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

    Neuronpedia

    INDEX
    Explanations

    negative or critical sentiments and terms related to health or medical treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.23
     myſelf
    -1.12
     itſelf
    -1.08
     Jefus
    -1.04
     Theſe
    -1.03
     Majefty
    -0.98
     snippetHide
    -0.97
     chofe
    -0.96
    ſelf
    -0.94
     becauſe
    -0.94
    POSITIVE LOGITS
     pre
    0.59
     Pre
    0.57
    Pre
    0.55
     ex
    0.54
      
    0.53
    pr
    0.53
     pr
    0.52
     
    0.52
    -
    0.51
    pre
    0.51
    Act Density 0.326%

    No Known Activations