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

    Neuronpedia

    INDEX
    Explanations

    greetings

    oai_token-act-pair · gpt-3.5-turbo

    the word "Welcome."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iph
    -0.76
    negie
    -0.74
    iche
    -0.67
    yrus
    -0.67
    ippi
    -0.66
    ive
    -0.66
     bounded
    -0.66
    iii
    -0.65
    ones
    -0.65
    ilib
    -0.65
    POSITIVE LOGITS
    Welcome
    1.17
     Welcome
    1.10
    elcome
    1.09
    ISSION
    0.91
    ãĤ¤ãĥĪ
    0.84
    ISTER
    0.84
    GGGGGGGG
    0.80
    Congratulations
    0.79
    GROUND
    0.75
    bye
    0.75
    Act Density 0.008%

    No Known Activations