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

    Neuronpedia

    INDEX
    Explanations

    references to educational institutions and student-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ante
    -0.16
     Hed
    -0.16
    entar
    -0.15
    ระ
    -0.15
     Ras
    -0.15
     Tob
    -0.14
    ynn
    -0.13
    agua
    -0.13
    gota
    -0.13
     discre
    -0.13
    POSITIVE LOGITS
     GOODMAN
    0.18
    erman
    0.17
    INET
    0.16
    hani
    0.15
    rupt
    0.14
    robe
    0.14
    ört
    0.14
    .levels
    0.14
     seedu
    0.13
     Goodman
    0.13
    Act Density 0.299%

    No Known Activations