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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intl
    -0.18
    Ïģή
    -0.17
    好ãģį
    -0.15
    istine
    -0.14
    akan
    -0.14
    nech
    -0.14
    agus
    -0.14
    аза
    -0.13
    -0.13
     Antoine
    -0.13
    POSITIVE LOGITS
    ung
    0.17
     Astroph
    0.15
    trace
    0.14
     ort
    0.14
    Hdr
    0.14
     colle
    0.14
    UNG
    0.13
    äº
    0.13
    ender
    0.13
     strain
    0.13
    Act Density 0.012%

    No Known Activations