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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical capabilities or performance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scalability and usability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulla
    -0.78
    inas
    -0.75
    sonian
    -0.74
    ergy
    -0.72
    eric
    -0.71
    inis
    -0.69
    lements
    -0.69
    jon
    -0.68
    yton
    -0.66
    stad
    -0.66
    POSITIVE LOGITS
     mismatch
    1.02
    anship
    0.91
    ability
    0.90
     assurance
    0.88
    iencies
    0.84
    worthiness
    0.84
     parity
    0.84
    iqueness
    0.82
    orously
    0.82
    ulner
    0.79
    Act Density 0.075%

    No Known Activations