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

    Neuronpedia

    INDEX
    Explanations

    detailed descriptions of course structures and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Courses
    -0.17
     courses
    -0.17
     Course
    -0.17
    Courses
    -0.16
    courses
    -0.15
    asz
    -0.15
    èľ
    -0.15
     UNUSED
    -0.15
    uffman
    -0.14
    dde
    -0.14
    POSITIVE LOGITS
     hands
    0.34
    hands
    0.32
     practical
    0.31
     Hands
    0.31
     theory
    0.27
    Hands
    0.26
     Practical
    0.25
    çIJĨ论
    0.24
     theoretical
    0.24
     theoret
    0.23
    Act Density 0.151%

    No Known Activations