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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to significant conflict and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meilleurs
    -0.49
     étroite
    -0.47
     šť
    -0.45
     congé
    -0.45
     ligação
    -0.44
     تضيفلها
    -0.44
     légère
    -0.43
     caccia
    -0.42
     različ
    -0.42
     readonly
    -0.40
    POSITIVE LOGITS
     gigantic
    1.19
     giant
    1.12
     big
    1.12
     large
    1.07
     عظ
    1.05
     besar
    1.02
     largest
    1.02
     grandeur
    1.02
     colossal
    1.01
     huge
    1.01
    Act Density 0.523%

    No Known Activations