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

    Neuronpedia

    INDEX
    Explanations

    statements emphasizing a particular aspect in a given context

    oai_token-act-pair · gpt-3.5-turbo

    statements that express significant importance or severity of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     superiority
    -0.69
     inev
    -0.65
     overwhelming
    -0.64
     endlessly
    -0.62
     endless
    -0.62
     interstellar
    -0.61
     unstoppable
    -0.61
     irresistible
    -0.60
     eternity
    -0.60
     civilisation
    -0.59
    POSITIVE LOGITS
    20439
    0.78
    zb
    0.72
    rings
    0.72
     insofar
    0.69
    iary
    0.68
    iaries
    0.67
     Cases
    0.65
    outheast
    0.64
    amazon
    0.63
     because
    0.63
    Act Density 0.179%

    No Known Activations