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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and relational phrases

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal connection and involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.83
    ancouver
    -0.74
    lihood
    -0.72
    aults
    -0.70
    reens
    -0.69
    itton
    -0.66
    okemon
    -0.66
    neapolis
    -0.65
    Marginal
    -0.65
    vernight
    -0.64
    POSITIVE LOGITS
     Promise
    0.81
    udic
    0.78
     gladly
    0.76
    'm
    0.76
    ona
    0.74
    bara
    0.72
    rish
    0.69
     recommend
    0.69
     am
    0.68
     promise
    0.66
    Act Density 0.335%

    No Known Activations