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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "speaking" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ium
    -0.14
     millennium
    -0.14
    TL
    -0.14
    se
    -0.13
    ester
    -0.13
    iosis
    -0.13
    pmat
    -0.13
    人æ°Ĺ
    -0.13
    Ctrls
    -0.13
    ike
    -0.13
    POSITIVE LOGITS
    enia
    0.16
    ην
    0.14
    CKET
    0.14
    BV
    0.14
    udiant
    0.14
    endet
    0.13
    odash
    0.13
    richt
    0.13
    dog
    0.13
    icina
    0.13
    Act Density 0.009%

    No Known Activations