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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptors that emphasize size, quality, and status of subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olar
    -0.17
    aid
    -0.16
    _PUS
    -0.15
    stral
    -0.14
    entine
    -0.14
    /png
    -0.14
    atern
    -0.14
     diam
    -0.14
    rud
    -0.14
    iah
    -0.14
    POSITIVE LOGITS
    reten
    0.14
    ¯
    0.13
    lee
    0.13
     mere
    0.13
     bubble
    0.13
    _touch
    0.13
     Squad
    0.13
    ODB
    0.12
     Nine
    0.12
    /MIT
    0.12
    Act Density 0.482%

    No Known Activations