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

    Neuronpedia

    INDEX
    Explanations

    references to locations, specifically cities and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ();)
    -0.68
    eclamp
    -0.62
     HttpResponse
    -0.59
     Sams
    -0.59
    راضي
    -0.58
     Galloway
    -0.56
    gag
    -0.56
     sams
    -0.55
     Dynamite
    -0.55
    arium
    -0.54
    POSITIVE LOGITS
     Stanford
    0.77
    Stanford
    0.77
    URBANA
    0.72
    KELEY
    0.72
    Yale
    0.70
    Princeton
    0.69
     ddelweddau
    0.69
    Harvard
    0.69
     Harvard
    0.67
     Cambridge
    0.67
    Act Density 0.264%

    No Known Activations