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

    Neuronpedia

    INDEX
    Explanations

    names and specific identifying information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to names and their significance or identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vable
    -0.84
    ractical
    -0.80
     resil
    -0.79
     stalls
    -0.78
    issance
    -0.78
    grade
    -0.76
    issions
    -0.75
    alysis
    -0.74
     teaches
    -0.72
    edience
    -0.70
    POSITIVE LOGITS
     initials
    0.88
     nationality
    0.81
    è£
    0.74
     pronouns
    0.74
     trademarks
    0.73
     Uzbek
    0.72
     amen
    0.72
     Tup
    0.71
     Arabic
    0.69
     Whats
    0.69
    Act Density 0.398%

    No Known Activations