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

    Neuronpedia

    INDEX
    Explanations

    negative qualifiers and phrases that indicate exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ******/
    -0.16
    (UnityEngine
    -0.15
     Pent
    -0.15
    inkel
    -0.14
    ause
    -0.14
    px
    -0.14
    ovol
    -0.14
    undry
    -0.14
    iteur
    -0.13
    ught
    -0.13
    POSITIVE LOGITS
    withstanding
    0.17
    tingham
    0.17
    ritz
    0.17
    ché
    0.16
    258
    0.16
     Sas
    0.15
    ewriter
    0.15
    ساÙĨÛĮ
    0.15
    ices
    0.15
    Uvs
    0.15
    Act Density 0.036%

    No Known Activations