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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    énieur
    -0.67
    avía
    -0.65
    <>();
    -0.58
    ينة
    -0.57
    ächlich
    -0.54
    dür
    -0.54
     Kleid
    -0.53
     consonant
    -0.53
    ãy
    -0.52
     Diplomat
    -0.51
    POSITIVE LOGITS
     Dont
    1.81
     dont
    1.75
    Dont
    1.74
    Heres
    1.69
     Thats
    1.66
    Theres
    1.66
     wasnt
    1.62
     youre
    1.61
     Theres
    1.59
     thats
    1.59
    Act Density 0.089%

    No Known Activations