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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or characters that appear frequently in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osten
    -0.14
    endar
    -0.14
     ÙħÙħÙĨ
    -0.14
    imdi
    -0.14
    vak
    -0.14
    Ñľ
    -0.14
    tingham
    -0.13
     Simpl
    -0.13
    ekli
    -0.13
    ÑħÑĥ
    -0.13
    POSITIVE LOGITS
     rushed
    0.21
     particularly
    0.20
     hurried
    0.18
     rush
    0.17
     especially
    0.17
    particularly
    0.17
     hurry
    0.16
     fle
    0.16
     even
    0.16
     rushes
    0.16
    Act Density 0.033%

    No Known Activations