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

    Neuronpedia

    INDEX
    Explanations

    mentions of greatness or importance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "great" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clips
    -0.89
    ople
    -0.88
    rette
    -0.72
    phrine
    -0.72
    CHAT
    -0.69
    chedel
    -0.69
    eters
    -0.68
     Leilan
    -0.68
    utical
    -0.68
    ptives
    -0.68
    POSITIVE LOGITS
    sword
    1.12
     strides
    0.91
     apes
    0.81
     grandson
    0.78
    reek
    0.77
     antiquity
    0.76
     importance
    0.76
     Dane
    0.75
     proportions
    0.75
     pains
    0.75
    Act Density 0.035%

    No Known Activations