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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals and their affiliations or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouser
    -0.17
    ester
    -0.16
    antan
    -0.16
    ilton
    -0.15
    ccione
    -0.15
    .lin
    -0.14
    uhan
    -0.14
     Marino
    -0.14
    #__
    -0.14
     обла
    -0.14
    POSITIVE LOGITS
     Jeb
    0.19
     Halk
    0.17
     Brooke
    0.16
     Darwin
    0.16
    ½
    0.16
     Souls
    0.15
     Cunning
    0.15
     Dani
    0.15
     de
    0.15
     Guest
    0.15
    Act Density 0.116%

    No Known Activations