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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tends
    -0.62
     podendo
    -0.58
     possano
    -0.56
     currently
    -0.56
    currently
    -0.56
    ώρα
    -0.55
     anymore
    -0.55
     shouldBe
    -0.54
     derzeit
    -0.54
     if
    -0.54
    POSITIVE LOGITS
     previously
    0.81
     originally
    0.79
     damals
    0.76
     vroeger
    0.75
     anteriormente
    0.74
    originally
    0.71
     précédemment
    0.69
     originalmente
    0.69
    previously
    0.69
     kemarin
    0.68
    Act Density 0.235%

    No Known Activations