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

    Neuronpedia

    INDEX
    Explanations

    concepts and terms related to artificial intelligence and machine learning methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLON
    -0.15
    ede
    -0.14
    ìłĪ
    -0.14
    ADDE
    -0.14
    alc
    -0.14
    亮
    -0.14
     bif
    -0.13
    odon
    -0.13
    ekt
    -0.13
    ropdown
    -0.13
    POSITIVE LOGITS
     transfer
    0.22
     domain
    0.19
     Domain
    0.19
    /domain
    0.19
    Domain
    0.19
     Transfer
    0.19
     princip
    0.18
    GAN
    0.18
     transferred
    0.17
    -domain
    0.17
    Act Density 0.021%

    No Known Activations