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

    Neuronpedia

    INDEX
    Explanations

    phrases related to artistic expression and critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avers
    -0.17
    ini
    -0.15
    zi
    -0.15
     detail
    -0.15
     torque
    -0.14
    agne
    -0.14
    avian
    -0.14
    anes
    -0.14
    MB
    -0.14
     tor
    -0.13
    POSITIVE LOGITS
    çļĦæĺ¯
    0.16
    something
    0.16
    SSERT
    0.15
    âĶIJ
    0.15
    aac
    0.15
    ependency
    0.15
    èĭ±éĽĦ
    0.14
    .NewLine
    0.14
    UGHT
    0.14
    istar
    0.14
    Act Density 0.266%

    No Known Activations