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

    Neuronpedia

    INDEX
    Explanations

    references to everyday life activities or products

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.94
    /***
    -0.65
    HasForeignKey
    -0.64
    lateinit
    -0.59
    CodeDom
    -0.54
    ('=
    -0.54
    adopt
    -0.53
    GenerationType
    -0.53
     reunite
    -0.52
     Ciò
    -0.51
    POSITIVE LOGITS
     everyday
    1.00
     prado
    0.94
     milano
    0.94
     Everyday
    0.93
     pican
    0.89
    Everyday
    0.89
     monaster
    0.88
     Ordinary
    0.88
     ordinary
    0.87
     tramont
    0.86
    Act Density 0.285%

    No Known Activations