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

    Neuronpedia

    INDEX
    Explanations

    phrases related to connections and relationships within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĢģå°ı
    -0.16
    (The
    -0.15
    acci
    -0.14
    sdale
    -0.14
    wang
    -0.14
    ippy
    -0.14
    wyn
    -0.14
    ãĢģé«ĺ
    -0.13
    its
    -0.13
    iets
    -0.13
    POSITIVE LOGITS
     th
    0.29
     ther
    0.24
     thee
    0.23
     t
    0.23
     te
    0.22
     thr
    0.22
     tile
    0.22
     tho
    0.21
     tl
    0.21
     he
    0.21
    Act Density 0.045%

    No Known Activations