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

    Neuronpedia

    INDEX
    Explanations

    expressions related to tightness or constriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imum
    -0.16
    apore
    -0.16
    leta
    -0.15
    iov
    -0.15
    uant
    -0.14
    FA
    -0.14
    ès
    -0.14
     ward
    -0.14
     lam
    -0.14
     Fee
    -0.14
    POSITIVE LOGITS
     tight
    0.20
    tight
    0.19
     tighter
    0.18
    est
    0.18
    ness
    0.17
    ifecycle
    0.16
    NESS
    0.16
     chặt
    0.15
    اسب
    0.15
    flush
    0.15
    Act Density 0.009%

    No Known Activations