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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adro
    -0.16
    lace
    -0.15
    urdy
    -0.15
    woff
    -0.14
    è¬
    -0.14
    decltype
    -0.14
     à¤ļलत
    -0.14
    .Relative
    -0.13
    azar
    -0.13
    ropoda
    -0.13
    POSITIVE LOGITS
     Singh
    0.29
     Kumar
    0.27
     Sharma
    0.26
     Sax
    0.24
     Gupta
    0.24
     Ti
    0.23
     sing
    0.23
    Sing
    0.22
     Tri
    0.21
     Jos
    0.20
    Act Density 0.185%

    No Known Activations