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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erville
    -0.17
     fav
    -0.16
    urred
    -0.15
    orst
    -0.15
     Underground
    -0.14
     govern
    -0.14
     underground
    -0.14
    uç
    -0.14
    ocommerce
    -0.14
     colon
    -0.13
    POSITIVE LOGITS
    herits
    0.18
    amac
    0.15
    phia
    0.15
     Reaper
    0.14
    Ñĩий
    0.14
    ires
    0.14
    spa
    0.14
    Ñĥнд
    0.14
    _literals
    0.14
    åŃ£
    0.14
    Act Density 0.008%

    No Known Activations