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

    Neuronpedia

    INDEX
    Explanations

    HTML image tags with attributes

    oai_token-act-pair · gemini-2.0-flash

    special characters or formatting in text

    np_token-act-pair-logits · gpt-4o-mini

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "
    -1.39
     “
    -1.30
     „
    -1.12
     «
    -1.11
    ("
    -0.85
     ''
    -0.81
    「
    -0.80
     '
    -0.80
     ‘
    -0.78
    “
    -0.78
    POSITIVE LOGITS
     myſelf
    1.70
     itſelf
    1.70
     Monfieur
    1.52
     pleaſure
    1.48
     ſeveral
    1.45
     raiſ
    1.43
     Efq
    1.42
     Majefty
    1.41
     houſe
    1.41
    ſelf
    1.41
    Act Density 1.922%

    No Known Activations