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

    Neuronpedia

    INDEX
    Explanations

    references to specific numbers or quantities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "Â" or related anomalies in text representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.87
     Nanto
    -0.81
     VK
    -0.81
     guiActiveUnfocused
    -0.80
    ãģ®éŃĶ
    -0.78
    enburg
    -0.72
     PubMed
    -0.71
    manship
    -0.70
     Luther
    -0.69
    enstein
    -0.66
    POSITIVE LOGITS
    ³
    1.29
    ¹
    1.28
    ´
    1.24
    ¨
    1.18
    ¦
    1.17
    ¿
    1.17
    ¸
    1.17
    ¾
    1.16
    ª
    1.15
    ¤
    1.14
    Act Density 0.007%

    No Known Activations