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

    Neuronpedia

    INDEX
    Explanations

    colons indicating the start of a new section or category within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rovers
    -0.16
    ano
    -0.15
    ture
    -0.14
    azzi
    -0.14
    fh
    -0.14
    stell
    -0.14
    onda
    -0.14
    iyi
    -0.14
    uthor
    -0.13
    allen
    -0.13
    POSITIVE LOGITS
    441
    0.15
    еÑģÑĮ
    0.15
    lys
    0.15
    phia
    0.14
    aign
    0.14
    stdafx
    0.13
    IDX
    0.13
    SPACE
    0.13
     Aircraft
    0.13
    enet
    0.13
    Act Density 0.001%

    No Known Activations