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
    ouch
    -0.16
    resco
    -0.15
    entai
    -0.15
    SearchParams
    -0.15
    rawer
    -0.15
    º
    -0.14
    ante
    -0.14
    ipar
    -0.14
    oucher
    -0.14
    usu
    -0.14
    POSITIVE LOGITS
    OfWork
    0.16
    fully
    0.15
     underlying
    0.15
    656
    0.14
    ofday
    0.14
    akat
    0.14
    acht
    0.14
    agem
    0.14
    ichel
    0.14
    issy
    0.14
    Act Density 0.021%

    No Known Activations