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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for confirmation or validation

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to personal identity or membership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shutterstock
    -0.80
    backs
    -0.74
    soever
    -0.69
     Springer
    -0.69
     hoops
    -0.68
    back
    -0.67
     paced
    -0.67
    bourg
    -0.66
    erton
    -0.66
     Canaver
    -0.65
    POSITIVE LOGITS
     existence
    1.44
     authenticity
    1.37
     validity
    1.33
     legitimacy
    1.22
     innocence
    1.17
    worthiness
    1.04
     presence
    1.01
    iability
    0.96
     importance
    0.96
     accuracy
    0.96
    Act Density 0.247%

    No Known Activations