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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or the existence of elements within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    colo
    -0.15
    .scalablytyped
    -0.14
    ero
    -0.14
    lace
    -0.14
    atis
    -0.14
    vero
    -0.14
    osto
    -0.13
    ä¸ģ
    -0.13
    orce
    -0.13
    ãĥŃãĥ¼
    -0.13
    POSITIVE LOGITS
    /use
    0.18
     two
    0.16
     hier
    0.15
     question
    0.15
     separ
    0.15
     existing
    0.15
     sop
    0.15
     exert
    0.15
     Jord
    0.15
    İ·
    0.14
    Act Density 0.038%

    No Known Activations