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

    Neuronpedia

    INDEX
    Explanations

    concepts related to ideas, particularly those that are challenging or require consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.80
    adaptiveStyles
    -0.72
     themſelves
    -0.70
     Majefty
    -0.70
     ſtate
    -0.69
     himſelf
    -0.68
     itſelf
    -0.67
     chofe
    -0.67
    adpleegd
    -0.66
     occaf
    -0.66
    POSITIVE LOGITS
     issues
    0.58
    <tbody>
    0.56
    NameInMap
    0.53
    gesellschaft
    0.50
     focused
    0.50
     بات
    0.49
    ıldız
    0.48
     developed
    0.48
    jspx
    0.48
     input
    0.48
    Act Density 0.848%

    No Known Activations