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

    Neuronpedia

    INDEX
    Explanations

    references to specific people, places, or notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lessing
    -0.84
    gameserver
    -0.81
    NgModule
    -0.77
    isnull
    -0.76
    oarece
    -0.76
     Hearn
    -0.76
     tranquillo
    -0.73
     Spence
    -0.73
     Trento
    -0.73
    ълга
    -0.72
    POSITIVE LOGITS
    Frat
    0.89
     Frat
    0.85
     LUN
    0.82
     lentils
    0.81
     Pizza
    0.78
     Ballo
    0.76
     Lun
    0.76
     pizza
    0.76
     ald
    0.74
     lun
    0.74
    Act Density 2.410%

    No Known Activations