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

    Neuronpedia

    INDEX
    Explanations

    references to the reader's engagement and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    пÑĢа
    -0.15
    ucken
    -0.15
    emm
    -0.15
    iks
    -0.14
    ONO
    -0.14
    ador
    -0.14
    abe
    -0.14
    à¸Ńาà¸Ī
    -0.14
    owe
    -0.14
    aper
    -0.13
    POSITIVE LOGITS
     enjoy
    0.21
     enjoyed
    0.21
     enjoys
    0.18
    702
    0.18
     enjoying
    0.17
     Enjoy
    0.16
    FRING
    0.16
    obia
    0.15
    Enjoy
    0.15
    TRACK
    0.15
    Act Density 0.022%

    No Known Activations