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

    Neuronpedia

    INDEX
    Explanations

    unique proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    位
    -0.75
     Bourgoin
    -0.71
    auen
    -0.68
     McLaughlin
    -0.66
    byen
    -0.65
    Rhin
    -0.65
    equalTo
    -0.64
    tolo
    -0.63
     McFar
    -0.63
     Heine
    -0.62
    POSITIVE LOGITS
     Azz
    1.10
     OSS
    1.08
     Sepp
    1.01
     Hatt
    1.00
    Ayy
    0.99
     Coss
    0.98
     TCC
    0.98
     Utt
    0.96
     Hii
    0.95
     ECC
    0.95
    Act Density 0.848%

    No Known Activations