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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that contrast two sides or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    太éĥİ
    -0.14
     Pey
    -0.14
    marshall
    -0.14
    SharedPointer
    -0.14
    arn
    -0.14
    enic
    -0.14
    ामà¤Ĺ
    -0.13
    nod
    -0.13
    uen
    -0.13
    outed
    -0.13
    POSITIVE LOGITS
    947
    0.16
    iyim
    0.16
     neb
    0.15
    655
    0.15
    PCP
    0.15
    edn
    0.15
    534
    0.15
    941
    0.14
     Bender
    0.14
    204
    0.14
    Act Density 0.037%

    No Known Activations