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

    Neuronpedia

    INDEX
    Explanations

    concepts related to separation and distinct entities or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibraltar
    -0.15
    oday
    -0.15
    PTION
    -0.15
    ept
    -0.15
     Ferry
    -0.14
    aster
    -0.14
    lah
    -0.14
    otics
    -0.14
    structor
    -0.14
    acom
    -0.14
    POSITIVE LOGITS
     separate
    0.28
     Separate
    0.25
     separately
    0.23
     seperate
    0.23
     individual
    0.20
     оÑĤделÑĮ
    0.20
     separ
    0.20
     ayrı
    0.18
     distinct
    0.17
    çĭ¬ç«ĭ
    0.17
    Act Density 0.283%

    No Known Activations