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

    Neuronpedia

    INDEX
    Explanations

    occurrences of prepositions and conjunctions that indicate relationships within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸įåŃĺåľ¨
    -0.15
    lez
    -0.15
    erald
    -0.14
    asca
    -0.14
     POLL
    -0.14
    ãĥ¼ãĤ¹ãĥĪ
    -0.14
     McConnell
    -0.14
    enz
    -0.14
    ncia
    -0.13
    åĭĴ
    -0.13
    POSITIVE LOGITS
     bit
    0.16
    nej
    0.16
    oment
    0.14
    ross
    0.14
    _bit
    0.14
    lab
    0.14
    426
    0.14
    üs
    0.14
    wand
    0.13
    æĦı
    0.13
    Act Density 0.046%

    No Known Activations