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

    Neuronpedia

    INDEX
    Explanations

    references to specific academic or scholarly works and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.71
    RefNanny
    -0.60
    Наводи
    -0.59
    majánló
    -0.59
    ########.
    -0.59
    InjectAttribute
    -0.59
     propOrder
    -0.59
    AndEndTag
    -0.57
     esternos
    -0.57
    enderror
    -0.57
    POSITIVE LOGITS
     gut
    0.71
    ner
    0.68
     Gut
    0.55
    NER
    0.55
     butter
    0.53
    gut
    0.52
    Gut
    0.50
     guts
    0.50
     nerves
    0.49
    nerv
    0.49
    Act Density 0.553%

    No Known Activations