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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.04
    URLException
    -1.03
    AndEndTag
    -1.02
     ivelany
    -0.99
     Bourgoin
    -0.91
     Chriftian
    -0.90
     betweenstory
    -0.89
    GEBURTSDATUM
    -0.89
     Efq
    -0.89
    出版年
    -0.88
    POSITIVE LOGITS
     because
    0.59
     to
    0.57
     for
    0.57
    ly
    0.53
     thing
    0.52
     work
    0.51
     as
    0.51
     stuff
    0.49
     if
    0.49
     in
    0.48
    Act Density 0.279%

    No Known Activations