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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contexts within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ronics
    -0.17
    ureau
    -0.17
    ibble
    -0.15
    irie
    -0.14
    нед
    -0.14
    Eye
    -0.14
    idebar
    -0.14
    ynes
    -0.14
    ailer
    -0.13
    Ìģ
    -0.13
    POSITIVE LOGITS
    utura
    0.16
    ida
    0.16
     Rav
    0.14
     Playground
    0.14
     Lov
    0.14
    ,readonly
    0.14
     Glover
    0.14
    278
    0.14
     Wa
    0.13
    Ut
    0.13
    Act Density 0.181%

    No Known Activations