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

    Neuronpedia

    INDEX
    Explanations

    specific actions and processes related to production and creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     slots
    -0.15
    empo
    -0.14
    inite
    -0.13
     directions
    -0.13
    faces
    -0.13
    odes
    -0.13
    ormal
    -0.13
    rows
    -0.13
    á»Ļ
    -0.13
     (
    -0.13
    POSITIVE LOGITS
     step
    0.39
     piece
    0.34
     word
    0.33
     pixel
    0.32
     bit
    0.30
     point
    0.30
     byte
    0.30
     molecule
    0.29
     inch
    0.29
    step
    0.29
    Act Density 0.386%

    No Known Activations