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

    Neuronpedia

    INDEX
    Explanations

    the beginning of sentences and paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.21
     فريبيس
    -1.19
     betweenstory
    -1.08
    ConstraintMaker
    -1.06
     CreateTagHelper
    -1.04
    TagMode
    -1.01
    principalTable
    -0.98
    Personendaten
    -0.97
    RetentionPolicy
    -0.97
    تقاوى
    -0.96
    POSITIVE LOGITS
    ↵↵
    0.54
     M
    0.47
     in
    0.47
    &
    0.46
     ré
    0.45
     ag
    0.44
    <eos>
    0.43
     «
    0.43
     “
    0.43
     ​​
    0.42
    Act Density 0.292%

    No Known Activations