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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight differences between groups or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     earnest
    -0.15
     Beyond
    -0.14
    \:
    -0.14
    upo
    -0.14
    resco
    -0.13
     ëĭ¤ìĸijíķľ
    -0.13
    erc
    -0.13
    erah
    -0.13
    ãĤįãģĨ
    -0.13
    Ñģам
    -0.13
    POSITIVE LOGITS
     counterparts
    0.33
     counterpart
    0.29
     comparable
    0.29
     other
    0.24
     equivalent
    0.23
     corresponding
    0.23
     compar
    0.22
     Comparable
    0.20
     elsewhere
    0.20
     mere
    0.20
    Act Density 0.248%

    No Known Activations