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

    Neuronpedia

    INDEX
    Explanations

    instances of commas and conjunctions connecting phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alth
    -0.14
    hcp
    -0.14
    寿
    -0.14
     pairwise
    -0.14
    hk
    -0.14
    anten
    -0.13
    алÑİ
    -0.13
    avier
    -0.13
     Benson
    -0.13
    illy
    -0.13
    POSITIVE LOGITS
    äd
    0.18
    @qq
    0.17
     then
    0.15
    lero
    0.15
    ìĭ¸
    0.15
    rome
    0.15
     second
    0.15
    conds
    0.15
    §Ãĥ
    0.15
    endl
    0.14
    Act Density 0.061%

    No Known Activations