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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.58
    MigrationBuilder
    -0.55
    帖最后由
    -0.54
    tagext
    -0.50
     ligiloj
    -0.49
    principalColumn
    -0.48
    fromnode
    -0.46
    BeginContext
    -0.44
    awtextra
    -0.43
    exitRule
    -0.41
    POSITIVE LOGITS
     Lewandowski
    0.55
     Kowal
    0.51
     Kraw
    0.49
     Nowak
    0.47
     Kowalski
    0.47
     Baran
    0.45
     Grab
    0.44
     Bien
    0.43
    kowski
    0.43
    laws
    0.42
    Act Density 0.311%

    No Known Activations