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

    Neuronpedia

    INDEX
    Explanations

    high-frequency function words and connectors that structure sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.17
    phies
    -0.16
    ucz
    -0.15
    argas
    -0.15
    ulet
    -0.15
     fetisch
    -0.14
    loi
    -0.14
    libs
    -0.14
    _COMPAT
    -0.14
    UGC
    -0.14
    POSITIVE LOGITS
    oup
    0.17
     quint
    0.15
    Y
    0.15
     Spe
    0.14
    ela
    0.14
     Tun
    0.14
     tun
    0.14
     instagram
    0.13
    ift
    0.13
     Att
    0.13
    Act Density 0.001%

    No Known Activations