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

    Neuronpedia

    INDEX
    Explanations

    content related to specific medical or scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
     in
    -0.52
     
    -0.51
     and
    -0.49
      
    -0.47
     of
    -0.47
     […]
    -0.45
     .
    -0.45
     ...
    -0.45
     …
    -0.44
    POSITIVE LOGITS
     pleaſure
    1.16
     Jefus
    1.13
    ⓧ
    1.10
     Majefty
    1.07
    +#+#
    1.07
     itſelf
    1.07
     myſelf
    1.07
     Diſ
    1.06
     ſever
    1.06
     Monfieur
    1.06
    Act Density 1.120%

    No Known Activations