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

    Neuronpedia

    INDEX
    Explanations

    actions and processes related to calculations and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Advance
    -0.15
    osta
    -0.14
    rys
    -0.14
    anka
    -0.13
     sne
    -0.13
    arge
    -0.13
     Sor
    -0.13
    tur
    -0.13
    inde
    -0.13
    zew
    -0.13
    POSITIVE LOGITS
     then
    0.17
    ynos
    0.16
    ãģĻãĤĭãģ¨
    0.15
     Then
    0.15
    then
    0.15
    μβ
    0.15
    ffic
    0.14
    Then
    0.14
     entonces
    0.14
    raphics
    0.13
    Act Density 0.074%

    No Known Activations