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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exceeding expectations or going the extra mile

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itty
    -0.20
    jt
    -0.15
    296
    -0.14
    ANGER
    -0.14
    Äįel
    -0.14
    got
    -0.14
    close
    -0.14
    nak
    -0.13
    ostel
    -0.13
    inding
    -0.13
    POSITIVE LOGITS
     beyond
    0.41
     Beyond
    0.33
    Beyond
    0.30
     extra
    0.29
    eyond
    0.28
     EXTRA
    0.27
     above
    0.26
    -extra
    0.23
    above
    0.23
     Above
    0.23
    Act Density 0.042%

    No Known Activations