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

    Neuronpedia

    INDEX
    Explanations

    sections of HTML or XML code and their structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.35
     Efq
    -1.35
     myſelf
    -1.31
     Theſe
    -1.29
     Majefty
    -1.28
     uſed
    -1.26
     pleaſure
    -1.25
     purpoſe
    -1.22
     Jefus
    -1.21
     itſelf
    -1.19
    POSITIVE LOGITS
    :✨
    0.67
     Cordero
    0.64
     .
    0.64
    </td>
    0.63
    Flor
    0.63
     Flor
    0.60
     المعيارى
    0.59
     الرغم
    0.58
     })}
    0.58
    MathML
    0.57
    Act Density 0.045%

    No Known Activations