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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements of fact or opinion, particularly those introduced by "that" or "having said."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouz
    -0.15
    illez
    -0.14
     Coverage
    -0.14
    uir
    -0.14
    lish
    -0.14
    IGHL
    -0.14
     (_,
    -0.14
    ayo
    -0.14
    upro
    -0.13
    upy
    -0.13
    POSITIVE LOGITS
    éĥİ
    0.17
     aside
    0.17
    etheless
    0.17
    unders
    0.16
     nonetheless
    0.15
    ahlen
    0.15
    ãģĹãģŁãĤī
    0.14
    obe
    0.14
    eral
    0.14
     nevertheless
    0.14
    Act Density 0.019%

    No Known Activations