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

    Neuronpedia

    INDEX
    Explanations

    text related to welcoming and introductions

    oai_token-act-pair · gpt-3.5-turbo

    welcome phrases related to introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.81
    arios
    -0.72
    oyer
    -0.66
    letes
    -0.65
    okia
    -0.65
    matic
    -0.65
     exercised
    -0.63
    umably
    -0.63
     acted
    -0.63
     actresses
    -0.62
    POSITIVE LOGITS
     Subtle
    0.90
     Welcome
    0.86
     Wonderland
    0.84
     another
    0.83
     Democracy
    0.80
     OUR
    0.80
     Anarchy
    0.80
     Fairy
    0.78
     Another
    0.78
     Planet
    0.77
    Act Density 0.096%

    No Known Activations