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
     koji
    -0.61
     himself
    -0.59
     Zeke
    -0.59
     који
    -0.58
     Himself
    -0.56
     Marcello
    -0.56
     Jeremy
    -0.55
    Joshua
    -0.55
     kevin
    -0.54
     lads
    -0.54
    POSITIVE LOGITS
     herself
    0.99
     Ann
    0.82
     bint
    0.82
     actress
    0.82
    herself
    0.76
     businesswoman
    0.74
    enerys
    0.73
    PerformLayout
    0.71
     actresses
    0.71
     Anne
    0.70
    Act Density 0.410%

    No Known Activations