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

    Neuronpedia

    INDEX
    Explanations

    punctuation, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dylib
    -0.16
    鹿
    -0.16
    FTA
    -0.15
     جز
    -0.15
    ãģ£ãģ¡
    -0.15
    Ùħر
    -0.15
    alem
    -0.14
    765
    -0.14
    monkey
    -0.14
     Liber
    -0.14
    POSITIVE LOGITS
     fishes
    0.27
     fish
    0.27
     Fish
    0.22
    é±¼
    0.21
     Til
    0.20
    fish
    0.20
     spawning
    0.20
     fins
    0.20
     schooling
    0.20
    Fish
    0.20
    Act Density 0.026%

    No Known Activations