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

    Neuronpedia

    INDEX
    Explanations

    constructs that indicate a formal or structural relationship in texts, particularly focusing on connections and reference points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asso
    -0.15
    InParameter
    -0.15
    isko
    -0.14
    keley
    -0.14
    onen
    -0.14
    /epl
    -0.14
    mland
    -0.14
    βε
    -0.14
    åł¡
    -0.14
    _Tis
    -0.14
    POSITIVE LOGITS
    ãģļ
    0.15
     cre
    0.15
    ventus
    0.14
    eselect
    0.14
    ERP
    0.14
     Cre
    0.14
     ford
    0.14
    \<
    0.13
    bff
    0.13
    blocked
    0.13
    Act Density 0.004%

    No Known Activations