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

    Neuronpedia

    INDEX
    Explanations

    misspelled words

    oai_token-act-pair · gpt-3.5-turbo

    misspellings and grammatical errors in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.79
    tnc
    -0.76
    Progress
    -0.75
    worms
    -0.74
    HQ
    -0.73
     resil
    -0.72
    progress
    -0.70
    uala
    -0.69
    gui
    -0.68
    velt
    -0.68
    POSITIVE LOGITS
     pronoun
    1.17
     spelling
    1.14
     plural
    1.11
     phrase
    1.10
     noun
    1.10
     phrases
    1.08
     ital
    1.06
     spelled
    1.05
     slang
    1.02
     verb
    1.02
    Act Density 0.581%

    No Known Activations