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

    Neuronpedia

    INDEX
    Explanations

    patterns of multiple word structures or phrases in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veau
    -0.18
    ifr
    -0.16
    олÑİ
    -0.16
    ought
    -0.14
    ibe
    -0.14
    aders
    -0.14
    zá
    -0.14
    大åħ¨
    -0.14
    ries
    -0.13
     ãĤ¢ãĤ¤
    -0.13
    POSITIVE LOGITS
    urdy
    0.16
    assis
    0.15
    Fuse
    0.15
    ohl
    0.14
    655
    0.14
    hai
    0.14
     reap
    0.14
    .sz
    0.14
    80
    0.13
     orient
    0.13
    Act Density 0.006%

    No Known Activations