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

    Neuronpedia

    INDEX
    Explanations

    method definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conv
    -0.16
    ale
    -0.16
    ammer
    -0.15
    ancing
    -0.15
     special
    -0.15
     Mey
    -0.14
    ,
    -0.14
     chapter
    -0.14
    _INTR
    -0.14
     habit
    -0.14
    POSITIVE LOGITS
    agi
    0.18
     پاس
    0.16
    (___
    0.14
    æ£ļ
    0.14
    oupper
    0.14
    ома
    0.13
     UIF
    0.13
    egas
    0.13
    _LEG
    0.13
    íı¬
    0.13
    Act Density 0.004%

    No Known Activations