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

    Neuronpedia

    INDEX
    Explanations

    instances where examples or additional information are introduced or emphasized in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Савезне
    -0.75
     estimés
    -0.54
     fraî
    -0.51
     Numerade
    -0.51
     propOrder
    -0.51
    trui
    -0.50
     PeEnEo
    -0.49
     okuyayım
    -0.49
     favoritas
    -0.48
    oredCriteria
    -0.47
    POSITIVE LOGITS
    Moreover
    0.96
     However
    0.92
    Consequently
    0.92
     Moreover
    0.91
     Consequently
    0.89
    However
    0.88
    Therefore
    0.87
     Therefore
    0.85
    Nevertheless
    0.84
    Furthermore
    0.81
    Act Density 0.415%

    No Known Activations