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

    Neuronpedia

    INDEX
    Explanations

    symbols and bullet points indicating list items or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rk
    -0.15
    geh
    -0.14
    ÛĮÙĩ
    -0.14
     McCart
    -0.14
     оÑĤв
    -0.13
    adian
    -0.13
    ystone
    -0.13
    лл
    -0.13
     alm
    -0.13
    reb
    -0.13
    POSITIVE LOGITS
    ÄįÃŃ
    0.15
     vrou
    0.14
     chains
    0.14
    é¾
    0.14
    orca
    0.14
    osate
    0.14
     Rel
    0.14
    vat
    0.13
    го
    0.13
    ardu
    0.13
    Act Density 0.053%

    No Known Activations