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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations related to functions and derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*
    -0.60
     betweenstory
    -0.47
    向
    -0.45
     privilege
    -0.43
    客
    -0.42
    multicolumn
    -0.42
     Extragalactic
    -0.42
    Ответить
    -0.41
     committee
    -0.41
     event
    -0.41
    POSITIVE LOGITS
    stood
    0.57
     itſelf
    0.56
     ujednoznacz
    0.55
     myſelf
    0.54
     Administrativna
    0.54
     zijne
    0.53
     mijne
    0.52
    AddTagHelper
    0.51
    setVerticalGroup
    0.51
    kapnya
    0.50
    Act Density 0.489%

    No Known Activations