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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles associated with individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bress
    -0.84
    IsMutable
    -0.75
    Хьажоргаш
    -0.74
     Kraw
    -0.73
    ieteur
    -0.71
    iſten
    -0.70
     Mazz
    -0.70
     Kowal
    -0.69
    alakip
    -0.68
     Steff
    -0.68
    POSITIVE LOGITS
     Fürst
    0.38
     Fields
    0.35
     Smith
    0.33
     Banks
    0.32
     Green
    0.32
     Wood
    0.31
     Doble
    0.31
     Collins
    0.31
     Kunde
    0.31
     Walker
    0.30
    Act Density 1.770%

    No Known Activations