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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships in complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     désolés
    -0.48
     gebeten
    -0.45
     Accidents
    -0.45
    principalTable
    -0.45
    jspb
    -0.45
     ivelany
    -0.43
    ностях
    -0.43
    лях
    -0.41
     препратки
    -0.41
     invokingState
    -0.40
    POSITIVE LOGITS
    OREM
    0.71
    orem
    0.61
    ходом
    0.60
    asem
    0.57
    $}}
    0.57
    blem
    0.56
    zeniem
    0.56
    inem
    0.55
    lossenen
    0.55
    }}$\\
    0.54
    Act Density 0.041%

    No Known Activations