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

    Neuronpedia

    INDEX
    Explanations

    references to historical claims and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erule
    -0.15
    åłĤ
    -0.15
     заклад
    -0.15
    antee
    -0.15
    ĥĿ
    -0.14
    å¼ĺ
    -0.14
    ÙİÙĬ
    -0.14
    heid
    -0.14
    ape
    -0.14
    lyn
    -0.13
    POSITIVE LOGITS
     claims
    0.16
     accounts
    0.16
     Pell
    0.15
    atrib
    0.15
    Ĺi
    0.14
    nder
    0.14
     claimed
    0.14
    uku
    0.14
     modern
    0.14
     disputed
    0.14
    Act Density 0.231%

    No Known Activations