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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¢Ĩ
    -0.15
     Mek
    -0.14
    arge
    -0.14
    .Startup
    -0.14
    uki
    -0.14
    иÑĤелем
    -0.14
     Bang
    -0.13
     Brit
    -0.13
     Benson
    -0.13
    497
    -0.13
    POSITIVE LOGITS
    以ä¸ĭ
    0.18
    istrovstvÃŃ
    0.18
     Below
    0.17
     below
    0.17
    Below
    0.17
    ioni
    0.15
    athers
    0.15
    below
    0.15
    CHANT
    0.15
    ClientRect
    0.15
    Act Density 0.074%

    No Known Activations