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

    Neuronpedia

    INDEX
    Explanations

    references to natural entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
     Biôgrafia
    -0.69
     étoit
    -0.67
     miniaturka
    -0.66
     zoude
    -0.66
    oneofs
    -0.66
     Económica
    -0.66
     ainfi
    -0.66
    windowFixed
    -0.66
    OGND
    -0.65
    POSITIVE LOGITS
     natural
    0.96
     coin
    0.70
    natural
    0.65
     NATURAL
    0.63
     Natural
    0.61
     draft
    0.57
    json
    0.54
     condition
    0.52
     round
    0.52
    sql
    0.51
    Act Density 0.251%

    No Known Activations