to exclusions or removals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exion
    -0.18
    orous
    -0.17
    ffects
    -0.17
    lsru
    -0.16
    -esque
    -0.16
    cot
    -0.15
    lements
    -0.15
    /editor
    -0.15
    /email
    -0.15
    lement
    -0.15
    POSITIVE LOGITS
    /import
    0.16
    udem
    0.16
    ively
    0.15
    plorer
    0.15
     coli
    0.15
    inction
    0.15
     ÐĶеÑĢжав
    0.15
    piry
    0.14
    à¤ľà¤¨
    0.14
    ãĥ³ãĥIJ
    0.14
    Act Density 0.178%

    No Known Activations