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

    Neuronpedia

    INDEX
    Explanations

    names of researchers and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.50
     مشين
    -0.49
     Houſe
    -0.47
     Morocco
    -0.47
     Reſ
    -0.47
     Vichy
    -0.46
     spagno
    -0.46
    PasswordEncoder
    -0.46
     kambing
    -0.46
     mı
    -0.46
    POSITIVE LOGITS
     Jun
    0.95
     Bin
    0.79
     Jian
    0.77
    帖最后由
    0.76
     Hai
    0.75
     Yong
    0.75
     Zhi
    0.74
     Jing
    0.74
     Min
    0.72
     Hong
    0.71
    Act Density 0.291%

    No Known Activations