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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and non-visible characters, possibly indicating document structure or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -1.38
     Jefus
    -1.25
     Efq
    -1.24
     Majefty
    -1.22
     Monfieur
    -1.18
     pleaſure
    -1.16
     uſed
    -1.15
     becauſe
    -1.14
     myſelf
    -1.14
     Reſ
    -1.13
    POSITIVE LOGITS
     of
    0.65
     </
    0.65
     ]
    0.65
     ]);
    0.65
     (
    0.65
     )
    0.65
     }\
    0.63
     /
    0.63
     or
    0.63
     [
    0.62
    Act Density 0.207%

    No Known Activations