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

    Neuronpedia

    INDEX
    Explanations

    measurements and dimensions related to objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teri
    -0.17
     Desk
    -0.16
     Tiny
    -0.15
     Extreme
    -0.15
    defs
    -0.14
    hurst
    -0.14
    aliz
    -0.14
    ICLE
    -0.14
    ument
    -0.14
    esson
    -0.14
    POSITIVE LOGITS
     wide
    0.40
     tall
    0.40
     thick
    0.33
    -wide
    0.32
    wide
    0.31
     long
    0.30
     high
    0.28
    -high
    0.26
     deep
    0.25
    Wide
    0.25
    Act Density 0.051%

    No Known Activations