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

    Neuronpedia

    INDEX
    Explanations

    sentences with the phrase "did not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or statements about non-confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gems
    -0.71
     horizont
    -0.66
     proportions
    -0.65
     Gone
    -0.65
     Rebellion
    -0.65
     Heads
    -0.64
    ses
    -0.63
     mediocre
    -0.63
     Stories
    -0.63
    tons
    -0.63
    POSITIVE LOGITS
     necessarily
    1.05
    icably
    1.02
     formally
    1.01
     officially
    0.98
    icable
    0.98
     disclose
    0.92
     divul
    0.91
     explicitly
    0.88
     specify
    0.88
     disclosed
    0.87
    Act Density 0.186%

    No Known Activations