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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģįãģŁ
    -0.19
    line
    -0.16
    ened
    -0.15
    PHY
    -0.15
    .Encoding
    -0.15
    ways
    -0.15
    ìĦľëĬĶ
    -0.15
    èį
    -0.15
    TickCount
    -0.15
    gorith
    -0.15
    POSITIVE LOGITS
    uvre
    0.17
    eer
    0.17
    ois
    0.16
    iro
    0.16
    ably
    0.16
    ry
    0.15
    uell
    0.15
    jour
    0.15
    DrawerToggle
    0.15
    etros
    0.14
    Act Density 0.135%

    No Known Activations