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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of addition or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAL
    -0.17
    abal
    -0.17
    rze
    -0.15
     ngoại
    -0.15
    auc
    -0.14
    nonce
    -0.14
    xico
    -0.14
    onen
    -0.14
    imestep
    -0.14
    uate
    -0.13
    POSITIVE LOGITS
    adera
    0.16
    zyst
    0.15
    ording
    0.15
    adier
    0.15
     being
    0.15
    andes
    0.15
    ocket
    0.15
    cci
    0.15
    izers
    0.14
    _As
    0.14
    Act Density 0.055%

    No Known Activations