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

    Neuronpedia

    INDEX
    Explanations

    randomly generated sequences of special characters

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "âĢ" which appears multiple times, indicating a focus on specific formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thomson
    -0.88
     Tob
    -0.77
     Jem
    -0.74
     mathemat
    -0.73
    itsch
    -0.72
     hypert
    -0.68
     Wer
    -0.68
     Wichita
    -0.68
     Skydragon
    -0.68
     telev
    -0.68
    POSITIVE LOGITS
    Ļ
    2.00
    ħ
    1.40
    ¬
    1.30
    ĺ
    1.29
    ı
    1.21
    ĸ
    1.20
    ļ
    1.20
    ¤
    1.19
    Ĩ
    1.15
    ¡
    1.14
    Act Density 0.330%

    No Known Activations