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

    Neuronpedia

    INDEX
    Explanations

    negative contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.69
     Chwiliwch
    -0.65
    s
    -0.62
    存于互联网档案馆
    -0.60
    ″]
    -0.60
    httphttps
    -0.54
    URLException
    -0.52
    EIF
    -0.52
     Pij
    -0.50
    ̢
    -0.50
    POSITIVE LOGITS
     doesn
    0.89
     didn
    0.86
    wouldn
    0.86
     wouldn
    0.84
     aren
    0.83
     wasn
    0.82
    doesn
    0.82
    Wouldn
    0.81
    didn
    0.81
     weren
    0.80
    Act Density 0.120%

    No Known Activations