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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and other connecting phrases in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.18
     konkrét
    -0.17
     Astroph
    -0.14
    cxx
    -0.14
    uko
    -0.14
    çī§
    -0.14
    Ø·ÙĦ
    -0.14
    ne
    -0.13
    stm
    -0.13
    upa
    -0.13
    POSITIVE LOGITS
    /or
    0.17
    rogen
    0.16
    amba
    0.15
     defer
    0.14
    643
    0.14
     Ashton
    0.14
    omo
    0.14
    ÑģÑĤÑĢов
    0.13
    quot
    0.13
    cz
    0.13
    Act Density 0.139%

    No Known Activations