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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values associated with dimensions or sizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bler
    -0.15
    bett
    -0.15
    wers
    -0.14
    mons
    -0.14
     Zy
    -0.14
    Ñĸдно
    -0.14
    werk
    -0.14
    legt
    -0.13
    mur
    -0.13
    anut
    -0.13
    POSITIVE LOGITS
    px
    0.35
    PX
    0.24
    pixel
    0.22
     pixels
    0.22
     pixel
    0.22
     px
    0.21
    Px
    0.21
    .px
    0.21
    .png
    0.21
    }px
    0.20
    Act Density 0.004%

    No Known Activations