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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions and preparation steps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Slash
    -0.16
     Slice
    -0.16
     Puzzle
    -0.15
    ograd
    -0.15
    élé
    -0.14
    anny
    -0.14
    .slice
    -0.14
    anne
    -0.14
    essen
    -0.14
    eriod
    -0.14
    POSITIVE LOGITS
     scoop
    0.27
     sco
    0.24
     ball
    0.24
     Sco
    0.23
     balls
    0.23
     BALL
    0.22
    -ball
    0.22
     formed
    0.21
     shapes
    0.20
     shaping
    0.20
    Act Density 0.019%

    No Known Activations