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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reasons for actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ettel
    -0.17
    ukan
    -0.15
    dust
    -0.15
     tube
    -0.14
    аÑĢаÑĤ
    -0.14
    ivery
    -0.14
    irst
    -0.14
    ĽĦ
    -0.14
    ilter
    -0.14
    ãģŀ
    -0.14
    POSITIVE LOGITS
    ataka
    0.15
    atak
    0.15
     correctness
    0.14
    ìĦł
    0.14
    IMIT
    0.14
     Maher
    0.14
    ema
    0.14
     Weiner
    0.13
    uddy
    0.13
    bourne
    0.13
    Act Density 0.015%

    No Known Activations