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

    Neuronpedia

    INDEX
    Explanations

    phrases that express definitions or the nature of experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.16
    abbit
    -0.14
    bourg
    -0.14
    ÅĻÃŃž
    -0.14
    ric
    -0.14
     Mezi
    -0.13
    flix
    -0.13
    borg
    -0.13
     justified
    -0.13
     Mall
    -0.13
    POSITIVE LOGITS
     means
    0.17
    ÑĢаг
    0.17
    éo
    0.15
     Means
    0.15
    means
    0.14
    .IContainer
    0.14
     takes
    0.14
     cost
    0.14
     Takes
    0.14
    ushort
    0.14
    Act Density 0.016%

    No Known Activations