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

    Neuronpedia

    INDEX
    Explanations

    quantitative descriptions of properties and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.57
    SequentialGroup
    -0.56
     modestly
    -0.48
     немного
    -0.48
    CrossRef
    -0.47
     appreciating
    -0.46
    anterie
    -0.45
     enjoyable
    -0.44
     Moderate
    -0.44
     moderately
    -0.44
    POSITIVE LOGITS
     literally
    0.52
    Literally
    0.48
     raiſ
    0.48
     unbelievably
    0.48
     fevere
    0.47
     ſta
    0.46
    contentLoaded
    0.46
    rzost
    0.46
     ſever
    0.45
    literally
    0.45
    Act Density 0.643%

    No Known Activations