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

    Neuronpedia

    INDEX
    Explanations

    references to time or temporal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.16
     Else
    -0.14
    ode
    -0.14
     merit
    -0.14
    uter
    -0.14
    yar
    -0.14
     subsequent
    -0.14
     overnight
    -0.14
    auen
    -0.14
     vé
    -0.14
    POSITIVE LOGITS
    cheng
    0.17
    OfDay
    0.17
    ingga
    0.15
    Ñīа
    0.15
    ramework
    0.15
    °}
    0.15
     há»ĵ
    0.15
    εÏĦ
    0.15
    OfFile
    0.15
    ÑĨÑĸ
    0.15
    Act Density 0.013%

    No Known Activations