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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences and product usage over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     crack
    -0.15
     Barr
    -0.14
     Rest
    -0.14
    adi
    -0.14
    cock
    -0.14
     Neg
    -0.14
     Concern
    -0.14
    ãĤ§
    -0.14
    iani
    -0.14
     illegal
    -0.14
    POSITIVE LOGITS
     myself
    0.18
    larım
    0.15
     ìµľê·¼
    0.15
     nonatomic
    0.15
    дÑĥ
    0.15
    esson
    0.14
    arlar
    0.14
    AMAGE
    0.14
    myfile
    0.14
    aign
    0.14
    Act Density 0.122%

    No Known Activations