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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and possibly locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.80
    الحياه
    -0.71
     autorytatywna
    -0.70
     CanadaChoose
    -0.69
     vulgaires
    -0.65
    GEBURTSDATUM
    -0.65
     препратки
    -0.63
     distanciation
    -0.62
    úgó
    -0.62
    kuuta
    -0.61
    POSITIVE LOGITS
    <bos>
    0.65
    BatchNorm
    0.58
     McC
    0.55
     actionMode
    0.54
     Ko
    0.53
     cellpadding
    0.53
     MonoBehaviour
    0.50
    McC
    0.50
     Mer
    0.50
     Mc
    0.49
    Act Density 0.312%

    No Known Activations