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

    Neuronpedia

    INDEX
    Explanations

    opinions about movies and personal experiences with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idon
    -0.16
    åĿĬ
    -0.15
    елеÑĦ
    -0.15
     FML
    -0.15
    NAL
    -0.15
    eldon
    -0.14
    MDB
    -0.14
    angan
    -0.14
    ãĤ¯ãĥĪ
    -0.14
    herits
    -0.13
    POSITIVE LOGITS
     enjoy
    0.58
     enjoys
    0.55
     enjoying
    0.54
     Enjoy
    0.52
     enjoyed
    0.51
     love
    0.50
    Enjoy
    0.46
     enjoyment
    0.45
     loves
    0.42
     LOVE
    0.42
    Act Density 0.664%

    No Known Activations