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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases related to evidence and assessments in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -1.01
     NDEBUG
    -0.95
     Efq
    -0.90
     itſelf
    -0.86
     للمعارف
    -0.85
     Jefus
    -0.83
     Monfieur
    -0.81
     $_"
    -0.81
    NUMX
    -0.80
    ContentLoaded
    -0.80
    POSITIVE LOGITS
    ↵↵
    0.64
    .
    0.57
    ↵
    0.56
      
    0.55
    ">)</
    0.50
    </b>
    0.49
     de
    0.48
    [
    0.48
    <b>
    0.47
    ).
    0.47
    Act Density 4.083%

    No Known Activations