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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.72
     a
    -0.67
     all
    -0.67
     "
    -0.66
     “
    -0.63
     
    -0.59
     her
    -0.57
    vi
    -0.56
    ja
    -0.55
    <eos>
    -0.55
    POSITIVE LOGITS
     متعلقه
    1.40
     فريبيس
    1.13
    出版年
    1.08
     NSCoder
    1.00
    GEBURTS
    0.99
     للمعارف
    0.97
    __':
    0.97
    XmlAccessType
    0.96
    RetentionPolicy
    0.96
    __":
    0.95
    Act Density 0.172%

    No Known Activations