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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their connections in relation to subjects and objects within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.14
    zcze
    -0.13
     ways
    -0.13
    }elseif
    -0.13
     verr
    -0.12
    onde
    -0.12
    Ïħν
    -0.12
    zano
    -0.12
    EventListener
    -0.12
    ons
    -0.12
    POSITIVE LOGITS
    人ãģ¯
    0.20
    ï¼īãģ¯
    0.18
    åŃIJãģ¯
    0.18
     ìĤ¬ëŀĮìĿĢ
    0.16
    ANNOT
    0.15
    this
    0.14
    anj
    0.14
     ÑįÑĤого
    0.14
     ìĿ´ë¥¼
    0.14
     же
    0.14
    Act Density 0.720%

    No Known Activations