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

    Neuronpedia

    INDEX
    Explanations

    requests for help or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tutti
    -0.36
     todos
    -0.34
     tutte
    -0.34
     everywhere
    -0.29
    principalColumn
    -0.29
    iz
    -0.29
    一一
    -0.28
     thing
    -0.28
     själva
    -0.28
     todas
    -0.28
    POSITIVE LOGITS
     someone
    4.09
    someone
    3.80
    Someone
    3.66
     somebody
    3.66
     Someone
    3.53
    somebody
    3.30
     alguien
    3.22
     SOMEONE
    3.09
     Somebody
    3.05
     quelqu
    3.03
    Act Density 0.959%

    No Known Activations