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

    Neuronpedia

    INDEX
    Explanations

    references to classifications and categories, especially in relation to aspects of culture or systematic organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ote
    -0.16
    uur
    -0.15
    öl
    -0.15
    uil
    -0.15
    haul
    -0.15
    oten
    -0.14
    chooser
    -0.14
    ente
    -0.14
     tw
    -0.14
     ag
    -0.13
    POSITIVE LOGITS
    orz
    0.16
    yre
    0.15
     пож
    0.15
    erdale
    0.15
    OfSize
    0.15
    orado
    0.15
    indy
    0.14
    .persistent
    0.14
     stages
    0.14
    anie
    0.14
    Act Density 0.323%

    No Known Activations