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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.13
     itſelf
    -1.11
     pleaſure
    -1.11
     Theſe
    -1.10
    ſelf
    -1.04
     Monfieur
    -1.02
     poffible
    -1.01
     myſelf
    -1.01
     Jefus
    -0.99
     Cæsar
    -0.99
    POSITIVE LOGITS
     John
    0.53
     ra
    0.52
     Sa
    0.51
     sa
    0.48
     
    0.48
    ´
    0.47
     senior
    0.46
     ju
    0.46
     A
    0.45
     r
    0.45
    Act Density 0.616%

    No Known Activations