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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    repeated pronouns, specifically "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Exit
    -0.65
     Thousand
    -0.64
     Benny
    -0.63
     Gran
    -0.62
     Dome
    -0.61
     Friend
    -0.61
     Dayton
    -0.60
     Colonial
    -0.60
    stead
    -0.58
     Advent
    -0.58
    POSITIVE LOGITS
    asca
    0.90
    displayText
    0.86
    self
    0.82
    unes
    0.77
    urses
    0.75
    chy
    0.75
    alian
    0.74
     intends
    0.72
    chwitz
    0.72
     indo
    0.71
    Act Density 0.095%

    No Known Activations