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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xCD
    -0.15
     lip
    -0.15
    hangi
    -0.14
     incl
    -0.14
    grim
    -0.14
    indo
    -0.14
     taj
    -0.14
    yar
    -0.14
    posables
    -0.14
     Plastic
    -0.13
    POSITIVE LOGITS
    share
    0.17
     share
    0.17
    aticon
    0.16
     Yük
    0.15
    .emf
    0.15
    Privacy
    0.15
    ÑĢеÑĪ
    0.15
     ÎļαÏĦηγοÏģία
    0.14
     Privacy
    0.14
     porr
    0.14
    Act Density 0.005%

    No Known Activations