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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -1.05
     ―――――
    -0.98
    actionMode
    -0.97
     '\\;'
    -0.89
     betweenstory
    -0.89
     pitié
    -0.88
     tanong
    -0.87
    Gambas
    -0.86
     EnglishChoose
    -0.86
    rungsseite
    -0.84
    POSITIVE LOGITS
     ‘
    0.79
    “
    0.77
     
    0.76
    </em>
    0.74
    </strong>
    0.72
     '
    0.69
     “
    0.67
    /
    0.67
    "
    0.67
    ‘
    0.66
    Act Density 0.220%

    No Known Activations