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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dawson
    -0.69
     Varela
    -0.69
     Huf
    -0.67
     Skirt
    -0.65
     Aj
    -0.64
    Thur
    -0.64
     Vila
    -0.64
     Jake
    -0.63
     call
    -0.63
     Teb
    -0.62
    POSITIVE LOGITS
     Flick
    0.95
    BSD
    0.94
    groet
    0.92
     Madura
    0.91
     Juniper
    0.90
    Flick
    0.90
    atyw
    0.88
     Mallory
    0.87
     Baran
    0.85
     Arya
    0.84
    Act Density 2.112%

    No Known Activations