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

    Neuronpedia

    INDEX
    Explanations

    references to object-oriented programming concepts and structures

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

    Code or data containing "this" keyword

    np_acts-logits-general · gemini-2.0-flash

    this and as well as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -1.65
     myſelf
    -1.56
     Jefus
    -1.50
    ьаж
    -1.43
     uſed
    -1.43
     poffible
    -1.42
     ſeveral
    -1.39
     raiſ
    -1.39
     purpoſe
    -1.38
    SourceChecksum
    -1.38
    POSITIVE LOGITS
    .
    1.21
    ,
    1.09
     to
    0.92
    :
    0.88
     is
    0.79
     =
    0.77
     as
    0.76
    ;
    0.75
     et
    0.72
     dem
    0.69
    Act Density 0.151%

    No Known Activations