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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and parentheses in the text

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

    SQL queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.93
    parsedMessage
    -0.90
    ſelves
    -0.88
     indígen
    -0.87
     queſta
    -0.86
    ſelf
    -0.84
     increí
    -0.84
     pleaſure
    -0.82
     ProtoMessage
    -0.77
     ſeine
    -0.77
    POSITIVE LOGITS
    “
    0.44
     "
    0.41
    ("
    0.39
     “
    0.38
    !("
    0.35
     x
    0.34
     $
    0.33
     
    0.33
    !
    0.33
     query
    0.32
    Act Density 0.005%

    No Known Activations