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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.63
    LookAnd
    -0.62
     tartalomajánló
    -0.60
     ویکی‌پدی
    -0.59
    afficheront
    -0.57
     iprot
    -0.56
     للاسماء
    -0.55
    AISSEE
    -0.54
     Biôgrafia
    -0.54
    ikyuu
    -0.52
    POSITIVE LOGITS
    zelfde
    0.60
     same
    0.56
     way
    0.50
     particular
    0.49
     cual
    0.44
     cuál
    0.43
     pesky
    0.41
    ched
    0.41
    assertThat
    0.40
    ching
    0.40
    Act Density 0.667%

    No Known Activations