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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "Tak" and its variations, which seem to be frequent in the context of certain names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ece
    -0.16
    MDB
    -0.16
    HCI
    -0.15
     Dest
    -0.15
    olas
    -0.15
    antly
    -0.15
    cheid
    -0.14
    eck
    -0.14
     pret
    -0.14
    hci
    -0.14
    POSITIVE LOGITS
    ashi
    0.22
    acs
    0.19
    论
    0.18
    aways
    0.18
    à¤Łà¤ķ
    0.17
    eniable
    0.17
    EDA
    0.17
    ACS
    0.17
    eturn
    0.16
    éo
    0.16
    Act Density 0.007%

    No Known Activations