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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or paragraphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fra
    -0.52
    edo
    -0.52
     con
    -0.50
     ,
    -0.50
    anti
    -0.48
     th
    -0.47
    rare
    -0.47
    abestanden
    -0.46
    によっては
    -0.45
     CYTHON
    -0.44
    POSITIVE LOGITS
     quæ
    0.98
     houſe
    0.77
     ejus
    0.73
     RIPRODUZIONE
    0.71
     myſelf
    0.71
     reaſon
    0.70
     purpoſe
    0.70
     ſtate
    0.70
     Monfieur
    0.69
     pinulongan
    0.69
    Act Density 0.181%

    No Known Activations