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

    Neuronpedia

    INDEX
    Explanations

    dialogue or conversation phrases

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases and expressions of informal dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulz
    -0.79
    iple
    -0.71
    Versions
    -0.69
    eatures
    -0.69
    etary
    -0.68
    heast
    -0.66
    olves
    -0.65
    Īè
    -0.65
    asters
    -0.65
    ensed
    -0.62
    POSITIVE LOGITS
     yeah
    0.97
     uh
    0.88
     oh
    0.83
     sir
    0.78
     hey
    0.78
     yes
    0.78
     maybe
    0.75
     wow
    0.74
     um
    0.73
     huh
    0.71
    Act Density 0.192%

    No Known Activations