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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     however
    -0.19
     totiž
    -0.18
     quindi
    -0.17
     ÑģооÑĤвеÑĤ
    -0.16
     hence
    -0.15
     zwar
    -0.15
     therefore
    -0.15
    æīĢ以
    -0.15
     moreover
    -0.14
     However
    -0.14
    POSITIVE LOGITS
    forth
    0.22
     note
    0.19
     unlike
    0.18
    że
    0.18
     please
    0.17
     due
    0.17
    much
    0.17
     much
    0.16
    please
    0.16
     do
    0.16
    Act Density 0.067%

    No Known Activations