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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cielos
    -0.49
    お気軽
    -0.49
    Morfologia
    -0.48
     Meksika
    -0.47
     Simplemente
    -0.47
     livré
    -0.46
     seleção
    -0.46
     parcours
    -0.45
     vecind
    -0.45
    ViewInit
    -0.45
    POSITIVE LOGITS
     Important
    1.41
     important
    1.38
    important
    1.37
    Important
    1.34
     Importance
    1.30
     importance
    1.24
     IMPORTANT
    1.13
    Importance
    1.13
    importance
    1.13
     importante
    1.13
    Act Density 0.135%

    No Known Activations