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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating growth or development

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "grow" and its variations, indicating development or change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.78
    oute
    -0.78
    ioned
    -0.72
    ãĥīãĥ©
    -0.71
    esson
    -0.68
    pta
    -0.65
    arted
    -0.64
    perse
    -0.64
    rolled
    -0.63
    isites
    -0.62
    POSITIVE LOGITS
     promot
    0.89
     exponentially
    0.88
     pains
    0.78
     accustomed
    0.74
     stronger
    0.70
    aroo
    0.69
     explos
    0.69
     closer
    0.67
    nir
    0.67
    icult
    0.65
    Act Density 0.040%

    No Known Activations