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

    Neuronpedia

    INDEX
    Explanations

    references to previously mentioned or discussed items and details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickle
    -0.15
    arus
    -0.15
    endoza
    -0.15
    aras
    -0.15
     Cumberland
    -0.14
    version
    -0.14
     noticed
    -0.14
    suma
    -0.14
    ettle
    -0.14
    _Version
    -0.14
    POSITIVE LOGITS
     elsewhere
    0.28
     below
    0.27
     above
    0.25
    below
    0.23
     вÑĭÑĪе
    0.23
     ниже
    0.23
    above
    0.23
     earlier
    0.22
     later
    0.20
    Else
    0.19
    Act Density 0.159%

    No Known Activations