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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain significant connectors and punctuation indicating important clauses or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    estimate parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.50
    wpdb
    -0.43
    mentazione
    -0.41
     geleverd
    -0.41
    MethodManager
    -0.41
    tiglia
    -0.39
    úly
    -0.39
    lizia
    -0.39
     Meyers
    -0.38
     spalle
    -0.38
    POSITIVE LOGITS
     chofe
    0.49
     Reſ
    0.48
    parsedMessage
    0.48
     purpoſe
    0.46
     disponibilités
    0.46
     houſe
    0.45
    unnitel
    0.44
    tomorrow
    0.44
    DIPSETTING
    0.44
     pleaſure
    0.44
    Act Density 0.047%

    No Known Activations