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

    Neuronpedia

    INDEX
    Explanations

    references to sensory activities and crafting projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duck
    -0.16
    yas
    -0.16
    rost
    -0.16
     lid
    -0.15
    orizontal
    -0.15
    askell
    -0.15
    \Mapping
    -0.15
    lane
    -0.14
    quiz
    -0.14
    erli
    -0.14
    POSITIVE LOGITS
     loops
    0.26
     Knot
    0.24
     knots
    0.24
     rope
    0.23
     knot
    0.23
     loop
    0.22
     ropes
    0.21
    -loop
    0.20
     Loop
    0.20
     Rope
    0.19
    Act Density 0.123%

    No Known Activations