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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, particularly in political and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.92
    ✨:
    -0.92
     Garza
    -0.86
    ftagPool
    -0.85
    ++
    -0.83
     henvisninger
    -0.83
     Albright
    -0.83
     insuffisamment
    -0.83
    Климат
    -0.82
    sidemargin
    -0.81
    POSITIVE LOGITS
     Schra
    0.83
     Cyclo
    0.81
     Mercan
    0.79
     cyclo
    0.76
     hoo
    0.74
    Hoo
    0.74
     Muck
    0.70
     Schal
    0.69
     Schiff
    0.69
     Vander
    0.69
    Act Density 1.609%

    No Known Activations