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

    Neuronpedia

    INDEX
    Explanations

    documentation comments and annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asing
    -0.16
    ict
    -0.14
     dil
    -0.14
    abouts
    -0.14
    men
    -0.14
    ery
    -0.14
    lings
    -0.14
     Ago
    -0.14
     bil
    -0.14
    ability
    -0.13
    POSITIVE LOGITS
     Note
    0.19
     note
    0.19
    yw
    0.17
     porr
    0.15
     NOTE
    0.15
    Note
    0.15
    937
    0.15
    841
    0.14
    874
    0.14
    377
    0.14
    Act Density 0.033%

    No Known Activations