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

    Neuronpedia

    INDEX
    Explanations

    standard terms and acronyms, especially in technical or scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    capital letters at the beginning of words

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

    Letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.24
     Theſe
    -1.23
     itſelf
    -1.23
     Reſ
    -1.17
     Houſe
    -1.16
     Majefty
    -1.12
    ſelves
    -1.10
     Efq
    -1.09
     ―――――
    -1.06
    ſelf
    -1.04
    POSITIVE LOGITS
     M
    1.02
     H
    1.01
     D
    0.98
     L
    0.97
     G
    0.96
     F
    0.95
     S
    0.91
     R
    0.90
     W
    0.90
     T
    0.89
    Act Density 15.900%

    No Known Activations