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

    Neuronpedia

    INDEX
    Explanations

    entities and specific names related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.61
    脚注の使い方
    -0.61
    usercontent
    -0.61
     nutella
    -0.59
     AssemblyTitle
    -0.59
    moiselle
    -0.58
     myſelf
    -0.58
     onlyOwner
    -0.56
    onOptions
    -0.56
     Dacia
    -0.56
    POSITIVE LOGITS
    colgante
    0.40
     his
    0.37
     loob
    0.36
     spalle
    0.35
     hablado
    0.35
    ề
    0.34
     ultimately
    0.34
     namanya
    0.33
    ds
    0.33
    omans
    0.33
    Act Density 1.050%

    No Known Activations