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

    Neuronpedia

    INDEX
    Explanations

    references to units or components within a system or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SGS
    -0.72
    -0.70
     Chry
    -0.67
     Gog
    -0.67
     GOS
    -0.67
    ']?>
    -0.67
    rhe
    -0.66
     JAS
    -0.65
    ">//
    -0.65
    helves
    -0.64
    POSITIVE LOGITS
     units
    1.64
     unit
    1.58
    units
    1.52
     Units
    1.51
     UNIT
    1.50
    unit
    1.47
     Unit
    1.47
    Units
    1.47
    UNIT
    1.40
     UNITS
    1.36
    Act Density 0.046%

    No Known Activations