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

    Neuronpedia

    INDEX
    Explanations

    references to theories and theoretical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.20
    itude
    -0.18
     theor
    -0.17
     teor
    -0.17
     theoretical
    -0.17
    itan
    -0.16
     theory
    -0.16
    nem
    -0.16
    ned
    -0.15
    engers
    -0.15
    POSITIVE LOGITS
    /do
    0.18
    /pr
    0.17
    ical
    0.17
    rence
    0.16
    سÛĮÙĨ
    0.16
    craft
    0.16
    /model
    0.16
    -pr
    0.16
    /models
    0.15
    à¤Ĥà¤Ĺल
    0.15
    Act Density 0.032%

    No Known Activations