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

    Neuronpedia

    INDEX
    Explanations

    words associated with character names and attributes in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.87
     poffible
    -0.72
     ſtand
    -0.72
     acorns
    -0.71
     Theſe
    -0.71
     Shakspeare
    -0.70
     canst
    -0.70
     Cæsar
    -0.70
     anhänger
    -0.70
    出版年
    -0.69
    POSITIVE LOGITS
     "
    0.77
     “
    0.77
     p
    0.64
     b
    0.64
     g
    0.62
    onAttach
    0.59
    CROSSTALK
    0.57
     m
    0.55
     ‘
    0.53
      
    0.53
    Act Density 0.532%

    No Known Activations