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

    Neuronpedia

    INDEX
    Explanations

    common linking words and auxiliary verbs indicating existence or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Richt
    -0.17
    ätz
    -0.16
     Linked
    -0.15
     Brace
    -0.15
    üt
    -0.14
    ffer
    -0.14
     Reject
    -0.14
     Went
    -0.14
    ibre
    -0.13
    æŁ
    -0.13
    POSITIVE LOGITS
    erus
    0.16
    Logic
    0.16
    logic
    0.15
     sensible
    0.15
    Ñĩна
    0.15
    ushman
    0.14
    wise
    0.14
    éal
    0.14
    tm
    0.14
    azaar
    0.14
    Act Density 0.005%

    No Known Activations