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

    Neuronpedia

    INDEX
    Explanations

    references to "pro" or "protection" related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nim
    -0.16
    εÏį
    -0.16
     Bourbon
    -0.15
    edral
    -0.15
    itsu
    -0.15
    rod
    -0.14
    ampa
    -0.14
    nw
    -0.14
    nuts
    -0.14
    磨
    -0.14
    POSITIVE LOGITS
    vision
    0.29
    portion
    0.24
    tection
    0.23
    ceed
    0.22
    long
    0.22
    spect
    0.21
    lif
    0.20
    tein
    0.20
    vides
    0.20
    VISION
    0.20
    Act Density 0.021%

    No Known Activations