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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transitions or progressions in a narrative

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and repetitions of the pronoun "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    package
    -0.65
    holding
    -0.64
    icons
    -0.61
    oles
    -0.59
     ears
    -0.59
    favorite
    -0.58
    quant
    -0.57
    Major
    -0.57
    idon
    -0.56
    animal
    -0.56
    POSITIVE LOGITS
     transpired
    0.98
    chy
    0.96
    iner
    0.91
     seems
    0.91
    unes
    0.89
     mattered
    0.89
     happened
    0.88
     dawn
    0.87
    alian
    0.86
    ueller
    0.84
    Act Density 0.357%

    No Known Activations