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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.75
     imageNamed
    -0.74
    URLException
    -0.69
    limsy
    -0.67
    adecimal
    -0.66
    дів
    -0.65
    foque
    -0.64
     Nul
    -0.62
    Rhestr
    -0.62
     tartalomajánló
    -0.60
    POSITIVE LOGITS
    edly
    0.57
     doInBackground
    0.53
     usai
    0.51
    شهاد
    0.51
     opět
    0.50
     respectivamente
    0.50
    ızı
    0.48
    一同
    0.47
     reportedly
    0.47
     stále
    0.46
    Act Density 0.296%

    No Known Activations