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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing an increase or decrease in qualities or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lucene
    -0.52
    スタム
    -0.51
    aptation
    -0.50
     hasn
    -0.50
    XmlType
    -0.50
    telle
    -0.49
     splin
    -0.48
    isn
    -0.48
     Siro
    -0.48
     BREAKING
    -0.47
    POSITIVE LOGITS
     дописавши
    0.76
    +#+#
    0.73
     >::
    0.64
    ergic
    0.63
    RectangleBorder
    0.59
     flatter
    0.58
     _{\
    0.57
    越大
    0.57
     становника
    0.56
    \{\\
    0.56
    Act Density 0.052%

    No Known Activations