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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laine
    -0.56
     térmica
    -0.55
     Lordships
    -0.55
     líquida
    -0.54
     PAIR
    -0.53
     estimés
    -0.53
     gradova
    -0.52
    StructEnd
    -0.52
     cérami
    -0.52
    kháu
    -0.50
    POSITIVE LOGITS
    UnknownFields
    0.79
    Архівовано
    0.69
    __(/*!
    0.66
    ExtendWith
    0.65
    TRACT
    0.62
     للاسماء
    0.60
    жели
    0.59
     Bux
    0.58
     atra
    0.58
     Weigh
    0.58
    Act Density 0.021%

    No Known Activations