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

    Neuronpedia

    INDEX
    Explanations

    keywords related to DIY projects and self-made solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bench
    -0.17
    indh
    -0.16
    ESH
    -0.16
    _bn
    -0.15
    cretion
    -0.14
    \grid
    -0.14
    Ùħار
    -0.14
    кид
    -0.14
    vil
    -0.14
    udev
    -0.13
    POSITIVE LOGITS
     DIY
    0.20
    -self
    0.17
    ost
    0.17
    /self
    0.17
     enthusiast
    0.16
     self
    0.15
    ellig
    0.15
    SELF
    0.15
     pseudo
    0.15
    ograd
    0.15
    Act Density 0.149%

    No Known Activations