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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [:]
    -0.68
     kya
    -0.68
    simpleType
    -0.65
    おか
    -0.64
     createStore
    -0.64
    Sera
    -0.63
    </h5>
    -0.63
    iseite
    -0.63
    ura
    -0.63
     Nora
    -0.62
    POSITIVE LOGITS
    — 
    0.83
     للمعارف
    0.80
    expandindo
    0.79
    ="#">
    0.79
     '@/
    0.74
     την
    0.72
    ostante
    0.71
    acterium
    0.71
     AppColors
    0.70
    Ƚ
    0.69
    Act Density 0.050%

    No Known Activations