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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and words that indicate transitions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancell
    -0.16
     indo
    -0.15
    uto
    -0.15
    uden
    -0.15
    hower
    -0.15
    oss
    -0.14
    person
    -0.14
    OOM
    -0.14
    antal
    -0.14
     Roller
    -0.13
    POSITIVE LOGITS
    ../../../../
    0.15
    RIX
    0.15
     Twin
    0.15
    dac
    0.14
    ErrorHandler
    0.14
    'gc
    0.14
     Ply
    0.14
    NotificationCenter
    0.14
    WSC
    0.13
    è¢ĸ
    0.13
    Act Density 0.024%

    No Known Activations