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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related phrases indicating continuance or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctl
    -0.17
    borough
    -0.14
    akan
    -0.14
    ãĥĥãĤ¯
    -0.14
    ayıp
    -0.13
    iris
    -0.13
     Phong
    -0.13
    .dc
    -0.13
     pre
    -0.13
    abc
    -0.13
    POSITIVE LOGITS
    eck
    0.17
    utter
    0.15
    ungi
    0.15
     Till
    0.14
    anou
    0.14
    MC
    0.14
     Chester
    0.14
    리ìĸ´
    0.14
     Plain
    0.14
    561
    0.13
    Act Density 0.186%

    No Known Activations