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

    Neuronpedia

    INDEX
    Explanations

    words indicating certainty or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ww
    -0.17
    alsy
    -0.17
    ixin
    -0.15
    aint
    -0.15
    Âłje
    -0.15
    ă
    -0.15
    baugh
    -0.15
    äd
    -0.14
    650
    -0.14
    rokes
    -0.14
    POSITIVE LOGITS
    plevel
    0.15
     hadn
    0.15
    acas
    0.15
     Saunders
    0.14
    _almost
    0.14
    acman
    0.14
     celib
    0.13
    ãĥªãĤ«
    0.13
    گراÙĨ
    0.13
     gratuita
    0.13
    Act Density 0.000%

    No Known Activations