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

    Neuronpedia

    INDEX
    Explanations

    phone numbers and email addresses

    oai_token-act-pair · gemini-2.0-flash

    punctuation and programming symbols

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

    phone numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.20
    AnchorStyles
    -1.16
    CloseOperation
    -1.12
    ſelf
    -1.11
    Билгалдахарш
    -1.09
     CreateTagHelper
    -1.09
     Jefus
    -1.05
     pleaſure
    -1.00
     ſtate
    -1.00
     purpoſe
    -1.00
    POSITIVE LOGITS
     or
    0.59
     on
    0.59
    ,
    0.57
    .
    0.53
     c
    0.53
     if
    0.49
     C
    0.47
     the
    0.45
     P
    0.45
     N
    0.45
    Act Density 2.584%

    No Known Activations